{"releases":[{"id":422387962,"tag":"v1.19.0","author":"timothycarambat","name":"AnythingLLM v1.19.0","draft":false,"prerelease":false,"createdAt":"2026-10-25T18:20:42Z","publishedAt":"2026-10-26T16:14:51Z","markdown":"### Built-in LLM for Docker\r\n<img width=\"3680\" height=\"2212\" alt=\"AnythingLLM Docker built-in LLM powered by Lemonade and llama.cpp\" src=\"https://github.com/user-attachments/assets/410b5784-ca15-4027-a1c4-056d9d5c748e\" />\r\n\r\nAnythingLLM Docker now has a default local LLM experience right out of the box. The same kind of built-in engine that ships with [AnythingLLM Desktop](https://docs.anythingllm.com/setup/llm-configuration/local/built-in) can now run **inside the container**: [Lemonade](https://lemonade-server.ai), the fully [open-source](https://github.com/lemonade-sdk/lemonade) local inference server from AMD, running your models with [llama.cpp](https://github.com/ggml-org/llama.cpp). You no longer need to run Ollama, LM Studio or any other inference server next to AnythingLLM.\r\n\r\nPass your GPU into the container and the engine is accelerated on whatever hardware you have. It picks the fastest backend automatically: CUDA for NVIDIA GPUs, Vulkan for AMD and Intel GPUs, or the CPU. It runs on both `amd64` and `arm64` hosts.\r\n\r\nWhen it's turned on, **Built-in** becomes the default LLM provider during onboarding, with three models recommended for your hardware. You can download any model from the model table or pull any GGUF model from Hugging Face. It works everywhere a provider can be used: the system LLM, workspace and agent LLMs, the chat window model picker, and [Model Router](https://docs.anythingllm.com/model-router/setup).\r\n\r\n> [!TIP]\r\n> **The built-in LLM is off by default.** Turn it on by starting the container with `-e ENABLE_BUILT_IN_LLM=true`, and add `--gpus all` (or pass in your AMD or Intel GPU devices) for GPU acceleration. See [Built-in LLM for Docker](https://docs.anythingllm.com/installation-docker/built-in-llm) for the full setup for each kind of hardware.\r\n\r\n### Color palettes\r\n\r\nColor palettes are straightforward thematic tinting you can apply to the entire UI. We plan to expand this functionality more so you can more heavily customize the UI and even layout. [Learn more](https://docs.anythingllm.com/features/branding)\r\n\r\n<table>\r\n  <tr>\r\n    <td><img width=\"100%\" alt=\"Ocean color palette\" src=\"https://github.com/user-attachments/assets/08c2baa2-9a9b-4ecd-ae95-88e88175ffe5\" /></td>\r\n    <td><img width=\"100%\" alt=\"Forest color palette\" src=\"https://github.com/user-attachments/assets/4274998a-dba8-490e-ab5d-9faecf9248c4\" /></td>\r\n  </tr>\r\n  <tr>\r\n    <td><img width=\"100%\" alt=\"Plum color palette\" src=\"https://github.com/user-attachments/assets/214c3571-7d72-4111-bf08-ce3d60ff1b99\" /></td>\r\n    <td><img width=\"100%\" alt=\"Ember color palette\" src=\"https://github.com/user-attachments/assets/88449231-139c-40a3-bb49-135bd0f1e9fa\" /></td>\r\n  </tr>\r\n</table>\r\n\r\n----\r\n\r\n## What's Changed\r\n* fix: route Bedrock India (in.) inference profiles via bedrock-runtime by @kimnamu in https://github.com/Mintplex-Labs/anything-llm/pull/6717\r\n* Remove open-computer (moved to its own repo) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6727\r\n* Neutralize spreadsheet formulas in CSV chat exports by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6728\r\n* Cap request body size to prevent unauthenticated embed DoS by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6729\r\n* feat: show notice when response hits max output token limit (#6703) by @ManojDevarajulu in https://github.com/Mintplex-Labs/anything-llm/pull/6726\r\n* Hold clarifying-question timeout once the user starts answering by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6730\r\n* Move Weaviate to weaviate-client v3 by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6675\r\n* Support .mov files for transcription by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6721\r\n* Stop system prompt variable values from expanding other placeholders by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6731\r\n* Apply workspace model changes to agent sessions mid-thread by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6673\r\n* Show per-file embed progress in context overflow modal by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6639\r\n* fix: include email body/recipients and job prompt in tool approval requests by @rtmalikian in https://github.com/Mintplex-Labs/anything-llm/pull/6732\r\n* fix: send the full GitLab branch name when fetching repository files by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6740\r\n* fix: return MCP tool text without the result envelope by @Sairaj-24 in https://github.com/Mintplex-Labs/anything-llm/pull/6736\r\n* Fix prompt compressor crash on history records skipped by convertToPromptHistory (#6737) by @ManojDevarajulu in https://github.com/Mintplex-Labs/anything-llm/pull/6738\r\n* fix: keep current-turn attachments when the string compressor runs by @devYRPauli in https://github.com/Mintplex-Labs/anything-llm/pull/6742\r\n* Stop sending deprecated sampling and thinking params to Gemini by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6733\r\n* fix: count the text of messages with attachments in statsFrom by @devYRPauli in https://github.com/Mintplex-Labs/anything-llm/pull/6745\r\n* Built-in LLM for Docker (embedded_lemonade) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6719\r\n* fix: truncate long citation URLs in the detail modal by @leilei3167 in https://github.com/Mintplex-Labs/anything-llm/pull/6781\r\n* fix: default OpenAI image generation to gpt-image-2.5-flare by @rtmalikian in https://github.com/Mintplex-Labs/anything-llm/pull/6780\r\n* fix: keep conversation history when the OpenAI compatible chat prompt is compressed by @MarMarLabs in https://github.com/Mintplex-Labs/anything-llm/pull/6777\r\n* fix: tell the user why a password reset was refused by @MarMarLabs in https://github.com/Mintplex-Labs/anything-llm/pull/6771\r\n* fix: report empty connector imports as failures by @MarMarLabs in https://github.com/Mintplex-Labs/anything-llm/pull/6775\r\n* fix(telegram): preserve complete agent answers across message chunks by @jianyx1 in https://github.com/Mintplex-Labs/anything-llm/pull/6767\r\n* fix: connect to the document collector on 127.0.0.1 by @leilei3167 in https://github.com/Mintplex-Labs/anything-llm/pull/6766\r\n* chore: drop API key fragments from web search error messages by @u00dxk2 in https://github.com/Mintplex-Labs/anything-llm/pull/6763\r\n* fix: crash on workspace chat settings when saved LLM provider is not in the list yet by @TMelik in https://github.com/Mintplex-Labs/anything-llm/pull/6761\r\n* docs: remove references to removed sqlite:migrate script by @jrlprost in https://github.com/Mintplex-Labs/anything-llm/pull/6759\r\n* fix(collector): read Excel's short date as an ISO date by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6758\r\n* Add Hungarian (hu) translation by @Proxy5 in https://github.com/Mintplex-Labs/anything-llm/pull/6757\r\n* fix: keep a CRLF file's line endings in filesystem-edit-file by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6756\r\n* Parse PDF and file links in the bulk link scraper by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6786\r\n* fix(a11y): announce a reply once it has finished streaming by @opensource-joe in https://github.com/Mintplex-Labs/anything-llm/pull/6752\r\n* fix: use the repository default branch in the GitHub connector by @Enesuygurs in https://github.com/Mintplex-Labs/anything-llm/pull/6800\r\n* fix(paperless-ngx): keep plain-text document content as it is instead of reading it as HTML by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6795\r\n* fix(confluence): keep code blocks as written instead of running them through htmlToText by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6794\r\n* fix: report failed workspace embeds on API document uploads by @Tong-bit-art in https://github.com/Mintplex-Labs/anything-llm/pull/6793\r\n* fix: regenerate and edit should still count toward daily message limit by @jrlprost in https://github.com/Mintplex-Labs/anything-llm/pull/6785\r\n* fix: isolate watched document sync failures by @Tong-bit-art in https://github.com/Mintplex-Labs/anything-llm/pull/6804\r\n* fix(mcp): treat unsupported ping as non-fatal so servers stay usable by @rtmalikian in https://github.com/Mintplex-Labs/anything-llm/pull/6805\r\n* fix: fall back to default chunk overlap when it is not smaller than the chunk size by @RaphaelFakhri in https://github.com/Mintplex-Labs/anything-llm/pull/6811\r\n* fix: use the repository default branch in the GitLab and Gitea connectors by @JoAdo07 in https://github.com/Mintplex-Labs/anything-llm/pull/6809\r\n* fix: preserve daily message quota when deleting threads by @Max-Reisinger in https://github.com/Mintplex-Labs/anything-llm/pull/6814\r\n* fix(ollama): keep context windows when one model show fails by @leilei3167 in https://github.com/Mintplex-Labs/anything-llm/pull/6816\r\n* feat: instance color palettes and tabbed branding settings by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6796\r\n* chore: bump version to 1.19.0 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6822\r\n* fix(mistral): support Mistral reasoning models, dedupe model list, add thinking toggle (#6821) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6825\r\n\r\n## New Contributors\r\n* @ManojDevarajulu made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6726\r\n* @rtmalikian made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6732\r\n* @Sairaj-24 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6736\r\n* @devYRPauli made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6742\r\n* @jianyx1 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6767\r\n* @TMelik made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6761\r\n* @jrlprost made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6759\r\n* @Proxy5 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6757\r\n* @Enesuygurs made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6800\r\n* @Tong-bit-art made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6793\r\n* @RaphaelFakhri made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6811\r\n* @JoAdo07 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6809\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.18.0...v1.19.0","html":"<div class=\"markdown-heading\"><h3 class=\"heading-element\">Built-in LLM for Docker</h3><a id=\"user-content-built-in-llm-for-docker\" class=\"anchor\" aria-label=\"Permalink: Built-in LLM for Docker\" href=\"#built-in-llm-for-docker\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/410b5784-ca15-4027-a1c4-056d9d5c748e\"><img width=\"2000\" height=\"1202\" alt=\"AnythingLLM Docker built-in LLM powered by Lemonade and llama.cpp\" src=\"https://github.com/user-attachments/assets/410b5784-ca15-4027-a1c4-056d9d5c748e\" style=\"max-width: 100%; height: auto; max-height: 1202px;\"></a></p>\n<p>AnythingLLM Docker now has a default local LLM experience right out of the box. The same kind of built-in engine that ships with <a href=\"https://docs.anythingllm.com/setup/llm-configuration/local/built-in\" rel=\"nofollow\">AnythingLLM Desktop</a> can now run <strong>inside the container</strong>: <a href=\"https://lemonade-server.ai\" rel=\"nofollow\">Lemonade</a>, the fully <a href=\"https://github.com/lemonade-sdk/lemonade\">open-source</a> local inference server from AMD, running your models with <a href=\"https://github.com/ggml-org/llama.cpp\">llama.cpp</a>. You no longer need to run Ollama, LM Studio or any other inference server next to AnythingLLM.</p>\n<p>Pass your GPU into the container and the engine is accelerated on whatever hardware you have. It picks the fastest backend automatically: CUDA for NVIDIA GPUs, Vulkan for AMD and Intel GPUs, or the CPU. It runs on both <code>amd64</code> and <code>arm64</code> hosts.</p>\n<p>When it's turned on, <strong>Built-in</strong> becomes the default LLM provider during onboarding, with three models recommended for your hardware. You can download any model from the model table or pull any GGUF model from Hugging Face. It works everywhere a provider can be used: the system LLM, workspace and agent LLMs, the chat window model picker, and <a href=\"https://docs.anythingllm.com/model-router/setup\" rel=\"nofollow\">Model Router</a>.</p>\n<blockquote>\n<p>[!TIP]\n<strong>The built-in LLM is off by default.</strong> Turn it on by starting the container with <code>-e ENABLE_BUILT_IN_LLM=true</code>, and add <code>--gpus all</code> (or pass in your AMD or Intel GPU devices) for GPU acceleration. See <a href=\"https://docs.anythingllm.com/installation-docker/built-in-llm\" rel=\"nofollow\">Built-in LLM for Docker</a> for the full setup for each kind of hardware.</p>\n</blockquote>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Color palettes</h3><a id=\"user-content-color-palettes\" class=\"anchor\" aria-label=\"Permalink: Color palettes\" href=\"#color-palettes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Color palettes are straightforward thematic tinting you can apply to the entire UI. We plan to expand this functionality more so you can more heavily customize the UI and even layout. <a href=\"https://docs.anythingllm.com/features/branding\" rel=\"nofollow\">Learn more</a></p>\n<table>\n  <tbody><tr>\n    <td><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/08c2baa2-9a9b-4ecd-ae95-88e88175ffe5\"><img width=\"100%\" alt=\"Ocean color palette\" src=\"https://github.com/user-attachments/assets/08c2baa2-9a9b-4ecd-ae95-88e88175ffe5\" style=\"max-width: 100%;\"></a></td>\n    <td><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/4274998a-dba8-490e-ab5d-9faecf9248c4\"><img width=\"100%\" alt=\"Forest color palette\" src=\"https://github.com/user-attachments/assets/4274998a-dba8-490e-ab5d-9faecf9248c4\" style=\"max-width: 100%;\"></a></td>\n  </tr>\n  <tr>\n    <td><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/214c3571-7d72-4111-bf08-ce3d60ff1b99\"><img width=\"100%\" alt=\"Plum color palette\" src=\"https://github.com/user-attachments/assets/214c3571-7d72-4111-bf08-ce3d60ff1b99\" style=\"max-width: 100%;\"></a></td>\n    <td><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/88449231-139c-40a3-bb49-135bd0f1e9fa\"><img width=\"100%\" alt=\"Ember color palette\" src=\"https://github.com/user-attachments/assets/88449231-139c-40a3-bb49-135bd0f1e9fa\" style=\"max-width: 100%;\"></a></td>\n  </tr>\n</tbody></table>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix: route Bedrock India (in.) inference profiles via bedrock-runtime by @kimnamu in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6717\">https://github.com/Mintplex-Labs/anything-llm/pull/6717</a>\n</li>\n<li>Remove open-computer (moved to its own repo) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6727\">https://github.com/Mintplex-Labs/anything-llm/pull/6727</a>\n</li>\n<li>Neutralize spreadsheet formulas in CSV chat exports by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6728\">https://github.com/Mintplex-Labs/anything-llm/pull/6728</a>\n</li>\n<li>Cap request body size to prevent unauthenticated embed DoS by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6729\">https://github.com/Mintplex-Labs/anything-llm/pull/6729</a>\n</li>\n<li>feat: show notice when response hits max output token limit (#6703) by @ManojDevarajulu in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6726\">https://github.com/Mintplex-Labs/anything-llm/pull/6726</a>\n</li>\n<li>Hold clarifying-question timeout once the user starts answering by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6730\">https://github.com/Mintplex-Labs/anything-llm/pull/6730</a>\n</li>\n<li>Move Weaviate to weaviate-client v3 by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6675\">https://github.com/Mintplex-Labs/anything-llm/pull/6675</a>\n</li>\n<li>Support .mov files for transcription by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6721\">https://github.com/Mintplex-Labs/anything-llm/pull/6721</a>\n</li>\n<li>Stop system prompt variable values from expanding other placeholders by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6731\">https://github.com/Mintplex-Labs/anything-llm/pull/6731</a>\n</li>\n<li>Apply workspace model changes to agent sessions mid-thread by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6673\">https://github.com/Mintplex-Labs/anything-llm/pull/6673</a>\n</li>\n<li>Show per-file embed progress in context overflow modal by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6639\">https://github.com/Mintplex-Labs/anything-llm/pull/6639</a>\n</li>\n<li>fix: include email body/recipients and job prompt in tool approval requests by @rtmalikian in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6732\">https://github.com/Mintplex-Labs/anything-llm/pull/6732</a>\n</li>\n<li>fix: send the full GitLab branch name when fetching repository files by @MohammadHijjawi97 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6740\">https://github.com/Mintplex-Labs/anything-llm/pull/6740</a>\n</li>\n<li>fix: return MCP tool text without the result envelope by @Sairaj-24 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6736\">https://github.com/Mintplex-Labs/anything-llm/pull/6736</a>\n</li>\n<li>Fix prompt compressor crash on history records skipped by convertToPromptHistory (#6737) by @ManojDevarajulu in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6738\">https://github.com/Mintplex-Labs/anything-llm/pull/6738</a>\n</li>\n<li>fix: keep current-turn attachments when the string compressor runs by @devYRPauli in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6742\">https://github.com/Mintplex-Labs/anything-llm/pull/6742</a>\n</li>\n<li>Stop sending deprecated sampling and thinking params to Gemini by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6733\">https://github.com/Mintplex-Labs/anything-llm/pull/6733</a>\n</li>\n<li>fix: count the text of messages with attachments in statsFrom by @devYRPauli in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6745\">https://github.com/Mintplex-Labs/anything-llm/pull/6745</a>\n</li>\n<li>Built-in LLM for Docker (embedded_lemonade) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6719\">https://github.com/Mintplex-Labs/anything-llm/pull/6719</a>\n</li>\n<li>fix: truncate long citation URLs in the detail modal by @leilei3167 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6781\">https://github.com/Mintplex-Labs/anything-llm/pull/6781</a>\n</li>\n<li>fix: default OpenAI image generation to gpt-image-2.5-flare by @rtmalikian in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6780\">https://github.com/Mintplex-Labs/anything-llm/pull/6780</a>\n</li>\n<li>fix: keep conversation history when the OpenAI compatible chat prompt is compressed by @MarMarLabs in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6777\">https://github.com/Mintplex-Labs/anything-llm/pull/6777</a>\n</li>\n<li>fix: tell the user why a password reset was refused by @MarMarLabs in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6771\">https://github.com/Mintplex-Labs/anything-llm/pull/6771</a>\n</li>\n<li>fix: report empty connector imports as failures by @MarMarLabs in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6775\">https://github.com/Mintplex-Labs/anything-llm/pull/6775</a>\n</li>\n<li>fix(telegram): preserve complete agent answers across message chunks by @jianyx1 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6767\">https://github.com/Mintplex-Labs/anything-llm/pull/6767</a>\n</li>\n<li>fix: connect to the document collector on 127.0.0.1 by @leilei3167 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6766\">https://github.com/Mintplex-Labs/anything-llm/pull/6766</a>\n</li>\n<li>chore: drop API key fragments from web search error messages by @u00dxk2 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6763\">https://github.com/Mintplex-Labs/anything-llm/pull/6763</a>\n</li>\n<li>fix: crash on workspace chat settings when saved LLM provider is not in the list yet by @TMelik in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6761\">https://github.com/Mintplex-Labs/anything-llm/pull/6761</a>\n</li>\n<li>docs: remove references to removed sqlite:migrate script by @jrlprost in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6759\">https://github.com/Mintplex-Labs/anything-llm/pull/6759</a>\n</li>\n<li>fix(collector): read Excel's short date as an ISO date by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6758\">https://github.com/Mintplex-Labs/anything-llm/pull/6758</a>\n</li>\n<li>Add Hungarian (hu) translation by @Proxy5 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6757\">https://github.com/Mintplex-Labs/anything-llm/pull/6757</a>\n</li>\n<li>fix: keep a CRLF file's line endings in filesystem-edit-file by @MohammadHijjawi97 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6756\">https://github.com/Mintplex-Labs/anything-llm/pull/6756</a>\n</li>\n<li>Parse PDF and file links in the bulk link scraper by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6786\">https://github.com/Mintplex-Labs/anything-llm/pull/6786</a>\n</li>\n<li>fix(a11y): announce a reply once it has finished streaming by @opensource-joe in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6752\">https://github.com/Mintplex-Labs/anything-llm/pull/6752</a>\n</li>\n<li>fix: use the repository default branch in the GitHub connector by @Enesuygurs in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6800\">https://github.com/Mintplex-Labs/anything-llm/pull/6800</a>\n</li>\n<li>fix(paperless-ngx): keep plain-text document content as it is instead of reading it as HTML by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6795\">https://github.com/Mintplex-Labs/anything-llm/pull/6795</a>\n</li>\n<li>fix(confluence): keep code blocks as written instead of running them through htmlToText by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6794\">https://github.com/Mintplex-Labs/anything-llm/pull/6794</a>\n</li>\n<li>fix: report failed workspace embeds on API document uploads by @Tong-bit-art in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6793\">https://github.com/Mintplex-Labs/anything-llm/pull/6793</a>\n</li>\n<li>fix: regenerate and edit should still count toward daily message limit by @jrlprost in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6785\">https://github.com/Mintplex-Labs/anything-llm/pull/6785</a>\n</li>\n<li>fix: isolate watched document sync failures by @Tong-bit-art in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6804\">https://github.com/Mintplex-Labs/anything-llm/pull/6804</a>\n</li>\n<li>fix(mcp): treat unsupported ping as non-fatal so servers stay usable by @rtmalikian in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6805\">https://github.com/Mintplex-Labs/anything-llm/pull/6805</a>\n</li>\n<li>fix: fall back to default chunk overlap when it is not smaller than the chunk size by @RaphaelFakhri in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6811\">https://github.com/Mintplex-Labs/anything-llm/pull/6811</a>\n</li>\n<li>fix: use the repository default branch in the GitLab and Gitea connectors by @JoAdo07 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6809\">https://github.com/Mintplex-Labs/anything-llm/pull/6809</a>\n</li>\n<li>fix: preserve daily message quota when deleting threads by @Max-Reisinger in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6814\">https://github.com/Mintplex-Labs/anything-llm/pull/6814</a>\n</li>\n<li>fix(ollama): keep context windows when one model show fails by @leilei3167 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6816\">https://github.com/Mintplex-Labs/anything-llm/pull/6816</a>\n</li>\n<li>feat: instance color palettes and tabbed branding settings by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6796\">https://github.com/Mintplex-Labs/anything-llm/pull/6796</a>\n</li>\n<li>chore: bump version to 1.19.0 by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6822\">https://github.com/Mintplex-Labs/anything-llm/pull/6822</a>\n</li>\n<li>fix(mistral): support Mistral reasoning models, dedupe model list, add thinking toggle (#6821) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6825\">https://github.com/Mintplex-Labs/anything-llm/pull/6825</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@ManojDevarajulu made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6726\">https://github.com/Mintplex-Labs/anything-llm/pull/6726</a>\n</li>\n<li>@rtmalikian made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6732\">https://github.com/Mintplex-Labs/anything-llm/pull/6732</a>\n</li>\n<li>@Sairaj-24 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6736\">https://github.com/Mintplex-Labs/anything-llm/pull/6736</a>\n</li>\n<li>@devYRPauli made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6742\">https://github.com/Mintplex-Labs/anything-llm/pull/6742</a>\n</li>\n<li>@jianyx1 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6767\">https://github.com/Mintplex-Labs/anything-llm/pull/6767</a>\n</li>\n<li>@TMelik made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6761\">https://github.com/Mintplex-Labs/anything-llm/pull/6761</a>\n</li>\n<li>@jrlprost made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6759\">https://github.com/Mintplex-Labs/anything-llm/pull/6759</a>\n</li>\n<li>@Proxy5 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6757\">https://github.com/Mintplex-Labs/anything-llm/pull/6757</a>\n</li>\n<li>@Enesuygurs made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6800\">https://github.com/Mintplex-Labs/anything-llm/pull/6800</a>\n</li>\n<li>@Tong-bit-art made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6793\">https://github.com/Mintplex-Labs/anything-llm/pull/6793</a>\n</li>\n<li>@RaphaelFakhri made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6811\">https://github.com/Mintplex-Labs/anything-llm/pull/6811</a>\n</li>\n<li>@JoAdo07 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6809\">https://github.com/Mintplex-Labs/anything-llm/pull/6809</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.18.0...v1.19.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.18.0...v1.19.0</a></p>\n","assets":[{"contentType":"application/octet-stream","size":633799570,"createdAt":"2026-10-25T20:07:31Z","updatedAt":"2026-10-25T20:07:49Z","downloadCount":445,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":501534408,"createdAt":"2026-10-25T20:06:03Z","updatedAt":"2026-10-25T20:06:17Z","downloadCount":604,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":584275091,"createdAt":"2026-10-25T20:06:17Z","updatedAt":"2026-10-25T20:06:35Z","downloadCount":1397,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":905441828,"createdAt":"2026-10-25T20:06:35Z","updatedAt":"2026-10-25T20:07:00Z","downloadCount":1698,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":550006618,"createdAt":"2026-10-25T20:07:00Z","updatedAt":"2026-10-25T20:07:17Z","downloadCount":450,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":403299096,"createdAt":"2026-10-25T20:07:17Z","updatedAt":"2026-10-25T20:07:31Z","downloadCount":11187,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":23552,"createdAt":"2026-10-25T20:06:35Z","updatedAt":"2026-10-25T20:06:35Z","downloadCount":204,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.19.0/installer.sh"}]},{"id":411049484,"tag":"v1.18.0","author":"timothycarambat","name":"AnythingLLM v1.18.0","draft":false,"prerelease":false,"createdAt":"2026-10-12T22:37:02Z","publishedAt":"2026-10-13T16:15:52Z","markdown":"\r\n## What's Changed\r\n* fix: point k8s probes at the server's /api/ping by @u00dxk2 in https://github.com/Mintplex-Labs/anything-llm/pull/6592\r\n* fix: don't crash when removing a parsed file while an image is attached by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6585\r\n* fix: open the clicked image when attachments share a file name by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6586\r\n* fix: stop sending history attachments to providers that build prompts from raw chat history by @simonether in https://github.com/Mintplex-Labs/anything-llm/pull/6591\r\n* fix: compare embed allowlist entries as browser origins by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6584\r\n* add dismissal comment to prevent low-effort research claims by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6608\r\n* fix: send agent tool required params on every provider path by @wenqiw777 in https://github.com/Mintplex-Labs/anything-llm/pull/6595\r\n* fix: honor the SDK retry count when ANYTHINGLLM_MAX_RETRIES is set by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6597\r\n* fix: save the Outlook account type so sign-in uses the right tenant by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6599\r\n* fix: show an error when a system prompt variable change fails by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6604\r\n* fix: apply TOOL_CALL_APPROVAL_TIMEOUT_MS to Telegram tool approvals by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6601\r\n* fix: convert the hourly schedule minute to UTC in half-hour time zones by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6605\r\n* fix: select entire folder after upload when picker is paginated by @YokoAC in https://github.com/Mintplex-Labs/anything-llm/pull/6610\r\n* fix: keep numeric strings over 15 digits as text in created Excel files by @deepanshupal in https://github.com/Mintplex-Labs/anything-llm/pull/6613\r\n* fix: restore dropped i18n placeholders in MCP and profile strings by @theluckystrike in https://github.com/Mintplex-Labs/anything-llm/pull/6614\r\n* fix: scrape each page once when bulk links differ only by #fragment by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6619\r\n* fix: attach requested files to Outlook replies and reply drafts by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6623\r\n* fix: return 404 for an unknown workspace on manage-users and update-pin by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6625\r\n* fix: load the next page of documents from the server's offset in the picker by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6628\r\n* fix: show an error when embedding attached files into the workspace fails by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6629\r\n* fix: restore dropped i18n values in model router and model picker strings by @theluckystrike in https://github.com/Mintplex-Labs/anything-llm/pull/6631\r\n* fix: preserve referenced MBOX chat attachments during orphan cleanup by @dakjdakd in https://github.com/Mintplex-Labs/anything-llm/pull/6633\r\n* fix: isolate chat attachment state and uploads by conversation by @dakjdakd in https://github.com/Mintplex-Labs/anything-llm/pull/6635\r\n* fix: finalize stopped scheduled job runs on Windows by @dakjdakd in https://github.com/Mintplex-Labs/anything-llm/pull/6637\r\n* fix: don't treat YouTube channel URLs as video links in the collector by @theluckystrike in https://github.com/Mintplex-Labs/anything-llm/pull/6644\r\n* fix: apply workspace similarity threshold to agent rag-memory search by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6648\r\n* fix: write bulk scraped pages that share a file name to separate files by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6650\r\n* fix: surface Confluence load failures instead of reporting no pages by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6652\r\n* fix: restore document embedding for AstraDB by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6654\r\n* fix: stop scheduled jobs after switching to multi-user mode by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6656\r\n* fix(server): keep $$ and $& intact when expanding prompt variables by @rome-xi in https://github.com/Mintplex-Labs/anything-llm/pull/6676\r\n* fix(collector): stop treating binary types with no converter as text by @moneebullah25 in https://github.com/Mintplex-Labs/anything-llm/pull/6670\r\n* fix: use response.send instead of response.text in repo provider check by @Saadanjum0 in https://github.com/Mintplex-Labs/anything-llm/pull/6677\r\n* fix: use a realistic fallback divisor for collector token estimates by @moneebullah25 in https://github.com/Mintplex-Labs/anything-llm/pull/6672\r\n* fix: return after resolve in wipeCollectorStorage guards by @moneebullah25 in https://github.com/Mintplex-Labs/anything-llm/pull/6671\r\n* Fix raw think blocks in scheduled job responses after tool calls by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6663\r\n* fix: keep unsent prompt text when attaching a file creates a new thread by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6704\r\n* fix: retry watched documents when re-embedding fails by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6701\r\n* fix: report a failed first Paperless-ngx request instead of no documents found by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6699\r\n* fix: keep the configured Paperless-ngx URL when following page links by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6698\r\n* fix: pass transcription and OCR settings to linked files by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6697\r\n* fix: give the same login error for an unknown username and a wrong password by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6693\r\n* fix: render nested and repeated lists correctly in created Word documents by @wenqiw777 in https://github.com/Mintplex-Labs/anything-llm/pull/6688\r\n* fix: request serial tool use for Anthropic agent providers by @dakjdakd in https://github.com/Mintplex-Labs/anything-llm/pull/6708\r\n* fix: propagate PGVector transaction failures without losing the original error by @dakjdakd in https://github.com/Mintplex-Labs/anything-llm/pull/6706\r\n* fix: cancel queued scheduled-job runs when a job is disabled or resynced by @dakjdakd in https://github.com/Mintplex-Labs/anything-llm/pull/6710\r\n* v1.18.0 tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6711\r\n\r\n## New Contributors\r\n* @u00dxk2 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6592\r\n* @YokoAC made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6610\r\n* @deepanshupal made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6613\r\n* @theluckystrike made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6614\r\n* @dakjdakd made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6633\r\n* @rome-xi made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6676\r\n* @moneebullah25 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6670\r\n* @Saadanjum0 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6677\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.17.0...v1.18.0","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix: point k8s probes at the server's /api/ping by @u00dxk2 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6592\">https://github.com/Mintplex-Labs/anything-llm/pull/6592</a>\n</li>\n<li>fix: don't crash when removing a parsed file while an image is attached by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6585\">https://github.com/Mintplex-Labs/anything-llm/pull/6585</a>\n</li>\n<li>fix: open the clicked image when attachments share a file name by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6586\">https://github.com/Mintplex-Labs/anything-llm/pull/6586</a>\n</li>\n<li>fix: stop sending history attachments to providers that build prompts from raw chat history by @simonether in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6591\">https://github.com/Mintplex-Labs/anything-llm/pull/6591</a>\n</li>\n<li>fix: compare embed allowlist entries as browser origins by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6584\">https://github.com/Mintplex-Labs/anything-llm/pull/6584</a>\n</li>\n<li>add dismissal comment to prevent low-effort research claims by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6608\">https://github.com/Mintplex-Labs/anything-llm/pull/6608</a>\n</li>\n<li>fix: send agent tool required params on every provider path by @wenqiw777 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6595\">https://github.com/Mintplex-Labs/anything-llm/pull/6595</a>\n</li>\n<li>fix: honor the SDK retry count when ANYTHINGLLM_MAX_RETRIES is set by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6597\">https://github.com/Mintplex-Labs/anything-llm/pull/6597</a>\n</li>\n<li>fix: save the Outlook account type so sign-in uses the right tenant by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6599\">https://github.com/Mintplex-Labs/anything-llm/pull/6599</a>\n</li>\n<li>fix: show an error when a system prompt variable change fails by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6604\">https://github.com/Mintplex-Labs/anything-llm/pull/6604</a>\n</li>\n<li>fix: apply TOOL_CALL_APPROVAL_TIMEOUT_MS to Telegram tool approvals by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6601\">https://github.com/Mintplex-Labs/anything-llm/pull/6601</a>\n</li>\n<li>fix: convert the hourly schedule minute to UTC in half-hour time zones by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6605\">https://github.com/Mintplex-Labs/anything-llm/pull/6605</a>\n</li>\n<li>fix: select entire folder after upload when picker is paginated by @YokoAC in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6610\">https://github.com/Mintplex-Labs/anything-llm/pull/6610</a>\n</li>\n<li>fix: keep numeric strings over 15 digits as text in created Excel files by @deepanshupal in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6613\">https://github.com/Mintplex-Labs/anything-llm/pull/6613</a>\n</li>\n<li>fix: restore dropped i18n placeholders in MCP and profile strings by @theluckystrike in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6614\">https://github.com/Mintplex-Labs/anything-llm/pull/6614</a>\n</li>\n<li>fix: scrape each page once when bulk links differ only by #fragment by @MohammadHijjawi97 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6619\">https://github.com/Mintplex-Labs/anything-llm/pull/6619</a>\n</li>\n<li>fix: attach requested files to Outlook replies and reply drafts by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6623\">https://github.com/Mintplex-Labs/anything-llm/pull/6623</a>\n</li>\n<li>fix: return 404 for an unknown workspace on manage-users and update-pin by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6625\">https://github.com/Mintplex-Labs/anything-llm/pull/6625</a>\n</li>\n<li>fix: load the next page of documents from the server's offset in the picker by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6628\">https://github.com/Mintplex-Labs/anything-llm/pull/6628</a>\n</li>\n<li>fix: show an error when embedding attached files into the workspace fails by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6629\">https://github.com/Mintplex-Labs/anything-llm/pull/6629</a>\n</li>\n<li>fix: restore dropped i18n values in model router and model picker strings by @theluckystrike in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6631\">https://github.com/Mintplex-Labs/anything-llm/pull/6631</a>\n</li>\n<li>fix: preserve referenced MBOX chat attachments during orphan cleanup by @dakjdakd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6633\">https://github.com/Mintplex-Labs/anything-llm/pull/6633</a>\n</li>\n<li>fix: isolate chat attachment state and uploads by conversation by @dakjdakd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6635\">https://github.com/Mintplex-Labs/anything-llm/pull/6635</a>\n</li>\n<li>fix: finalize stopped scheduled job runs on Windows by @dakjdakd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6637\">https://github.com/Mintplex-Labs/anything-llm/pull/6637</a>\n</li>\n<li>fix: don't treat YouTube channel URLs as video links in the collector by @theluckystrike in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6644\">https://github.com/Mintplex-Labs/anything-llm/pull/6644</a>\n</li>\n<li>fix: apply workspace similarity threshold to agent rag-memory search by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6648\">https://github.com/Mintplex-Labs/anything-llm/pull/6648</a>\n</li>\n<li>fix: write bulk scraped pages that share a file name to separate files by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6650\">https://github.com/Mintplex-Labs/anything-llm/pull/6650</a>\n</li>\n<li>fix: surface Confluence load failures instead of reporting no pages by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6652\">https://github.com/Mintplex-Labs/anything-llm/pull/6652</a>\n</li>\n<li>fix: restore document embedding for AstraDB by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6654\">https://github.com/Mintplex-Labs/anything-llm/pull/6654</a>\n</li>\n<li>fix: stop scheduled jobs after switching to multi-user mode by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6656\">https://github.com/Mintplex-Labs/anything-llm/pull/6656</a>\n</li>\n<li>fix(server): keep $$ and $&amp; intact when expanding prompt variables by @rome-xi in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6676\">https://github.com/Mintplex-Labs/anything-llm/pull/6676</a>\n</li>\n<li>fix(collector): stop treating binary types with no converter as text by @moneebullah25 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6670\">https://github.com/Mintplex-Labs/anything-llm/pull/6670</a>\n</li>\n<li>fix: use response.send instead of response.text in repo provider check by @Saadanjum0 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6677\">https://github.com/Mintplex-Labs/anything-llm/pull/6677</a>\n</li>\n<li>fix: use a realistic fallback divisor for collector token estimates by @moneebullah25 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6672\">https://github.com/Mintplex-Labs/anything-llm/pull/6672</a>\n</li>\n<li>fix: return after resolve in wipeCollectorStorage guards by @moneebullah25 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6671\">https://github.com/Mintplex-Labs/anything-llm/pull/6671</a>\n</li>\n<li>Fix raw think blocks in scheduled job responses after tool calls by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6663\">https://github.com/Mintplex-Labs/anything-llm/pull/6663</a>\n</li>\n<li>fix: keep unsent prompt text when attaching a file creates a new thread by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6704\">https://github.com/Mintplex-Labs/anything-llm/pull/6704</a>\n</li>\n<li>fix: retry watched documents when re-embedding fails by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6701\">https://github.com/Mintplex-Labs/anything-llm/pull/6701</a>\n</li>\n<li>fix: report a failed first Paperless-ngx request instead of no documents found by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6699\">https://github.com/Mintplex-Labs/anything-llm/pull/6699</a>\n</li>\n<li>fix: keep the configured Paperless-ngx URL when following page links by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6698\">https://github.com/Mintplex-Labs/anything-llm/pull/6698</a>\n</li>\n<li>fix: pass transcription and OCR settings to linked files by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6697\">https://github.com/Mintplex-Labs/anything-llm/pull/6697</a>\n</li>\n<li>fix: give the same login error for an unknown username and a wrong password by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6693\">https://github.com/Mintplex-Labs/anything-llm/pull/6693</a>\n</li>\n<li>fix: render nested and repeated lists correctly in created Word documents by @wenqiw777 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6688\">https://github.com/Mintplex-Labs/anything-llm/pull/6688</a>\n</li>\n<li>fix: request serial tool use for Anthropic agent providers by @dakjdakd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6708\">https://github.com/Mintplex-Labs/anything-llm/pull/6708</a>\n</li>\n<li>fix: propagate PGVector transaction failures without losing the original error by @dakjdakd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6706\">https://github.com/Mintplex-Labs/anything-llm/pull/6706</a>\n</li>\n<li>fix: cancel queued scheduled-job runs when a job is disabled or resynced by @dakjdakd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6710\">https://github.com/Mintplex-Labs/anything-llm/pull/6710</a>\n</li>\n<li>v1.18.0 tags by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6711\">https://github.com/Mintplex-Labs/anything-llm/pull/6711</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@u00dxk2 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6592\">https://github.com/Mintplex-Labs/anything-llm/pull/6592</a>\n</li>\n<li>@YokoAC made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6610\">https://github.com/Mintplex-Labs/anything-llm/pull/6610</a>\n</li>\n<li>@deepanshupal made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6613\">https://github.com/Mintplex-Labs/anything-llm/pull/6613</a>\n</li>\n<li>@theluckystrike made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6614\">https://github.com/Mintplex-Labs/anything-llm/pull/6614</a>\n</li>\n<li>@dakjdakd made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6633\">https://github.com/Mintplex-Labs/anything-llm/pull/6633</a>\n</li>\n<li>@rome-xi made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6676\">https://github.com/Mintplex-Labs/anything-llm/pull/6676</a>\n</li>\n<li>@moneebullah25 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6670\">https://github.com/Mintplex-Labs/anything-llm/pull/6670</a>\n</li>\n<li>@Saadanjum0 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6677\">https://github.com/Mintplex-Labs/anything-llm/pull/6677</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.17.0...v1.18.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.17.0...v1.18.0</a></p>\n","assets":[{"contentType":"application/octet-stream","size":632226083,"createdAt":"2026-10-13T00:02:08Z","updatedAt":"2026-10-13T00:02:28Z","downloadCount":300,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":513734624,"createdAt":"2026-10-13T00:02:28Z","updatedAt":"2026-10-13T00:02:44Z","downloadCount":293,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":582631265,"createdAt":"2026-10-13T00:02:44Z","updatedAt":"2026-10-13T00:03:06Z","downloadCount":688,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":903867816,"createdAt":"2026-10-13T00:03:07Z","updatedAt":"2026-10-13T00:03:37Z","downloadCount":1209,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":548548002,"createdAt":"2026-10-13T00:03:37Z","updatedAt":"2026-10-13T00:03:53Z","downloadCount":162,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":407381240,"createdAt":"2026-10-13T00:01:55Z","updatedAt":"2026-10-13T00:02:08Z","downloadCount":5302,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":23552,"createdAt":"2026-10-13T00:03:06Z","updatedAt":"2026-10-13T00:03:06Z","downloadCount":167,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/installer.sh"},{"contentType":"text/plain","size":6,"createdAt":"2026-10-13T00:03:06Z","updatedAt":"2026-10-13T00:03:07Z","downloadCount":417,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.18.0/version.txt"}]},{"id":401384048,"tag":"v1.17.0","author":"timothycarambat","name":"AnythingLLM v1.17.0","draft":false,"prerelease":false,"createdAt":"2026-10-01T22:12:22Z","publishedAt":"2026-10-01T22:17:40Z","markdown":"## What's Changed\r\n* fix(collector): read spreadsheet dates as dates, not serial numbers by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6478\r\n* Drop temp param for Anthropic models by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6472\r\n* Allow Generic OpenAI max tokens of 0 to omit max_tokens from request by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6470\r\n* fix: support SearchApi engines in agent web browsing by @evilive3000 in https://github.com/Mintplex-Labs/anything-llm/pull/6465\r\n* fix: ignore malformed agent WebSocket frames instead of crashing the server by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6493\r\n* fix(collector): read an HTML-only mbox message instead of skipping it by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6484\r\n* fix(collector): read text uploads in the encoding they were written in by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6486\r\n* fix(weaviate, astra): score chunks by cosine similarity like the other providers by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6488\r\n* fix(bedrock): support OpenAI models on AWS by @hahahahahayesyeseys in https://github.com/Mintplex-Labs/anything-llm/pull/6473\r\n* fix: fetch Kokoro voices from the same base path speech uses by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6459\r\n* feat(togetherai): allow configuring max_tokens to prevent response truncation by @imanecdoche in https://github.com/Mintplex-Labs/anything-llm/pull/6463\r\n* fix: reset vectors and warn when the Azure embedding deployment changes by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6461\r\n* fix: keep manually set env settings when a settings save rewrites .env by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6457\r\n* fix: use the workspace refusal text when an embed has no documents by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6454\r\n* fix: export only the chats the chat window shows by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6452\r\n* fix: keep every sheet of a multi-sheet XLSX upload by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6450\r\n* Include generated images in chat exports by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6482\r\n* feat: add Firecrawl agent web-search provider by @JuampiHernandez in https://github.com/Mintplex-Labs/anything-llm/pull/6480\r\n* Autosave workspace settings on edit by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6343\r\n* Add keyboard navigation and autofocus to provider search menus by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6483\r\n* Read Anthropic replies from text blocks, not the first block by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6496\r\n* fix: keep Telegram link URLs intact when they contain markdown characters by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6524\r\n* feat: add Gemini as an image generation provider by @petre in https://github.com/Mintplex-Labs/anything-llm/pull/6520\r\n* fix(ui): use dynamic viewport height for mobile sidebar drawers by @albiea in https://github.com/Mintplex-Labs/anything-llm/pull/6518\r\n* fix: keep compressed RAG context when the prompt or a chunk says \"Context:\" by @breken-ai in https://github.com/Mintplex-Labs/anything-llm/pull/6503\r\n* fix: skip emoji when reading a message aloud by @SulimanAbdulrazzaq in https://github.com/Mintplex-Labs/anything-llm/pull/6500\r\n* fix: clear the workspace router when switching back to the system default by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6506\r\n* fix: skip saving an embed chat when the reply came back empty by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6508\r\n* fix: let users and admins clear a bio by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6510\r\n* fix: resolve relative links against the page they appear on when crawling deeper by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6512\r\n* fix: keep each mbox message's own title when an upload supplies one by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6514\r\n* Add llmman image generation provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6497\r\n* fix: let Milvus and Zilliz embed into workspaces whose slug starts with a digit by @wenqiw777 in https://github.com/Mintplex-Labs/anything-llm/pull/6527\r\n* fix: filter Google Calendar skill in multi-user mode and apply its disabled sub-skills by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6539\r\n* fix: keep Confluence code blocks whose macro does not list ac:name first by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6530\r\n* fix: embed every document an API upload returns into addToWorkspaces by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6532\r\n* fix: keep IPs, versions and decimal commas as text in created Excel files by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6534\r\n* fix: only run Telegram bot commands at the start of a message by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6536\r\n* fix: send the Keep Alive setting on agent requests to Ollama and llmman by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6538\r\n* fix(mobile): reject unknown threadSlug on reset-chat and stream-chat by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6540\r\n* fix: render c++, ~~~ and nested fenced code as code in Telegram replies by @huiq777 in https://github.com/Mintplex-Labs/anything-llm/pull/6547\r\n* fix: decode DuckDuckGo result links once and strip HTML from titles by @simonether in https://github.com/Mintplex-Labs/anything-llm/pull/6544\r\n* Clean up TTS text for cloud voices and Telegram voice replies by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6552\r\n* fix: use each workspace's prompt and id in JSONL and Alpaca chat exports by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6551\r\n* Rotate empty chat greetings by time of day by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6567\r\n* fix: mask the saved LiteLLM API key and save changes to it by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6556\r\n* fix: shift the weekday and day of month of scheduled jobs across UTC midnight by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6558\r\n* fix: load Fireworks models and Kokoro voices with the saved API key by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6557\r\n* fix: give each new agent flow block its own id by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6560\r\n* fix: save turning password protection off so it survives a restart by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6562\r\n* fix: save links whose URL path cannot be percent-decoded by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6565\r\n* fix: use the embed's message history limit when the model router is on by @MohammadHijjawi97 in https://github.com/Mintplex-Labs/anything-llm/pull/6566\r\n* fix: stop filesystem-edit-file expanding $ patterns in newText by @wenqiw777 in https://github.com/Mintplex-Labs/anything-llm/pull/6569\r\n* fix: parse developer API document attachments for agent chats by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6573\r\n* fix: keep uploaded images when switching from chat to @agent mid-session by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6572\r\n* Apply workspace temperature to agents and omit the parameter when unset by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6285\r\n* Reasoning effort controls by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6269\r\n\r\n## New Contributors\r\n* @evilive3000 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6465\r\n* @hahahahahayesyeseys made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6473\r\n* @imanecdoche made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6463\r\n* @JuampiHernandez made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6480\r\n* @MohammadHijjawi97 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6524\r\n* @albiea made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6518\r\n* @breken-ai made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6503\r\n* @SulimanAbdulrazzaq made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6500\r\n* @wenqiw777 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6527\r\n* @huiq777 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6547\r\n* @simonether made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6544\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.2...v1.17.0","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix(collector): read spreadsheet dates as dates, not serial numbers by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6478\">https://github.com/Mintplex-Labs/anything-llm/pull/6478</a>\n</li>\n<li>Drop temp param for Anthropic models by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6472\">https://github.com/Mintplex-Labs/anything-llm/pull/6472</a>\n</li>\n<li>Allow Generic OpenAI max tokens of 0 to omit max_tokens from request by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6470\">https://github.com/Mintplex-Labs/anything-llm/pull/6470</a>\n</li>\n<li>fix: support SearchApi engines in agent web browsing by @evilive3000 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6465\">https://github.com/Mintplex-Labs/anything-llm/pull/6465</a>\n</li>\n<li>fix: ignore malformed agent WebSocket frames instead of crashing the server by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6493\">https://github.com/Mintplex-Labs/anything-llm/pull/6493</a>\n</li>\n<li>fix(collector): read an HTML-only mbox message instead of skipping it by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6484\">https://github.com/Mintplex-Labs/anything-llm/pull/6484</a>\n</li>\n<li>fix(collector): read text uploads in the encoding they were written in by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6486\">https://github.com/Mintplex-Labs/anything-llm/pull/6486</a>\n</li>\n<li>fix(weaviate, astra): score chunks by cosine similarity like the other providers by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6488\">https://github.com/Mintplex-Labs/anything-llm/pull/6488</a>\n</li>\n<li>fix(bedrock): support OpenAI models on AWS by @hahahahahayesyeseys in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6473\">https://github.com/Mintplex-Labs/anything-llm/pull/6473</a>\n</li>\n<li>fix: fetch Kokoro voices from the same base path speech uses by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6459\">https://github.com/Mintplex-Labs/anything-llm/pull/6459</a>\n</li>\n<li>feat(togetherai): allow configuring max_tokens to prevent response truncation by @imanecdoche in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6463\">https://github.com/Mintplex-Labs/anything-llm/pull/6463</a>\n</li>\n<li>fix: reset vectors and warn when the Azure embedding deployment changes by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6461\">https://github.com/Mintplex-Labs/anything-llm/pull/6461</a>\n</li>\n<li>fix: keep manually set env settings when a settings save rewrites .env by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6457\">https://github.com/Mintplex-Labs/anything-llm/pull/6457</a>\n</li>\n<li>fix: use the workspace refusal text when an embed has no documents by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6454\">https://github.com/Mintplex-Labs/anything-llm/pull/6454</a>\n</li>\n<li>fix: export only the chats the chat window shows by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6452\">https://github.com/Mintplex-Labs/anything-llm/pull/6452</a>\n</li>\n<li>fix: keep every sheet of a multi-sheet XLSX upload by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6450\">https://github.com/Mintplex-Labs/anything-llm/pull/6450</a>\n</li>\n<li>Include generated images in chat exports by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6482\">https://github.com/Mintplex-Labs/anything-llm/pull/6482</a>\n</li>\n<li>feat: add Firecrawl agent web-search provider by @JuampiHernandez in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6480\">https://github.com/Mintplex-Labs/anything-llm/pull/6480</a>\n</li>\n<li>Autosave workspace settings on edit by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6343\">https://github.com/Mintplex-Labs/anything-llm/pull/6343</a>\n</li>\n<li>Add keyboard navigation and autofocus to provider search menus by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6483\">https://github.com/Mintplex-Labs/anything-llm/pull/6483</a>\n</li>\n<li>Read Anthropic replies from text blocks, not the first block by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6496\">https://github.com/Mintplex-Labs/anything-llm/pull/6496</a>\n</li>\n<li>fix: keep Telegram link URLs intact when they contain markdown characters by @MohammadHijjawi97 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6524\">https://github.com/Mintplex-Labs/anything-llm/pull/6524</a>\n</li>\n<li>feat: add Gemini as an image generation provider by @petre in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6520\">https://github.com/Mintplex-Labs/anything-llm/pull/6520</a>\n</li>\n<li>fix(ui): use dynamic viewport height for mobile sidebar drawers by @albiea in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6518\">https://github.com/Mintplex-Labs/anything-llm/pull/6518</a>\n</li>\n<li>fix: keep compressed RAG context when the prompt or a chunk says \"Context:\" by @breken-ai in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6503\">https://github.com/Mintplex-Labs/anything-llm/pull/6503</a>\n</li>\n<li>fix: skip emoji when reading a message aloud by @SulimanAbdulrazzaq in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6500\">https://github.com/Mintplex-Labs/anything-llm/pull/6500</a>\n</li>\n<li>fix: clear the workspace router when switching back to the system default by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6506\">https://github.com/Mintplex-Labs/anything-llm/pull/6506</a>\n</li>\n<li>fix: skip saving an embed chat when the reply came back empty by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6508\">https://github.com/Mintplex-Labs/anything-llm/pull/6508</a>\n</li>\n<li>fix: let users and admins clear a bio by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6510\">https://github.com/Mintplex-Labs/anything-llm/pull/6510</a>\n</li>\n<li>fix: resolve relative links against the page they appear on when crawling deeper by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6512\">https://github.com/Mintplex-Labs/anything-llm/pull/6512</a>\n</li>\n<li>fix: keep each mbox message's own title when an upload supplies one by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6514\">https://github.com/Mintplex-Labs/anything-llm/pull/6514</a>\n</li>\n<li>Add llmman image generation provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6497\">https://github.com/Mintplex-Labs/anything-llm/pull/6497</a>\n</li>\n<li>fix: let Milvus and Zilliz embed into workspaces whose slug starts with a digit by @wenqiw777 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6527\">https://github.com/Mintplex-Labs/anything-llm/pull/6527</a>\n</li>\n<li>fix: filter Google Calendar skill in multi-user mode and apply its disabled sub-skills by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6539\">https://github.com/Mintplex-Labs/anything-llm/pull/6539</a>\n</li>\n<li>fix: keep Confluence code blocks whose macro does not list ac:name first by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6530\">https://github.com/Mintplex-Labs/anything-llm/pull/6530</a>\n</li>\n<li>fix: embed every document an API upload returns into addToWorkspaces by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6532\">https://github.com/Mintplex-Labs/anything-llm/pull/6532</a>\n</li>\n<li>fix: keep IPs, versions and decimal commas as text in created Excel files by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6534\">https://github.com/Mintplex-Labs/anything-llm/pull/6534</a>\n</li>\n<li>fix: only run Telegram bot commands at the start of a message by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6536\">https://github.com/Mintplex-Labs/anything-llm/pull/6536</a>\n</li>\n<li>fix: send the Keep Alive setting on agent requests to Ollama and llmman by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6538\">https://github.com/Mintplex-Labs/anything-llm/pull/6538</a>\n</li>\n<li>fix(mobile): reject unknown threadSlug on reset-chat and stream-chat by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6540\">https://github.com/Mintplex-Labs/anything-llm/pull/6540</a>\n</li>\n<li>fix: render c++, ~~~ and nested fenced code as code in Telegram replies by @huiq777 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6547\">https://github.com/Mintplex-Labs/anything-llm/pull/6547</a>\n</li>\n<li>fix: decode DuckDuckGo result links once and strip HTML from titles by @simonether in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6544\">https://github.com/Mintplex-Labs/anything-llm/pull/6544</a>\n</li>\n<li>Clean up TTS text for cloud voices and Telegram voice replies by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6552\">https://github.com/Mintplex-Labs/anything-llm/pull/6552</a>\n</li>\n<li>fix: use each workspace's prompt and id in JSONL and Alpaca chat exports by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6551\">https://github.com/Mintplex-Labs/anything-llm/pull/6551</a>\n</li>\n<li>Rotate empty chat greetings by time of day by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6567\">https://github.com/Mintplex-Labs/anything-llm/pull/6567</a>\n</li>\n<li>fix: mask the saved LiteLLM API key and save changes to it by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6556\">https://github.com/Mintplex-Labs/anything-llm/pull/6556</a>\n</li>\n<li>fix: shift the weekday and day of month of scheduled jobs across UTC midnight by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6558\">https://github.com/Mintplex-Labs/anything-llm/pull/6558</a>\n</li>\n<li>fix: load Fireworks models and Kokoro voices with the saved API key by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6557\">https://github.com/Mintplex-Labs/anything-llm/pull/6557</a>\n</li>\n<li>fix: give each new agent flow block its own id by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6560\">https://github.com/Mintplex-Labs/anything-llm/pull/6560</a>\n</li>\n<li>fix: save turning password protection off so it survives a restart by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6562\">https://github.com/Mintplex-Labs/anything-llm/pull/6562</a>\n</li>\n<li>fix: save links whose URL path cannot be percent-decoded by @MohammadHijjawi97 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6565\">https://github.com/Mintplex-Labs/anything-llm/pull/6565</a>\n</li>\n<li>fix: use the embed's message history limit when the model router is on by @MohammadHijjawi97 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6566\">https://github.com/Mintplex-Labs/anything-llm/pull/6566</a>\n</li>\n<li>fix: stop filesystem-edit-file expanding $ patterns in newText by @wenqiw777 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6569\">https://github.com/Mintplex-Labs/anything-llm/pull/6569</a>\n</li>\n<li>fix: parse developer API document attachments for agent chats by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6573\">https://github.com/Mintplex-Labs/anything-llm/pull/6573</a>\n</li>\n<li>fix: keep uploaded images when switching from chat to @agent mid-session by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6572\">https://github.com/Mintplex-Labs/anything-llm/pull/6572</a>\n</li>\n<li>Apply workspace temperature to agents and omit the parameter when unset by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6285\">https://github.com/Mintplex-Labs/anything-llm/pull/6285</a>\n</li>\n<li>Reasoning effort controls by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6269\">https://github.com/Mintplex-Labs/anything-llm/pull/6269</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@evilive3000 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6465\">https://github.com/Mintplex-Labs/anything-llm/pull/6465</a>\n</li>\n<li>@hahahahahayesyeseys made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6473\">https://github.com/Mintplex-Labs/anything-llm/pull/6473</a>\n</li>\n<li>@imanecdoche made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6463\">https://github.com/Mintplex-Labs/anything-llm/pull/6463</a>\n</li>\n<li>@JuampiHernandez made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6480\">https://github.com/Mintplex-Labs/anything-llm/pull/6480</a>\n</li>\n<li>@MohammadHijjawi97 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6524\">https://github.com/Mintplex-Labs/anything-llm/pull/6524</a>\n</li>\n<li>@albiea made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6518\">https://github.com/Mintplex-Labs/anything-llm/pull/6518</a>\n</li>\n<li>@breken-ai made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6503\">https://github.com/Mintplex-Labs/anything-llm/pull/6503</a>\n</li>\n<li>@SulimanAbdulrazzaq made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6500\">https://github.com/Mintplex-Labs/anything-llm/pull/6500</a>\n</li>\n<li>@wenqiw777 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6527\">https://github.com/Mintplex-Labs/anything-llm/pull/6527</a>\n</li>\n<li>@huiq777 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6547\">https://github.com/Mintplex-Labs/anything-llm/pull/6547</a>\n</li>\n<li>@simonether made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6544\">https://github.com/Mintplex-Labs/anything-llm/pull/6544</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.2...v1.17.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.2...v1.17.0</a></p>\n","assets":[{"contentType":"application/octet-stream","size":631938379,"createdAt":"2026-10-01T22:11:14Z","updatedAt":"2026-10-01T22:11:33Z","downloadCount":320,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":521652408,"createdAt":"2026-10-01T22:11:32Z","updatedAt":"2026-10-01T22:11:47Z","downloadCount":377,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":566665700,"createdAt":"2026-10-01T22:11:47Z","updatedAt":"2026-10-01T22:12:05Z","downloadCount":515,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":903580827,"createdAt":"2026-10-01T22:10:19Z","updatedAt":"2026-10-01T22:10:46Z","downloadCount":935,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":531987496,"createdAt":"2026-10-01T22:10:46Z","updatedAt":"2026-10-01T22:11:01Z","downloadCount":254,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":410136032,"createdAt":"2026-10-01T22:11:01Z","updatedAt":"2026-10-01T22:11:14Z","downloadCount":4558,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":11669,"createdAt":"2026-10-01T22:12:04Z","updatedAt":"2026-10-01T22:12:05Z","downloadCount":154,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/installer.sh"},{"contentType":"text/plain","size":6,"createdAt":"2026-10-01T22:12:05Z","updatedAt":"2026-10-01T22:12:05Z","downloadCount":403,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.17.0/version.txt"}]},{"id":394031720,"tag":"v1.16.2","author":"timothycarambat","name":"AnythingLLM v1.16.2","draft":false,"prerelease":false,"createdAt":"2026-09-22T18:50:18Z","publishedAt":"2026-09-22T19:06:03Z","markdown":"## New Features\r\n\r\n- [x] [LLMman - OSS](https://github.com/llmmanorg/llmman) is now available as a local LLM provider, replacing Docker Model Runner\r\n- [x] [Google Vertex AI](https://cloud.google.com/products/gemini-enterprise-agent-platform) is now available as an LLM provider\r\n- [x] New `generate-image` agent skill for creating images from chat\r\n- [x] You.com is now the default web search provider for richer web-searches with Zero Data Retention\r\n- [x] Agent flow variables now support optional arguments\r\n- [x] Hindi, Bulgarian, and Swedish language support added\r\n- [x] GenieX on Windows on ARM now lists models found in your local model directory and lets you pull models directly from Hugging Face in the UI\r\n- [x] Click the version tag in the top of the window to jump to your logs and storage directory more easily\r\n\r\n## Improvements\r\n\r\n- [x] Web browsing is now enabled by default for agents\r\n- [x] Local providers now report model loading status in chat so you know why the first response is slow\r\n- [x] Ollama runtime bumped to 0.33.3 with an updated bundled model list\r\n- [x] Removed the borders around the main content area for a cleaner desktop layout\r\n- [x] Redesigned the \"new feature\" modal layout\r\n- [x] Dates in tables are now shown in a human-readable format\r\n- [x] Scraped web pages now preserve tables, ordered lists, and code blocks instead of flattening them\r\n- [x] PDF pages are now joined with newlines so words don't fuse across page boundaries\r\n- [x] Mistral embeddings are now batched, making large document embedding significantly faster\r\n- [x] Document search now matches your terms literally instead of as a regular expression\r\n- [x] Watched documents now clear stale vectors on sync\r\n- [x] AnySearch as a web-search provider\r\n- [x] KoboldCPP provider overhauled and modernized to match the rest of our providers\r\n- [x] Keenable added as a web search provider\r\n- [x] OpenRouter service tier selection for controlling routing cost and priority\r\n- [x] LocalAI image editing via reference images\r\n-----\r\n\r\n## All Changes\r\n* bump to patched @mintplex-labs/mdpdf pkg by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6216\r\n* Identify AnythingLLM Perplexity requests by @qirh in https://github.com/Mintplex-Labs/anything-llm/pull/6206\r\n* Add `X-Client-Info` to You.com attribution by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6221\r\n* Google Vertex LLM Provider support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6218\r\n* fix: stop fillSourceWindow reversing the caller's chat history array by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6231\r\n* fix: keep workspace prompt and temperature when an embed sends no override by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6232\r\n* pass include status on sessionID chat getter by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6237\r\n* fix: stop $ sequences corrupting restored Telegram code blocks by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6235\r\n* Add Swedish frontend locale by @yeager in https://github.com/Mintplex-Labs/anything-llm/pull/6227\r\n* fix: keep thread and user on the query-mode refusal row by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6236\r\n* feat: replace the Docker Model Runner provider with llmman by @ericcurtin in https://github.com/Mintplex-Labs/anything-llm/pull/6226\r\n* fix: return the API Call block's response body instead of a parse message by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6240\r\n* fix: report a failed password update instead of always answering success by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6245\r\n* fix: mobile reset-chat clears the whole workspace instead of the named thread by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6241\r\n* fix: Only block explicit matches for built-in slash commands by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6243\r\n* 6246 pw restrictions by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6250\r\n* Pretty dates on tables by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6251\r\n* Implement LocalAI image editing via ref_images by @TheGoodMorty in https://github.com/Mintplex-Labs/anything-llm/pull/6222\r\n* fix: score Lance chunks at or past orthogonal as 0, not a perfect match by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6253\r\n* Migrate threads on MuM migration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6259\r\n* fix: stop citation cleanup mangling scraped code and numbered links by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6252\r\n* fix: scope website-depth crawling by origin and path segment by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6258\r\n* docs: fix dead links in README by @1t1sCooL in https://github.com/Mintplex-Labs/anything-llm/pull/6193\r\n* Add variable categories to agent flow variables by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6249\r\n* Add generate-image agent skill by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6140\r\n* fix: four server-side bugs (privatemode provider, prompt-history delete, success flag, event log) by @simpleqt in https://github.com/Mintplex-Labs/anything-llm/pull/6165\r\n* feat: support batch URL uploads by @Max-Reisinger in https://github.com/Mintplex-Labs/anything-llm/pull/6175\r\n* fix: restrict workspace prompt-history read to admin/manager by @IdanMit in https://github.com/Mintplex-Labs/anything-llm/pull/6137\r\n* fix: match document search terms literally instead of as regular expressions by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6268\r\n* fix: store DrupalWiki page attachments instead of skipping every one by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6266\r\n* fix: separate PDF page boundaries instead of fusing the adjoining words by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6264\r\n* fix(i18n): correct six Italian UI translations by @Carleoinserra in https://github.com/Mintplex-Labs/anything-llm/pull/6317\r\n* feat(i18n): add Hindi (hi) language support by @tejasashinde in https://github.com/Mintplex-Labs/anything-llm/pull/6319\r\n* fix: clear stale document_vectors rows during watched document sync by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6323\r\n* fix path resolution double slash on fastCRW by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6324\r\n* fix(collector): treat a blank published value as absent, not as the epoch by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6275\r\n* fix: keep chat-history attachments for TogetherAI, SambaNova, Z.ai and Cerebras by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6296\r\n* fix: keep the GitLab repo scheme so http self-hosted instances can re-sync by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6294\r\n* fix: pin @qdrant/js-client-rest to 1.18.0 so lockfile-less builds keep search() by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6326\r\n* fix: honor captureAs html on the scraper's fetch fallback by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6292\r\n* fix: preserve Unicode characters in imported skill names by @dawNotPoi in https://github.com/Mintplex-Labs/anything-llm/pull/6286\r\n* fix: require sql_query, not table_name by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6329\r\n* fix: update workspace chat lastUpdatedAt by @AbarnaaSree in https://github.com/Mintplex-Labs/anything-llm/pull/6288\r\n* fix(collector): keep upload-link metadata when the link resolves to a file by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6277\r\n* fix(generic-openai): honor max tokens in Tooled/UnTooled agent streams by @Jkand in https://github.com/Mintplex-Labs/anything-llm/pull/6331\r\n* Make web search use You.com as the default provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6280\r\n* Enable web-browsing by default by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6335\r\n* Add Keenable web search provider by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6336\r\n* Add `TOOL_CALL_APPROVAL_TIMEOUT_MS` to admin env config by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6339\r\n* Add Bulgarian (bg) translation by @axander44 in https://github.com/Mintplex-Labs/anything-llm/pull/6344\r\n* docs: add Easypanel to self-hosting deploy table by @Ahson-Shaikh in https://github.com/Mintplex-Labs/anything-llm/pull/6360\r\n* patch GHSA-8wh8-3v68-whwj by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6361\r\n* fix: accept the documented allowlist_domains array in the embed API by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6358\r\n* fix: drop a GitLab access token the instance rejects instead of reusing it by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6356\r\n* fix: set Simple SSO temporary auth token expiry to 10 minutes by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6362\r\n* fix: paperless-ngx resync returned empty for every existing document by @auyua9 in https://github.com/Mintplex-Labs/anything-llm/pull/6348\r\n* Add `deepseek-flash` to IncludeReasoning array due to deprecation/upgrade of alias by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6379\r\n* fix(mistral): batch embedding requests and declare the engine's limits by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6378\r\n* fix: stop section and cite cleanup mangling scraped code and links by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6371\r\n* fix: keep the Confluence page scheme so http self-hosted instances re-sync by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6372\r\n* fix: linked mbox scraping returned only the first message by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6374\r\n* fix: decode GitHub file content as UTF-8 when re-syncing a watched document by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6373\r\n* fix: llmman model discovery ignored the token entered in settings by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6376\r\n* KoboldCPP overhaul by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6380\r\n* fix(xlsx): escape spreadsheet cells the way CSV requires by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6381\r\n* fix: log chunk header exceeding chunk size by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6386\r\n* fix: convert a scraped table into a table, not into loose paragraphs by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6387\r\n* Add OpenRouter service tier selection by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6337\r\n* Bump embed submodule by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6389\r\n* Report model loading status for local agent providers by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6392\r\n* fix: give a merged table cell the columns it covers by @L4XB in https://github.com/Mintplex-Labs/anything-llm/pull/6388\r\n* Fix JSON body corruption when agent flow variables contain quotes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6402\r\n* fix(localai): pass API key when fetching generated image URL by @leilei3167 in https://github.com/Mintplex-Labs/anything-llm/pull/6425\r\n* fix: read a system message's content parts in the OpenAI-compatible chat endpoint by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6424\r\n* fix: return 404 from thread stream-chat for a missing workspace or thread by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6423\r\n* fix: accept a GitLab clone URL, trailing slash or view URL the way the siblings do by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6420\r\n* fix: return the TogetherAI context window as a number instead of a promise by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6418\r\n* fix: carry the Confluence personal access token through the re-sync payload by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6414\r\n* Resolve GHSA-3f4c-xj8r-h4cr by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6427\r\n* fix: stop the open-computer scraper deleting brackets from code and labels from links by @shoemoney in https://github.com/Mintplex-Labs/anything-llm/pull/6408\r\n* fix: add static promptWindowLimit to MoonshotAI and PPIO by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6438\r\n* fix: reject an empty message list with the existing 400 in the OpenAI-compatible chat endpoint by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6431\r\n* fix: let Groq's current vision model receive image attachments by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6429\r\n* fix: re-sync watched GitLab issues and wiki pages by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6433\r\n* feat: add AnySearch agent web-search provider by @tbontb-iaq in https://github.com/Mintplex-Labs/anything-llm/pull/6439\r\n\r\n## New Contributors\r\n* @qirh made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6206\r\n* @yeager made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6227\r\n* @ericcurtin made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6226\r\n* @TheGoodMorty made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6222\r\n* @1t1sCooL made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6193\r\n* @Max-Reisinger made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6175\r\n* @IdanMit made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6137\r\n* @Carleoinserra made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6317\r\n* @tejasashinde made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6319\r\n* @dawNotPoi made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6286\r\n* @AbarnaaSree made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6288\r\n* @Jkand made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6331\r\n* @axander44 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6344\r\n* @Ahson-Shaikh made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6360\r\n* @auyua9 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6348\r\n* @L4XB made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6378\r\n* @leilei3167 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6425\r\n* @shoemoney made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6408\r\n* @tbontb-iaq made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6439\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.1...v1.16.2","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Features</h2><a id=\"user-content-new-features\" class=\"anchor\" aria-label=\"Permalink: New Features\" href=\"#new-features\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] <a href=\"https://github.com/llmmanorg/llmman\">LLMman - OSS</a> is now available as a local LLM provider, replacing Docker Model Runner</li>\n<li>[x] <a href=\"https://cloud.google.com/products/gemini-enterprise-agent-platform\" rel=\"nofollow\">Google Vertex AI</a> is now available as an LLM provider</li>\n<li>[x] New <code>generate-image</code> agent skill for creating images from chat</li>\n<li>[x] You.com is now the default web search provider for richer web-searches with Zero Data Retention</li>\n<li>[x] Agent flow variables now support optional arguments</li>\n<li>[x] Hindi, Bulgarian, and Swedish language support added</li>\n<li>[x] GenieX on Windows on ARM now lists models found in your local model directory and lets you pull models directly from Hugging Face in the UI</li>\n<li>[x] Click the version tag in the top of the window to jump to your logs and storage directory more easily</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Improvements</h2><a id=\"user-content-improvements\" class=\"anchor\" aria-label=\"Permalink: Improvements\" href=\"#improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Web browsing is now enabled by default for agents</li>\n<li>[x] Local providers now report model loading status in chat so you know why the first response is slow</li>\n<li>[x] Ollama runtime bumped to 0.33.3 with an updated bundled model list</li>\n<li>[x] Removed the borders around the main content area for a cleaner desktop layout</li>\n<li>[x] Redesigned the \"new feature\" modal layout</li>\n<li>[x] Dates in tables are now shown in a human-readable format</li>\n<li>[x] Scraped web pages now preserve tables, ordered lists, and code blocks instead of flattening them</li>\n<li>[x] PDF pages are now joined with newlines so words don't fuse across page boundaries</li>\n<li>[x] Mistral embeddings are now batched, making large document embedding significantly faster</li>\n<li>[x] Document search now matches your terms literally instead of as a regular expression</li>\n<li>[x] Watched documents now clear stale vectors on sync</li>\n<li>[x] AnySearch as a web-search provider</li>\n<li>[x] KoboldCPP provider overhauled and modernized to match the rest of our providers</li>\n<li>[x] Keenable added as a web search provider</li>\n<li>[x] OpenRouter service tier selection for controlling routing cost and priority</li>\n<li>[x] LocalAI image editing via reference images</li>\n</ul>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">All Changes</h2><a id=\"user-content-all-changes\" class=\"anchor\" aria-label=\"Permalink: All Changes\" href=\"#all-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>bump to patched @mintplex-labs/mdpdf pkg by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6216\">https://github.com/Mintplex-Labs/anything-llm/pull/6216</a>\n</li>\n<li>Identify AnythingLLM Perplexity requests by @qirh in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6206\">https://github.com/Mintplex-Labs/anything-llm/pull/6206</a>\n</li>\n<li>Add <code>X-Client-Info</code> to You.com attribution by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6221\">https://github.com/Mintplex-Labs/anything-llm/pull/6221</a>\n</li>\n<li>Google Vertex LLM Provider support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6218\">https://github.com/Mintplex-Labs/anything-llm/pull/6218</a>\n</li>\n<li>fix: stop fillSourceWindow reversing the caller's chat history array by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6231\">https://github.com/Mintplex-Labs/anything-llm/pull/6231</a>\n</li>\n<li>fix: keep workspace prompt and temperature when an embed sends no override by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6232\">https://github.com/Mintplex-Labs/anything-llm/pull/6232</a>\n</li>\n<li>pass include status on sessionID chat getter by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6237\">https://github.com/Mintplex-Labs/anything-llm/pull/6237</a>\n</li>\n<li>fix: stop $ sequences corrupting restored Telegram code blocks by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6235\">https://github.com/Mintplex-Labs/anything-llm/pull/6235</a>\n</li>\n<li>Add Swedish frontend locale by @yeager in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6227\">https://github.com/Mintplex-Labs/anything-llm/pull/6227</a>\n</li>\n<li>fix: keep thread and user on the query-mode refusal row by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6236\">https://github.com/Mintplex-Labs/anything-llm/pull/6236</a>\n</li>\n<li>feat: replace the Docker Model Runner provider with llmman by @ericcurtin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6226\">https://github.com/Mintplex-Labs/anything-llm/pull/6226</a>\n</li>\n<li>fix: return the API Call block's response body instead of a parse message by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6240\">https://github.com/Mintplex-Labs/anything-llm/pull/6240</a>\n</li>\n<li>fix: report a failed password update instead of always answering success by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6245\">https://github.com/Mintplex-Labs/anything-llm/pull/6245</a>\n</li>\n<li>fix: mobile reset-chat clears the whole workspace instead of the named thread by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6241\">https://github.com/Mintplex-Labs/anything-llm/pull/6241</a>\n</li>\n<li>fix: Only block explicit matches for built-in slash commands by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6243\">https://github.com/Mintplex-Labs/anything-llm/pull/6243</a>\n</li>\n<li>6246 pw restrictions by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6250\">https://github.com/Mintplex-Labs/anything-llm/pull/6250</a>\n</li>\n<li>Pretty dates on tables by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6251\">https://github.com/Mintplex-Labs/anything-llm/pull/6251</a>\n</li>\n<li>Implement LocalAI image editing via ref_images by @TheGoodMorty in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6222\">https://github.com/Mintplex-Labs/anything-llm/pull/6222</a>\n</li>\n<li>fix: score Lance chunks at or past orthogonal as 0, not a perfect match by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6253\">https://github.com/Mintplex-Labs/anything-llm/pull/6253</a>\n</li>\n<li>Migrate threads on MuM migration by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6259\">https://github.com/Mintplex-Labs/anything-llm/pull/6259</a>\n</li>\n<li>fix: stop citation cleanup mangling scraped code and numbered links by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6252\">https://github.com/Mintplex-Labs/anything-llm/pull/6252</a>\n</li>\n<li>fix: scope website-depth crawling by origin and path segment by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6258\">https://github.com/Mintplex-Labs/anything-llm/pull/6258</a>\n</li>\n<li>docs: fix dead links in README by @1t1sCooL in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6193\">https://github.com/Mintplex-Labs/anything-llm/pull/6193</a>\n</li>\n<li>Add variable categories to agent flow variables by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6249\">https://github.com/Mintplex-Labs/anything-llm/pull/6249</a>\n</li>\n<li>Add generate-image agent skill by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6140\">https://github.com/Mintplex-Labs/anything-llm/pull/6140</a>\n</li>\n<li>fix: four server-side bugs (privatemode provider, prompt-history delete, success flag, event log) by @simpleqt in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6165\">https://github.com/Mintplex-Labs/anything-llm/pull/6165</a>\n</li>\n<li>feat: support batch URL uploads by @Max-Reisinger in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6175\">https://github.com/Mintplex-Labs/anything-llm/pull/6175</a>\n</li>\n<li>fix: restrict workspace prompt-history read to admin/manager by @IdanMit in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6137\">https://github.com/Mintplex-Labs/anything-llm/pull/6137</a>\n</li>\n<li>fix: match document search terms literally instead of as regular expressions by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6268\">https://github.com/Mintplex-Labs/anything-llm/pull/6268</a>\n</li>\n<li>fix: store DrupalWiki page attachments instead of skipping every one by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6266\">https://github.com/Mintplex-Labs/anything-llm/pull/6266</a>\n</li>\n<li>fix: separate PDF page boundaries instead of fusing the adjoining words by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6264\">https://github.com/Mintplex-Labs/anything-llm/pull/6264</a>\n</li>\n<li>fix(i18n): correct six Italian UI translations by @Carleoinserra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6317\">https://github.com/Mintplex-Labs/anything-llm/pull/6317</a>\n</li>\n<li>feat(i18n): add Hindi (hi) language support by @tejasashinde in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6319\">https://github.com/Mintplex-Labs/anything-llm/pull/6319</a>\n</li>\n<li>fix: clear stale document_vectors rows during watched document sync by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6323\">https://github.com/Mintplex-Labs/anything-llm/pull/6323</a>\n</li>\n<li>fix path resolution double slash on fastCRW by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6324\">https://github.com/Mintplex-Labs/anything-llm/pull/6324</a>\n</li>\n<li>fix(collector): treat a blank published value as absent, not as the epoch by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6275\">https://github.com/Mintplex-Labs/anything-llm/pull/6275</a>\n</li>\n<li>fix: keep chat-history attachments for TogetherAI, SambaNova, Z.ai and Cerebras by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6296\">https://github.com/Mintplex-Labs/anything-llm/pull/6296</a>\n</li>\n<li>fix: keep the GitLab repo scheme so http self-hosted instances can re-sync by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6294\">https://github.com/Mintplex-Labs/anything-llm/pull/6294</a>\n</li>\n<li>fix: pin @qdrant/js-client-rest to 1.18.0 so lockfile-less builds keep search() by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6326\">https://github.com/Mintplex-Labs/anything-llm/pull/6326</a>\n</li>\n<li>fix: honor captureAs html on the scraper's fetch fallback by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6292\">https://github.com/Mintplex-Labs/anything-llm/pull/6292</a>\n</li>\n<li>fix: preserve Unicode characters in imported skill names by @dawNotPoi in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6286\">https://github.com/Mintplex-Labs/anything-llm/pull/6286</a>\n</li>\n<li>fix: require sql_query, not table_name by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6329\">https://github.com/Mintplex-Labs/anything-llm/pull/6329</a>\n</li>\n<li>fix: update workspace chat lastUpdatedAt by @AbarnaaSree in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6288\">https://github.com/Mintplex-Labs/anything-llm/pull/6288</a>\n</li>\n<li>fix(collector): keep upload-link metadata when the link resolves to a file by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6277\">https://github.com/Mintplex-Labs/anything-llm/pull/6277</a>\n</li>\n<li>fix(generic-openai): honor max tokens in Tooled/UnTooled agent streams by @Jkand in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6331\">https://github.com/Mintplex-Labs/anything-llm/pull/6331</a>\n</li>\n<li>Make web search use You.com as the default provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6280\">https://github.com/Mintplex-Labs/anything-llm/pull/6280</a>\n</li>\n<li>Enable web-browsing by default by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6335\">https://github.com/Mintplex-Labs/anything-llm/pull/6335</a>\n</li>\n<li>Add Keenable web search provider by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6336\">https://github.com/Mintplex-Labs/anything-llm/pull/6336</a>\n</li>\n<li>Add <code>TOOL_CALL_APPROVAL_TIMEOUT_MS</code> to admin env config by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6339\">https://github.com/Mintplex-Labs/anything-llm/pull/6339</a>\n</li>\n<li>Add Bulgarian (bg) translation by @axander44 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6344\">https://github.com/Mintplex-Labs/anything-llm/pull/6344</a>\n</li>\n<li>docs: add Easypanel to self-hosting deploy table by @Ahson-Shaikh in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6360\">https://github.com/Mintplex-Labs/anything-llm/pull/6360</a>\n</li>\n<li>patch GHSA-8wh8-3v68-whwj by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6361\">https://github.com/Mintplex-Labs/anything-llm/pull/6361</a>\n</li>\n<li>fix: accept the documented allowlist_domains array in the embed API by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6358\">https://github.com/Mintplex-Labs/anything-llm/pull/6358</a>\n</li>\n<li>fix: drop a GitLab access token the instance rejects instead of reusing it by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6356\">https://github.com/Mintplex-Labs/anything-llm/pull/6356</a>\n</li>\n<li>fix: set Simple SSO temporary auth token expiry to 10 minutes by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6362\">https://github.com/Mintplex-Labs/anything-llm/pull/6362</a>\n</li>\n<li>fix: paperless-ngx resync returned empty for every existing document by @auyua9 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6348\">https://github.com/Mintplex-Labs/anything-llm/pull/6348</a>\n</li>\n<li>Add <code>deepseek-flash</code> to IncludeReasoning array due to deprecation/upgrade of alias by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6379\">https://github.com/Mintplex-Labs/anything-llm/pull/6379</a>\n</li>\n<li>fix(mistral): batch embedding requests and declare the engine's limits by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6378\">https://github.com/Mintplex-Labs/anything-llm/pull/6378</a>\n</li>\n<li>fix: stop section and cite cleanup mangling scraped code and links by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6371\">https://github.com/Mintplex-Labs/anything-llm/pull/6371</a>\n</li>\n<li>fix: keep the Confluence page scheme so http self-hosted instances re-sync by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6372\">https://github.com/Mintplex-Labs/anything-llm/pull/6372</a>\n</li>\n<li>fix: linked mbox scraping returned only the first message by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6374\">https://github.com/Mintplex-Labs/anything-llm/pull/6374</a>\n</li>\n<li>fix: decode GitHub file content as UTF-8 when re-syncing a watched document by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6373\">https://github.com/Mintplex-Labs/anything-llm/pull/6373</a>\n</li>\n<li>fix: llmman model discovery ignored the token entered in settings by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6376\">https://github.com/Mintplex-Labs/anything-llm/pull/6376</a>\n</li>\n<li>KoboldCPP overhaul by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6380\">https://github.com/Mintplex-Labs/anything-llm/pull/6380</a>\n</li>\n<li>fix(xlsx): escape spreadsheet cells the way CSV requires by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6381\">https://github.com/Mintplex-Labs/anything-llm/pull/6381</a>\n</li>\n<li>fix: log chunk header exceeding chunk size by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6386\">https://github.com/Mintplex-Labs/anything-llm/pull/6386</a>\n</li>\n<li>fix: convert a scraped table into a table, not into loose paragraphs by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6387\">https://github.com/Mintplex-Labs/anything-llm/pull/6387</a>\n</li>\n<li>Add OpenRouter service tier selection by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6337\">https://github.com/Mintplex-Labs/anything-llm/pull/6337</a>\n</li>\n<li>Bump embed submodule by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6389\">https://github.com/Mintplex-Labs/anything-llm/pull/6389</a>\n</li>\n<li>Report model loading status for local agent providers by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6392\">https://github.com/Mintplex-Labs/anything-llm/pull/6392</a>\n</li>\n<li>fix: give a merged table cell the columns it covers by @L4XB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6388\">https://github.com/Mintplex-Labs/anything-llm/pull/6388</a>\n</li>\n<li>Fix JSON body corruption when agent flow variables contain quotes by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6402\">https://github.com/Mintplex-Labs/anything-llm/pull/6402</a>\n</li>\n<li>fix(localai): pass API key when fetching generated image URL by @leilei3167 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6425\">https://github.com/Mintplex-Labs/anything-llm/pull/6425</a>\n</li>\n<li>fix: read a system message's content parts in the OpenAI-compatible chat endpoint by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6424\">https://github.com/Mintplex-Labs/anything-llm/pull/6424</a>\n</li>\n<li>fix: return 404 from thread stream-chat for a missing workspace or thread by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6423\">https://github.com/Mintplex-Labs/anything-llm/pull/6423</a>\n</li>\n<li>fix: accept a GitLab clone URL, trailing slash or view URL the way the siblings do by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6420\">https://github.com/Mintplex-Labs/anything-llm/pull/6420</a>\n</li>\n<li>fix: return the TogetherAI context window as a number instead of a promise by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6418\">https://github.com/Mintplex-Labs/anything-llm/pull/6418</a>\n</li>\n<li>fix: carry the Confluence personal access token through the re-sync payload by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6414\">https://github.com/Mintplex-Labs/anything-llm/pull/6414</a>\n</li>\n<li>Resolve GHSA-3f4c-xj8r-h4cr by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6427\">https://github.com/Mintplex-Labs/anything-llm/pull/6427</a>\n</li>\n<li>fix: stop the open-computer scraper deleting brackets from code and labels from links by @shoemoney in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6408\">https://github.com/Mintplex-Labs/anything-llm/pull/6408</a>\n</li>\n<li>fix: add static promptWindowLimit to MoonshotAI and PPIO by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6438\">https://github.com/Mintplex-Labs/anything-llm/pull/6438</a>\n</li>\n<li>fix: reject an empty message list with the existing 400 in the OpenAI-compatible chat endpoint by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6431\">https://github.com/Mintplex-Labs/anything-llm/pull/6431</a>\n</li>\n<li>fix: let Groq's current vision model receive image attachments by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6429\">https://github.com/Mintplex-Labs/anything-llm/pull/6429</a>\n</li>\n<li>fix: re-sync watched GitLab issues and wiki pages by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6433\">https://github.com/Mintplex-Labs/anything-llm/pull/6433</a>\n</li>\n<li>feat: add AnySearch agent web-search provider by @tbontb-iaq in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6439\">https://github.com/Mintplex-Labs/anything-llm/pull/6439</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@qirh made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6206\">https://github.com/Mintplex-Labs/anything-llm/pull/6206</a>\n</li>\n<li>@yeager made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6227\">https://github.com/Mintplex-Labs/anything-llm/pull/6227</a>\n</li>\n<li>@ericcurtin made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6226\">https://github.com/Mintplex-Labs/anything-llm/pull/6226</a>\n</li>\n<li>@TheGoodMorty made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6222\">https://github.com/Mintplex-Labs/anything-llm/pull/6222</a>\n</li>\n<li>@1t1sCooL made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6193\">https://github.com/Mintplex-Labs/anything-llm/pull/6193</a>\n</li>\n<li>@Max-Reisinger made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6175\">https://github.com/Mintplex-Labs/anything-llm/pull/6175</a>\n</li>\n<li>@IdanMit made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6137\">https://github.com/Mintplex-Labs/anything-llm/pull/6137</a>\n</li>\n<li>@Carleoinserra made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6317\">https://github.com/Mintplex-Labs/anything-llm/pull/6317</a>\n</li>\n<li>@tejasashinde made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6319\">https://github.com/Mintplex-Labs/anything-llm/pull/6319</a>\n</li>\n<li>@dawNotPoi made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6286\">https://github.com/Mintplex-Labs/anything-llm/pull/6286</a>\n</li>\n<li>@AbarnaaSree made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6288\">https://github.com/Mintplex-Labs/anything-llm/pull/6288</a>\n</li>\n<li>@Jkand made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6331\">https://github.com/Mintplex-Labs/anything-llm/pull/6331</a>\n</li>\n<li>@axander44 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6344\">https://github.com/Mintplex-Labs/anything-llm/pull/6344</a>\n</li>\n<li>@Ahson-Shaikh made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6360\">https://github.com/Mintplex-Labs/anything-llm/pull/6360</a>\n</li>\n<li>@auyua9 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6348\">https://github.com/Mintplex-Labs/anything-llm/pull/6348</a>\n</li>\n<li>@L4XB made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6378\">https://github.com/Mintplex-Labs/anything-llm/pull/6378</a>\n</li>\n<li>@leilei3167 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6425\">https://github.com/Mintplex-Labs/anything-llm/pull/6425</a>\n</li>\n<li>@shoemoney made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6408\">https://github.com/Mintplex-Labs/anything-llm/pull/6408</a>\n</li>\n<li>@tbontb-iaq made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6439\">https://github.com/Mintplex-Labs/anything-llm/pull/6439</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.1...v1.16.2\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.1...v1.16.2</a></p>\n","assets":[{"contentType":"application/octet-stream","size":631749078,"createdAt":"2026-09-22T18:57:14Z","updatedAt":"2026-09-22T18:57:33Z","downloadCount":190,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":520814592,"createdAt":"2026-09-22T18:57:33Z","updatedAt":"2026-09-22T18:57:45Z","downloadCount":238,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":566063097,"createdAt":"2026-09-22T18:57:45Z","updatedAt":"2026-09-22T18:58:00Z","downloadCount":338,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":903387826,"createdAt":"2026-09-22T18:58:01Z","updatedAt":"2026-09-22T18:58:32Z","downloadCount":640,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":532011890,"createdAt":"2026-09-22T18:58:32Z","updatedAt":"2026-09-22T18:58:57Z","downloadCount":120,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":410276472,"createdAt":"2026-09-22T18:58:57Z","updatedAt":"2026-09-22T18:59:13Z","downloadCount":2917,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":11669,"createdAt":"2026-09-22T18:58:00Z","updatedAt":"2026-09-22T18:58:01Z","downloadCount":138,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/installer.sh"},{"contentType":"text/plain","size":6,"createdAt":"2026-09-22T18:58:01Z","updatedAt":"2026-09-22T18:58:01Z","downloadCount":429,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.2/version.txt"}]},{"id":377971782,"tag":"v1.16.1","author":"timothycarambat","name":"AnythingLLM v1.16.1","draft":false,"prerelease":false,"createdAt":"2026-08-27T16:16:40Z","publishedAt":"2026-08-27T16:42:21Z","markdown":"### Activity and Chain of Thought Overhaul\r\n<img width=\"3680\" height=\"2212\" alt=\"image\" src=\"https://github.com/user-attachments/assets/34e52190-51e3-40b5-baeb-d1936319cb4a\" />\r\n\r\nWe overhauled our UI for long-horizon agentic tasks that show multiple thinking and tool calls to now roll up into a single clean, collapsible UI element.\r\n\r\nThis gives you more screen real estate for the actual response while still keeping the important call stack and thoughts the model produces in an easy-to-read format.\r\n\r\n### Navigation Warning\r\n\r\n<img width=\"3680\" height=\"2212\" alt=\"image\" src=\"https://github.com/user-attachments/assets/dfa98c30-4bde-4321-86cc-eb0bcd7b9873\" />\r\n\r\nRecently, we added true abort signals across every supported LLM so that when you cancel inference or leave the page, we stop inference to save you on compute costs.\r\n\r\nHowever, this had the unintended side effect of canceling inference when navigating away from a chat, preventing background completion. Now we warn you before aborting the response.\r\n\r\n**Roadmap item:** We intend to make this user configurable so you can customize this behavior and allow background inference for those with more powerful or high-concurrency setups where multiple parallel inference sessions are feasible.\r\n\r\n### Foundry Local Embedded (Desktop Only)\r\n\r\n<img width=\"1280\" height=\"720\" alt=\"image\" src=\"https://github.com/user-attachments/assets/d43ba423-83a8-4150-8b62-606ffb6c8882\" />\r\n\r\n[FoundryLocal](https://github.com/microsoft/foundry-local) is an inference engine built by Microsoft that is pre-installed and available on Windows 11 (version 24H2, build 26100 or later).\r\n\r\nThis uses WinML to load models for your CPU, GPU, or NPU across any Windows hardware configuration. It's a great option for hardware configurations we don't have explicit support for. Keep in mind that model availability may be limited as FoundryLocal is still rolling out. Vision models are **not** available currently.\r\n\r\n_We partner with Microsoft for this, if you have bugs or issues we can help forward them to the FoundryLocal team_\r\n\r\n### GenieX for Snapdragon (Desktop Only)\r\n\r\n<img width=\"1280\" height=\"720\" alt=\"image\" src=\"https://github.com/user-attachments/assets/866a7cc2-e3e7-4189-af56-6a29c030aab5\" />\r\n\r\n> [!NOTE]\r\n> This replaces our previous Snapdragon NPU engine. Any previous models from the old engine are deleted on update, and you'll need to re-download these optimized models. You should see a significant performance increase for NPU models and regular GGUFs.\r\n> \r\n> We highly recommend using only GGUF models for this engine. Qualcomm NPU-only models have 4K context windows and will result in a poor agent experience.\r\n\r\n[GenieX](https://github.com/qualcomm/GenieX) is an open-source inference engine built by Qualcomm (previously [NexaAI](https://aihub.qualcomm.com/genai)) that efficiently runs GGUFs and Qualcomm AI Hub models on NPU for X and X2 Elite devices.\r\n\r\nAnythingLLM offers fully managed and built-in support by selecting the \"AnythingLLM GenieX\" provider in the dropdown. Both GGUFs and NPU-only models can leverage the NPU, giving you the power efficiency and intelligence of both.\r\n\r\n_We partner with Qualcomm for this, if you have bugs or issues we can help forward them to the GenieX team or you can make an issue on their GitHub. s/o @zhiyuan8, @alexchen4ai & @alanzhuly_\r\n\r\n## New Features\r\n\r\n- [x] Native Foundry Local SDK on Windows (x64/ARM64) - the Foundry provider is now fully self-contained and no longer requires a separate Foundry Local install, with GPU/NPU-optimized model variants exposed in the catalog\r\n- [x] GenieX runtime support for Windows ARM64 devices\r\n- [x] AWS Bedrock cross-region inference profile support - geo-prefixed profile IDs (`us.`, `eu.`, `global.`) now appear in the model dropdown and route correctly, plus manual region entry for regions outside the preset list (GovCloud, specialized partitions)\r\n- [x] LocalAI added as an image generation provider, listing only image-capable models from your server\r\n- [x] LocalAI context window auto-detection - context windows are read per-model from your server's config, with the manual setting now an optional override\r\n- [x] Silent/headless install and uninstall flags for the Windows installer - see the [Windows installation docs](https://docs.anythingllm.com/installation-desktop/windows#silent--headless-installation)\r\n\r\n## Improvements\r\n\r\n- [x] Chain of thought and agent activity are now a single collapsible component - one line when collapsed, one step per thought with a connected rail when expanded, and the live thought shown in the header while streaming\r\n- [x] The new chain of thought rollup is now mirrored in the Assistant Panel\r\n- [x] Leaving a thread or navigating away mid-inference now warns you before the response is lost, instead of silently killing the generation\r\n- [x] Foundry Local no longer prompts for setup when using the built-in runtime, and auto-loads models by capability detection\r\n- [x] Onboarding light mode styling and a redesigned LLM selection UI\r\n- [x] Beacon now renders thinking blocks and markdown formatting correctly while streaming, with collapsible thinking and a fix for model detail text overflow\r\n- [x] Windows installer now includes a sidebar panel image\r\n- [x] Prompt input drafts now persist between navigation\r\n\r\n## Bug Fixes\r\n\r\n- [x] Fixed a Gemini crash caused by a content-header length mismatch on unpinned `undici` versions - now compatible with both v6 and v7\r\n- [x] Fixed a crash when aborting an Anthropic (or Bedrock Anthropic) response mid-stream in `chat` mode and then sending a follow-up\r\n- [x] Fixed a memory leak from leaked abort-stream listeners, which also caused pausing a response to wipe the entire chat\r\n- [x] Fixed a crash when creating a new workspace\r\n- [x] Fixed missing setup CTAs on modals introduced by the new uniform modal component - Scheduled Job skill setup on both the category and tool views, Community Hub connection key, and the experimental features reject button\r\n- [x] Fixed the intermediate loader being too tall while waiting for an agent capability response\r\n- [x] Fixed the stray border around the delete button in Workspace Chats\r\n- [x] Fixed reasoning getting stuck on \"thinking\" when a model never closes its think tag\r\n- [x] Fixed agent websocket sends firing while the connection was still opening\r\n\r\n## All Changes\r\n* fix: OCR 1-bit scanned PDFs instead of dropping pages by @tzlwn1 in https://github.com/Mintplex-Labs/anything-llm/pull/6128\r\n* New AnythingLLM wordmark + fix logo theme resolution by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6138\r\n* fix: persist API @agent chats into thread history by @LHMQ878 in https://github.com/Mintplex-Labs/anything-llm/pull/6125\r\n* fix: enforce workspace memory limit during extraction by @uczltw6 in https://github.com/Mintplex-Labs/anything-llm/pull/6149\r\n* fix(a11y): announce that a reply is generating, and that one failed by @opensource-joe in https://github.com/Mintplex-Labs/anything-llm/pull/6135\r\n* Feat/cost tracking by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6150\r\n* Fix agent backend crash from oversized tool reranker query by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6152\r\n* Uniform modal component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5741\r\n* chore: drop two package scripts whose targets are gone by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6155\r\n* docs(gcp): describe what the deployment actually creates by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6154\r\n* fix(docker): check the port the server is actually listening on by @marmar9615-cloud in https://github.com/Mintplex-Labs/anything-llm/pull/6159\r\n* docs: fix remaining broken relative links and dead anchors by @simpleqt in https://github.com/Mintplex-Labs/anything-llm/pull/6168\r\n* Route Bedrock cross-region inference profiles via bedrock-runtime by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6181\r\n* Patch crash with Anthropic mid-stream abort/reply by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6186\r\n* LocalAI context window auto-detection by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6177\r\n* Add LocalAI as an image generation provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6176\r\n* Revamp chain of thought UI component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6182\r\n* Prevent unload if under inference workload by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6190\r\n* fix: agent WSS send while connecting + prompt input draft persistence by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6191\r\n* 1.16.1 tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6194\r\n\r\n## New Contributors\r\n* @tzlwn1 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6128\r\n* @LHMQ878 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6125\r\n* @uczltw6 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6149\r\n* @opensource-joe made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6135\r\n* @marmar9615-cloud made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6155\r\n* @simpleqt made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6168\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.0...v1.16.1","html":"<div class=\"markdown-heading\"><h3 class=\"heading-element\">Activity and Chain of Thought Overhaul</h3><a id=\"user-content-activity-and-chain-of-thought-overhaul\" class=\"anchor\" aria-label=\"Permalink: Activity and Chain of Thought Overhaul\" href=\"#activity-and-chain-of-thought-overhaul\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/34e52190-51e3-40b5-baeb-d1936319cb4a\"><img width=\"2000\" height=\"1202\" alt=\"image\" src=\"https://github.com/user-attachments/assets/34e52190-51e3-40b5-baeb-d1936319cb4a\" style=\"max-width: 100%; height: auto; max-height: 1202px;\"></a></p>\n<p>We overhauled our UI for long-horizon agentic tasks that show multiple thinking and tool calls to now roll up into a single clean, collapsible UI element.</p>\n<p>This gives you more screen real estate for the actual response while still keeping the important call stack and thoughts the model produces in an easy-to-read format.</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Navigation Warning</h3><a id=\"user-content-navigation-warning\" class=\"anchor\" aria-label=\"Permalink: Navigation Warning\" href=\"#navigation-warning\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/dfa98c30-4bde-4321-86cc-eb0bcd7b9873\"><img width=\"2000\" height=\"1202\" alt=\"image\" src=\"https://github.com/user-attachments/assets/dfa98c30-4bde-4321-86cc-eb0bcd7b9873\" style=\"max-width: 100%; height: auto; max-height: 1202px;\"></a></p>\n<p>Recently, we added true abort signals across every supported LLM so that when you cancel inference or leave the page, we stop inference to save you on compute costs.</p>\n<p>However, this had the unintended side effect of canceling inference when navigating away from a chat, preventing background completion. Now we warn you before aborting the response.</p>\n<p><strong>Roadmap item:</strong> We intend to make this user configurable so you can customize this behavior and allow background inference for those with more powerful or high-concurrency setups where multiple parallel inference sessions are feasible.</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Foundry Local Embedded (Desktop Only)</h3><a id=\"user-content-foundry-local-embedded-desktop-only\" class=\"anchor\" aria-label=\"Permalink: Foundry Local Embedded (Desktop Only)\" href=\"#foundry-local-embedded-desktop-only\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/d43ba423-83a8-4150-8b62-606ffb6c8882\"><img width=\"1280\" height=\"720\" alt=\"image\" src=\"https://github.com/user-attachments/assets/d43ba423-83a8-4150-8b62-606ffb6c8882\" style=\"max-width: 100%; height: auto; max-height: 720px;\"></a></p>\n<p><a href=\"https://github.com/microsoft/foundry-local\">FoundryLocal</a> is an inference engine built by Microsoft that is pre-installed and available on Windows 11 (version 24H2, build 26100 or later).</p>\n<p>This uses WinML to load models for your CPU, GPU, or NPU across any Windows hardware configuration. It's a great option for hardware configurations we don't have explicit support for. Keep in mind that model availability may be limited as FoundryLocal is still rolling out. Vision models are <strong>not</strong> available currently.</p>\n<p><em>We partner with Microsoft for this, if you have bugs or issues we can help forward them to the FoundryLocal team</em></p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">GenieX for Snapdragon (Desktop Only)</h3><a id=\"user-content-geniex-for-snapdragon-desktop-only\" class=\"anchor\" aria-label=\"Permalink: GenieX for Snapdragon (Desktop Only)\" href=\"#geniex-for-snapdragon-desktop-only\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/866a7cc2-e3e7-4189-af56-6a29c030aab5\"><img width=\"1280\" height=\"720\" alt=\"image\" src=\"https://github.com/user-attachments/assets/866a7cc2-e3e7-4189-af56-6a29c030aab5\" style=\"max-width: 100%; height: auto; max-height: 720px;\"></a></p>\n<blockquote>\n<p>[!NOTE]\nThis replaces our previous Snapdragon NPU engine. Any previous models from the old engine are deleted on update, and you'll need to re-download these optimized models. You should see a significant performance increase for NPU models and regular GGUFs.</p>\n<p>We highly recommend using only GGUF models for this engine. Qualcomm NPU-only models have 4K context windows and will result in a poor agent experience.</p>\n</blockquote>\n<p><a href=\"https://github.com/qualcomm/GenieX\">GenieX</a> is an open-source inference engine built by Qualcomm (previously <a href=\"https://aihub.qualcomm.com/genai\" rel=\"nofollow\">NexaAI</a>) that efficiently runs GGUFs and Qualcomm AI Hub models on NPU for X and X2 Elite devices.</p>\n<p>AnythingLLM offers fully managed and built-in support by selecting the \"AnythingLLM GenieX\" provider in the dropdown. Both GGUFs and NPU-only models can leverage the NPU, giving you the power efficiency and intelligence of both.</p>\n<p><em>We partner with Qualcomm for this, if you have bugs or issues we can help forward them to the GenieX team or you can make an issue on their GitHub. s/o @zhiyuan8, @alexchen4ai &amp; @alanzhuly</em></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Features</h2><a id=\"user-content-new-features\" class=\"anchor\" aria-label=\"Permalink: New Features\" href=\"#new-features\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Native Foundry Local SDK on Windows (x64/ARM64) - the Foundry provider is now fully self-contained and no longer requires a separate Foundry Local install, with GPU/NPU-optimized model variants exposed in the catalog</li>\n<li>[x] GenieX runtime support for Windows ARM64 devices</li>\n<li>[x] AWS Bedrock cross-region inference profile support - geo-prefixed profile IDs (<code>us.</code>, <code>eu.</code>, <code>global.</code>) now appear in the model dropdown and route correctly, plus manual region entry for regions outside the preset list (GovCloud, specialized partitions)</li>\n<li>[x] LocalAI added as an image generation provider, listing only image-capable models from your server</li>\n<li>[x] LocalAI context window auto-detection - context windows are read per-model from your server's config, with the manual setting now an optional override</li>\n<li>[x] Silent/headless install and uninstall flags for the Windows installer - see the <a href=\"https://docs.anythingllm.com/installation-desktop/windows#silent--headless-installation\" rel=\"nofollow\">Windows installation docs</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Improvements</h2><a id=\"user-content-improvements\" class=\"anchor\" aria-label=\"Permalink: Improvements\" href=\"#improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Chain of thought and agent activity are now a single collapsible component - one line when collapsed, one step per thought with a connected rail when expanded, and the live thought shown in the header while streaming</li>\n<li>[x] The new chain of thought rollup is now mirrored in the Assistant Panel</li>\n<li>[x] Leaving a thread or navigating away mid-inference now warns you before the response is lost, instead of silently killing the generation</li>\n<li>[x] Foundry Local no longer prompts for setup when using the built-in runtime, and auto-loads models by capability detection</li>\n<li>[x] Onboarding light mode styling and a redesigned LLM selection UI</li>\n<li>[x] Beacon now renders thinking blocks and markdown formatting correctly while streaming, with collapsible thinking and a fix for model detail text overflow</li>\n<li>[x] Windows installer now includes a sidebar panel image</li>\n<li>[x] Prompt input drafts now persist between navigation</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Bug Fixes</h2><a id=\"user-content-bug-fixes\" class=\"anchor\" aria-label=\"Permalink: Bug Fixes\" href=\"#bug-fixes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Fixed a Gemini crash caused by a content-header length mismatch on unpinned <code>undici</code> versions - now compatible with both v6 and v7</li>\n<li>[x] Fixed a crash when aborting an Anthropic (or Bedrock Anthropic) response mid-stream in <code>chat</code> mode and then sending a follow-up</li>\n<li>[x] Fixed a memory leak from leaked abort-stream listeners, which also caused pausing a response to wipe the entire chat</li>\n<li>[x] Fixed a crash when creating a new workspace</li>\n<li>[x] Fixed missing setup CTAs on modals introduced by the new uniform modal component - Scheduled Job skill setup on both the category and tool views, Community Hub connection key, and the experimental features reject button</li>\n<li>[x] Fixed the intermediate loader being too tall while waiting for an agent capability response</li>\n<li>[x] Fixed the stray border around the delete button in Workspace Chats</li>\n<li>[x] Fixed reasoning getting stuck on \"thinking\" when a model never closes its think tag</li>\n<li>[x] Fixed agent websocket sends firing while the connection was still opening</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">All Changes</h2><a id=\"user-content-all-changes\" class=\"anchor\" aria-label=\"Permalink: All Changes\" href=\"#all-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix: OCR 1-bit scanned PDFs instead of dropping pages by @tzlwn1 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6128\">https://github.com/Mintplex-Labs/anything-llm/pull/6128</a>\n</li>\n<li>New AnythingLLM wordmark + fix logo theme resolution by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6138\">https://github.com/Mintplex-Labs/anything-llm/pull/6138</a>\n</li>\n<li>fix: persist API @agent chats into thread history by @LHMQ878 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6125\">https://github.com/Mintplex-Labs/anything-llm/pull/6125</a>\n</li>\n<li>fix: enforce workspace memory limit during extraction by @uczltw6 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6149\">https://github.com/Mintplex-Labs/anything-llm/pull/6149</a>\n</li>\n<li>fix(a11y): announce that a reply is generating, and that one failed by @opensource-joe in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6135\">https://github.com/Mintplex-Labs/anything-llm/pull/6135</a>\n</li>\n<li>Feat/cost tracking by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6150\">https://github.com/Mintplex-Labs/anything-llm/pull/6150</a>\n</li>\n<li>Fix agent backend crash from oversized tool reranker query by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6152\">https://github.com/Mintplex-Labs/anything-llm/pull/6152</a>\n</li>\n<li>Uniform modal component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5741\">https://github.com/Mintplex-Labs/anything-llm/pull/5741</a>\n</li>\n<li>chore: drop two package scripts whose targets are gone by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6155\">https://github.com/Mintplex-Labs/anything-llm/pull/6155</a>\n</li>\n<li>docs(gcp): describe what the deployment actually creates by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6154\">https://github.com/Mintplex-Labs/anything-llm/pull/6154</a>\n</li>\n<li>fix(docker): check the port the server is actually listening on by @marmar9615-cloud in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6159\">https://github.com/Mintplex-Labs/anything-llm/pull/6159</a>\n</li>\n<li>docs: fix remaining broken relative links and dead anchors by @simpleqt in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6168\">https://github.com/Mintplex-Labs/anything-llm/pull/6168</a>\n</li>\n<li>Route Bedrock cross-region inference profiles via bedrock-runtime by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6181\">https://github.com/Mintplex-Labs/anything-llm/pull/6181</a>\n</li>\n<li>Patch crash with Anthropic mid-stream abort/reply by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6186\">https://github.com/Mintplex-Labs/anything-llm/pull/6186</a>\n</li>\n<li>LocalAI context window auto-detection by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6177\">https://github.com/Mintplex-Labs/anything-llm/pull/6177</a>\n</li>\n<li>Add LocalAI as an image generation provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6176\">https://github.com/Mintplex-Labs/anything-llm/pull/6176</a>\n</li>\n<li>Revamp chain of thought UI component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6182\">https://github.com/Mintplex-Labs/anything-llm/pull/6182</a>\n</li>\n<li>Prevent unload if under inference workload by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6190\">https://github.com/Mintplex-Labs/anything-llm/pull/6190</a>\n</li>\n<li>fix: agent WSS send while connecting + prompt input draft persistence by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6191\">https://github.com/Mintplex-Labs/anything-llm/pull/6191</a>\n</li>\n<li>1.16.1 tags by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6194\">https://github.com/Mintplex-Labs/anything-llm/pull/6194</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@tzlwn1 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6128\">https://github.com/Mintplex-Labs/anything-llm/pull/6128</a>\n</li>\n<li>@LHMQ878 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6125\">https://github.com/Mintplex-Labs/anything-llm/pull/6125</a>\n</li>\n<li>@uczltw6 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6149\">https://github.com/Mintplex-Labs/anything-llm/pull/6149</a>\n</li>\n<li>@opensource-joe made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6135\">https://github.com/Mintplex-Labs/anything-llm/pull/6135</a>\n</li>\n<li>@marmar9615-cloud made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6155\">https://github.com/Mintplex-Labs/anything-llm/pull/6155</a>\n</li>\n<li>@simpleqt made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6168\">https://github.com/Mintplex-Labs/anything-llm/pull/6168</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.0...v1.16.1\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.16.0...v1.16.1</a></p>\n","assets":[{"contentType":"application/octet-stream","size":631052881,"createdAt":"2026-08-27T16:37:21Z","updatedAt":"2026-08-27T16:37:42Z","downloadCount":324,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":521403672,"createdAt":"2026-08-27T16:37:42Z","updatedAt":"2026-08-27T16:37:58Z","downloadCount":555,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":547603907,"createdAt":"2026-08-27T16:37:58Z","updatedAt":"2026-08-27T16:38:13Z","downloadCount":729,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":902698392,"createdAt":"2026-08-27T16:36:22Z","updatedAt":"2026-08-27T16:36:51Z","downloadCount":1461,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":513697075,"createdAt":"2026-08-27T16:36:51Z","updatedAt":"2026-08-27T16:37:07Z","downloadCount":250,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":410516264,"createdAt":"2026-08-27T16:37:07Z","updatedAt":"2026-08-27T16:37:21Z","downloadCount":11397,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":11669,"createdAt":"2026-08-27T16:38:13Z","updatedAt":"2026-08-27T16:38:13Z","downloadCount":303,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.1/installer.sh"}]},{"id":370225907,"tag":"v1.16.0","author":"timothycarambat","name":"AnythingLLM v1.16.0","draft":false,"prerelease":false,"createdAt":"2026-08-13T21:27:31Z","publishedAt":"2026-08-13T21:38:01Z","markdown":"## Notable Changes\r\n\r\n### Image Generation\r\n\r\nNow you can generate images via `/img` when a [supported provider is set up](https://docs.anythingllm.com/features/image-generation#supported-providers).\r\n\r\nThis flow also allows image attachments for edits, followups, or combination prompts if your provider supports image editing.\r\n\r\n<img width=\"2254\" height=\"986\" alt=\"image\" src=\"https://github.com/user-attachments/assets/9286ba43-c8fe-43f9-a18d-6c2814f6907f\" />\r\n\r\n\r\n> Ability for an agent-tool to generate images is coming next update.\r\n\r\n### Better File Picker UX\r\n\r\nNow in the file picker you can drag entire folders and their hierarchy will be preserved in the upload panel. This will only import the **top level** files in the folder — it will be deep and recursive in a later update.\r\n\r\nYou can also now drag and drop a file into an existing folder directly without needing to move it.\r\n\r\nLastly, you no longer need to type `https` in the URL fetcher - it will just assume https when left out.\r\n\r\nWe also made some large performance improvements, like lazy-loading of folders, for those with thousands of documents in a folder.\r\n\r\n### Tool Toggle Mid-Session\r\n\r\nNow, during agentic chats you can freely toggle tools on/off at will without needing to reload or start a new session. Only tools that have been configured (if configuration is required) are available.\r\n\r\n### Stop Generation\r\n\r\nA large improvement is now that `aborting` a response actually fully kills the inference as well so that ghost inference does not continue when no longer wanted mid-stream.\r\n\r\n\r\n## All Changes\r\n* feat: increases the username character limit to 64 by @guilopesn in https://github.com/Mintplex-Labs/anything-llm/pull/5914\r\n* Fixes typos and mistakes in Catalan translation by @jordimas in https://github.com/Mintplex-Labs/anything-llm/pull/5923\r\n* Update default fallback models for OpenAI/Anthropic by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5949\r\n* fix: disable temperature for claude-sonnet-5 model by @petre in https://github.com/Mintplex-Labs/anything-llm/pull/5947\r\n* fix: stream Anthropic non-streaming chat completions for REST API workspace chat by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5941\r\n* feat: add support for openai-compatible whisper api by @guilopesn in https://github.com/Mintplex-Labs/anything-llm/pull/5952\r\n* fix: render kokoro-tts voice list for pre-0.3.x kokoro-fastapi servers by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5930\r\n* OC readme bump by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5966\r\n* fix: scope thread lookup to validated workspace in validWorkspaceAndThreadSlug by @Joshua-Medvinsky in https://github.com/Mintplex-Labs/anything-llm/pull/5784\r\n* fix: MCP servers hidden from UI by post-connection errors and url-only definitions rejected by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5943\r\n* Agent SQL Connector Fixes by @ss-rstocchi in https://github.com/Mintplex-Labs/anything-llm/pull/5922\r\n* Fix scrollbar color on light mode by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5980\r\n* (OpenComputer) Update model version in use case demos by @FI-Mihej in https://github.com/Mintplex-Labs/anything-llm/pull/5978\r\n* Give Downloaded Models its Own `<optgroup>` in Workspace Model Selector by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5967\r\n* Gate Workspace System Prompt Override in `Workspace.new()` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5971\r\n* feat: add Windows x64 (WHPX) support to open-computer by @Varun-Patkar in https://github.com/Mintplex-Labs/anything-llm/pull/5982\r\n* test: fix isoDeviceArgs unit test after usb-storage change by @Varun-Patkar in https://github.com/Mintplex-Labs/anything-llm/pull/5987\r\n* Patch API Citations regression by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5994\r\n* Patch Generic OpenAI bug for OSA with Magic Echo by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5995\r\n* Add Translations for Create Scheduled Job Agent Tool by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5932\r\n* feat: create-scheduled-job agent tool by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5916\r\n* docs(bare-metal): fix env var name to match frontend/.env — VITE_API_BASE by @unusdon in https://github.com/Mintplex-Labs/anything-llm/pull/5996\r\n* oMLX LLM Provider  by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5973\r\n* Toggle agent tools during an active agent session by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5856\r\n* fix: preserve TTS audio content type by @ivan-digital in https://github.com/Mintplex-Labs/anything-llm/pull/6012\r\n* Fix slash command presets not expanding into prompt text by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6038\r\n* Update Italian translation by @albanobattistella in https://github.com/Mintplex-Labs/anything-llm/pull/6018\r\n* i18n: add Lao (lo) language support by @bounkirdni-2025 in https://github.com/Mintplex-Labs/anything-llm/pull/6039\r\n* feat(i18n): add Indonesian (id) language support - closes #4198 by @samlehoy in https://github.com/Mintplex-Labs/anything-llm/pull/6037\r\n* Inline MCP tool $ref/$defs schemas for Anthropic agent tool calls by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5786\r\n* 5846 auto scroll by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6046\r\n* i18n: add Croatian (hr) language support by @devanonyme42 in https://github.com/Mintplex-Labs/anything-llm/pull/6052\r\n* feat(agents): add You.com as web search provider by @Souravrajvi0 in https://github.com/Mintplex-Labs/anything-llm/pull/6058\r\n* refactor: remove workspace profile picture feature by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6010\r\n* Add datetime to default system prompts by @Adityai1411 in https://github.com/Mintplex-Labs/anything-llm/pull/6016\r\n* Fix: Restore Stop Generation Button During Agent Session Execution Loop by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5970\r\n* feat: folder upload with relative paths preserved in document manager by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6027\r\n* fix: keep watched document re-syncs from breaking pinned document de-duplication by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6029\r\n* Add input_audio support for audio attachments on generic OpenAI provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6055\r\n* Start model router cooldown after inference completes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6047\r\n* fix: validate workspace update payloads to prevent misleading 200 responses by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6070\r\n* chore: route agent chats with no tools through native tooled completions by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6067\r\n* fix Bedrock model workspace selection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6079\r\n* fix empty agent skill section in MuM by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6080\r\n* Reset agent clarifying-questions counter per turn by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/6083\r\n* AWS Bedrock overhaul by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6081\r\n* feat: abort agent sessions end-to-end when the user stops generation by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/6063\r\n* docs: fix broken service links in open-computer README by @richboyneedcash in https://github.com/Mintplex-Labs/anything-llm/pull/6088\r\n* feat: add image generation via /img command by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5904\r\n* 6089 milvus count by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6095\r\n* feat: add Gitea data connector by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6087\r\n* Fix generic openai thinking parsers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6105\r\n* fix(i18n): correct zh-TW scheduled job labels by @nrps9909 in https://github.com/Mintplex-Labs/anything-llm/pull/6112\r\n* feat: stream PiperTTS playback + harden long-message TTS by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6114\r\n* FoundryLocal overhaul by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6119\r\n* feat: support GitHub Enterprise URLs in the GitHub data connector by @ArslanRasheed60 in https://github.com/Mintplex-Labs/anything-llm/pull/6117\r\n* v1.16.0 tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/6122\r\n\r\n## New Contributors\r\n* @Joshua-Medvinsky made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5784\r\n* @ss-rstocchi made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5922\r\n* @FI-Mihej made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5978\r\n* @Varun-Patkar made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5982\r\n* @unusdon made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5996\r\n* @ivan-digital made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6012\r\n* @albanobattistella made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6018\r\n* @bounkirdni-2025 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6039\r\n* @samlehoy made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6037\r\n* @devanonyme42 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6052\r\n* @Souravrajvi0 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6058\r\n* @Adityai1411 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6016\r\n* @ArslanRasheed60 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6029\r\n* @richboyneedcash made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6088\r\n* @nrps9909 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/6112\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.15.0...v1.16.0","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Changes</h2><a id=\"user-content-notable-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Changes\" href=\"#notable-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Image Generation</h3><a id=\"user-content-image-generation\" class=\"anchor\" aria-label=\"Permalink: Image Generation\" href=\"#image-generation\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now you can generate images via <code>/img</code> when a <a href=\"https://docs.anythingllm.com/features/image-generation#supported-providers\" rel=\"nofollow\">supported provider is set up</a>.</p>\n<p>This flow also allows image attachments for edits, followups, or combination prompts if your provider supports image editing.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/9286ba43-c8fe-43f9-a18d-6c2814f6907f\"><img width=\"2000\" height=\"875\" alt=\"image\" src=\"https://github.com/user-attachments/assets/9286ba43-c8fe-43f9-a18d-6c2814f6907f\" style=\"max-width: 100%; height: auto; max-height: 875px;\"></a></p>\n<blockquote>\n<p>Ability for an agent-tool to generate images is coming next update.</p>\n</blockquote>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Better File Picker UX</h3><a id=\"user-content-better-file-picker-ux\" class=\"anchor\" aria-label=\"Permalink: Better File Picker UX\" href=\"#better-file-picker-ux\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now in the file picker you can drag entire folders and their hierarchy will be preserved in the upload panel. This will only import the <strong>top level</strong> files in the folder — it will be deep and recursive in a later update.</p>\n<p>You can also now drag and drop a file into an existing folder directly without needing to move it.</p>\n<p>Lastly, you no longer need to type <code>https</code> in the URL fetcher - it will just assume https when left out.</p>\n<p>We also made some large performance improvements, like lazy-loading of folders, for those with thousands of documents in a folder.</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Tool Toggle Mid-Session</h3><a id=\"user-content-tool-toggle-mid-session\" class=\"anchor\" aria-label=\"Permalink: Tool Toggle Mid-Session\" href=\"#tool-toggle-mid-session\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, during agentic chats you can freely toggle tools on/off at will without needing to reload or start a new session. Only tools that have been configured (if configuration is required) are available.</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Stop Generation</h3><a id=\"user-content-stop-generation\" class=\"anchor\" aria-label=\"Permalink: Stop Generation\" href=\"#stop-generation\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>A large improvement is now that <code>aborting</code> a response actually fully kills the inference as well so that ghost inference does not continue when no longer wanted mid-stream.</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">All Changes</h2><a id=\"user-content-all-changes\" class=\"anchor\" aria-label=\"Permalink: All Changes\" href=\"#all-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>feat: increases the username character limit to 64 by @guilopesn in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5914\">https://github.com/Mintplex-Labs/anything-llm/pull/5914</a>\n</li>\n<li>Fixes typos and mistakes in Catalan translation by @jordimas in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5923\">https://github.com/Mintplex-Labs/anything-llm/pull/5923</a>\n</li>\n<li>Update default fallback models for OpenAI/Anthropic by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5949\">https://github.com/Mintplex-Labs/anything-llm/pull/5949</a>\n</li>\n<li>fix: disable temperature for claude-sonnet-5 model by @petre in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5947\">https://github.com/Mintplex-Labs/anything-llm/pull/5947</a>\n</li>\n<li>fix: stream Anthropic non-streaming chat completions for REST API workspace chat by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5941\">https://github.com/Mintplex-Labs/anything-llm/pull/5941</a>\n</li>\n<li>feat: add support for openai-compatible whisper api by @guilopesn in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5952\">https://github.com/Mintplex-Labs/anything-llm/pull/5952</a>\n</li>\n<li>fix: render kokoro-tts voice list for pre-0.3.x kokoro-fastapi servers by @sanidhyasin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5930\">https://github.com/Mintplex-Labs/anything-llm/pull/5930</a>\n</li>\n<li>OC readme bump by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5966\">https://github.com/Mintplex-Labs/anything-llm/pull/5966</a>\n</li>\n<li>fix: scope thread lookup to validated workspace in validWorkspaceAndThreadSlug by @Joshua-Medvinsky in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5784\">https://github.com/Mintplex-Labs/anything-llm/pull/5784</a>\n</li>\n<li>fix: MCP servers hidden from UI by post-connection errors and url-only definitions rejected by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5943\">https://github.com/Mintplex-Labs/anything-llm/pull/5943</a>\n</li>\n<li>Agent SQL Connector Fixes by @ss-rstocchi in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5922\">https://github.com/Mintplex-Labs/anything-llm/pull/5922</a>\n</li>\n<li>Fix scrollbar color on light mode by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5980\">https://github.com/Mintplex-Labs/anything-llm/pull/5980</a>\n</li>\n<li>(OpenComputer) Update model version in use case demos by @FI-Mihej in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5978\">https://github.com/Mintplex-Labs/anything-llm/pull/5978</a>\n</li>\n<li>Give Downloaded Models its Own <code>&lt;optgroup&gt;</code> in Workspace Model Selector by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5967\">https://github.com/Mintplex-Labs/anything-llm/pull/5967</a>\n</li>\n<li>Gate Workspace System Prompt Override in <code>Workspace.new()</code> by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5971\">https://github.com/Mintplex-Labs/anything-llm/pull/5971</a>\n</li>\n<li>feat: add Windows x64 (WHPX) support to open-computer by @Varun-Patkar in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5982\">https://github.com/Mintplex-Labs/anything-llm/pull/5982</a>\n</li>\n<li>test: fix isoDeviceArgs unit test after usb-storage change by @Varun-Patkar in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5987\">https://github.com/Mintplex-Labs/anything-llm/pull/5987</a>\n</li>\n<li>Patch API Citations regression by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5994\">https://github.com/Mintplex-Labs/anything-llm/pull/5994</a>\n</li>\n<li>Patch Generic OpenAI bug for OSA with Magic Echo by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5995\">https://github.com/Mintplex-Labs/anything-llm/pull/5995</a>\n</li>\n<li>Add Translations for Create Scheduled Job Agent Tool by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5932\">https://github.com/Mintplex-Labs/anything-llm/pull/5932</a>\n</li>\n<li>feat: create-scheduled-job agent tool by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5916\">https://github.com/Mintplex-Labs/anything-llm/pull/5916</a>\n</li>\n<li>docs(bare-metal): fix env var name to match frontend/.env — VITE_API_BASE by @unusdon in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5996\">https://github.com/Mintplex-Labs/anything-llm/pull/5996</a>\n</li>\n<li>oMLX LLM Provider  by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5973\">https://github.com/Mintplex-Labs/anything-llm/pull/5973</a>\n</li>\n<li>Toggle agent tools during an active agent session by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5856\">https://github.com/Mintplex-Labs/anything-llm/pull/5856</a>\n</li>\n<li>fix: preserve TTS audio content type by @ivan-digital in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6012\">https://github.com/Mintplex-Labs/anything-llm/pull/6012</a>\n</li>\n<li>Fix slash command presets not expanding into prompt text by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6038\">https://github.com/Mintplex-Labs/anything-llm/pull/6038</a>\n</li>\n<li>Update Italian translation by @albanobattistella in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6018\">https://github.com/Mintplex-Labs/anything-llm/pull/6018</a>\n</li>\n<li>i18n: add Lao (lo) language support by @bounkirdni-2025 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6039\">https://github.com/Mintplex-Labs/anything-llm/pull/6039</a>\n</li>\n<li>feat(i18n): add Indonesian (id) language support - closes #4198 by @samlehoy in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6037\">https://github.com/Mintplex-Labs/anything-llm/pull/6037</a>\n</li>\n<li>Inline MCP tool $ref/$defs schemas for Anthropic agent tool calls by @sanidhyasin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5786\">https://github.com/Mintplex-Labs/anything-llm/pull/5786</a>\n</li>\n<li>5846 auto scroll by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6046\">https://github.com/Mintplex-Labs/anything-llm/pull/6046</a>\n</li>\n<li>i18n: add Croatian (hr) language support by @devanonyme42 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6052\">https://github.com/Mintplex-Labs/anything-llm/pull/6052</a>\n</li>\n<li>feat(agents): add You.com as web search provider by @Souravrajvi0 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6058\">https://github.com/Mintplex-Labs/anything-llm/pull/6058</a>\n</li>\n<li>refactor: remove workspace profile picture feature by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6010\">https://github.com/Mintplex-Labs/anything-llm/pull/6010</a>\n</li>\n<li>Add datetime to default system prompts by @Adityai1411 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6016\">https://github.com/Mintplex-Labs/anything-llm/pull/6016</a>\n</li>\n<li>Fix: Restore Stop Generation Button During Agent Session Execution Loop by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5970\">https://github.com/Mintplex-Labs/anything-llm/pull/5970</a>\n</li>\n<li>feat: folder upload with relative paths preserved in document manager by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6027\">https://github.com/Mintplex-Labs/anything-llm/pull/6027</a>\n</li>\n<li>fix: keep watched document re-syncs from breaking pinned document de-duplication by @ArslanRasheed60 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6029\">https://github.com/Mintplex-Labs/anything-llm/pull/6029</a>\n</li>\n<li>Add input_audio support for audio attachments on generic OpenAI provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6055\">https://github.com/Mintplex-Labs/anything-llm/pull/6055</a>\n</li>\n<li>Start model router cooldown after inference completes by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6047\">https://github.com/Mintplex-Labs/anything-llm/pull/6047</a>\n</li>\n<li>fix: validate workspace update payloads to prevent misleading 200 responses by @ArslanRasheed60 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6070\">https://github.com/Mintplex-Labs/anything-llm/pull/6070</a>\n</li>\n<li>chore: route agent chats with no tools through native tooled completions by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6067\">https://github.com/Mintplex-Labs/anything-llm/pull/6067</a>\n</li>\n<li>fix Bedrock model workspace selection by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6079\">https://github.com/Mintplex-Labs/anything-llm/pull/6079</a>\n</li>\n<li>fix empty agent skill section in MuM by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6080\">https://github.com/Mintplex-Labs/anything-llm/pull/6080</a>\n</li>\n<li>Reset agent clarifying-questions counter per turn by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6083\">https://github.com/Mintplex-Labs/anything-llm/pull/6083</a>\n</li>\n<li>AWS Bedrock overhaul by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6081\">https://github.com/Mintplex-Labs/anything-llm/pull/6081</a>\n</li>\n<li>feat: abort agent sessions end-to-end when the user stops generation by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6063\">https://github.com/Mintplex-Labs/anything-llm/pull/6063</a>\n</li>\n<li>docs: fix broken service links in open-computer README by @richboyneedcash in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6088\">https://github.com/Mintplex-Labs/anything-llm/pull/6088</a>\n</li>\n<li>feat: add image generation via /img command by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5904\">https://github.com/Mintplex-Labs/anything-llm/pull/5904</a>\n</li>\n<li>6089 milvus count by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6095\">https://github.com/Mintplex-Labs/anything-llm/pull/6095</a>\n</li>\n<li>feat: add Gitea data connector by @ArslanRasheed60 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6087\">https://github.com/Mintplex-Labs/anything-llm/pull/6087</a>\n</li>\n<li>Fix generic openai thinking parsers by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6105\">https://github.com/Mintplex-Labs/anything-llm/pull/6105</a>\n</li>\n<li>fix(i18n): correct zh-TW scheduled job labels by @nrps9909 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6112\">https://github.com/Mintplex-Labs/anything-llm/pull/6112</a>\n</li>\n<li>feat: stream PiperTTS playback + harden long-message TTS by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6114\">https://github.com/Mintplex-Labs/anything-llm/pull/6114</a>\n</li>\n<li>FoundryLocal overhaul by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6119\">https://github.com/Mintplex-Labs/anything-llm/pull/6119</a>\n</li>\n<li>feat: support GitHub Enterprise URLs in the GitHub data connector by @ArslanRasheed60 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6117\">https://github.com/Mintplex-Labs/anything-llm/pull/6117</a>\n</li>\n<li>v1.16.0 tags by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6122\">https://github.com/Mintplex-Labs/anything-llm/pull/6122</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@Joshua-Medvinsky made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5784\">https://github.com/Mintplex-Labs/anything-llm/pull/5784</a>\n</li>\n<li>@ss-rstocchi made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5922\">https://github.com/Mintplex-Labs/anything-llm/pull/5922</a>\n</li>\n<li>@FI-Mihej made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5978\">https://github.com/Mintplex-Labs/anything-llm/pull/5978</a>\n</li>\n<li>@Varun-Patkar made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5982\">https://github.com/Mintplex-Labs/anything-llm/pull/5982</a>\n</li>\n<li>@unusdon made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5996\">https://github.com/Mintplex-Labs/anything-llm/pull/5996</a>\n</li>\n<li>@ivan-digital made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6012\">https://github.com/Mintplex-Labs/anything-llm/pull/6012</a>\n</li>\n<li>@albanobattistella made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6018\">https://github.com/Mintplex-Labs/anything-llm/pull/6018</a>\n</li>\n<li>@bounkirdni-2025 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6039\">https://github.com/Mintplex-Labs/anything-llm/pull/6039</a>\n</li>\n<li>@samlehoy made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6037\">https://github.com/Mintplex-Labs/anything-llm/pull/6037</a>\n</li>\n<li>@devanonyme42 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6052\">https://github.com/Mintplex-Labs/anything-llm/pull/6052</a>\n</li>\n<li>@Souravrajvi0 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6058\">https://github.com/Mintplex-Labs/anything-llm/pull/6058</a>\n</li>\n<li>@Adityai1411 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6016\">https://github.com/Mintplex-Labs/anything-llm/pull/6016</a>\n</li>\n<li>@ArslanRasheed60 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6029\">https://github.com/Mintplex-Labs/anything-llm/pull/6029</a>\n</li>\n<li>@richboyneedcash made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6088\">https://github.com/Mintplex-Labs/anything-llm/pull/6088</a>\n</li>\n<li>@nrps9909 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/6112\">https://github.com/Mintplex-Labs/anything-llm/pull/6112</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.15.0...v1.16.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.15.0...v1.16.0</a></p>\n","assets":[{"contentType":"application/octet-stream","size":556480535,"createdAt":"2026-08-13T21:33:50Z","updatedAt":"2026-08-13T21:34:07Z","downloadCount":208,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.0/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":543081424,"createdAt":"2026-08-13T21:34:07Z","updatedAt":"2026-08-13T21:34:23Z","downloadCount":328,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.0/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":506752783,"createdAt":"2026-08-13T21:34:23Z","updatedAt":"2026-08-13T21:34:39Z","downloadCount":842,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.0/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":577247582,"createdAt":"2026-08-13T21:33:04Z","updatedAt":"2026-08-13T21:33:21Z","downloadCount":832,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.0/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":513222878,"createdAt":"2026-08-13T21:33:22Z","updatedAt":"2026-08-13T21:33:37Z","downloadCount":151,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.0/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":396070296,"createdAt":"2026-08-13T21:33:37Z","updatedAt":"2026-08-13T21:33:50Z","downloadCount":5568,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.16.0/AnythingLLMDesktop.exe"}]},{"id":345036070,"tag":"v1.15.0","author":"timothycarambat","name":"AnythingLLM v1.15.0","draft":false,"prerelease":false,"createdAt":"2026-06-25T23:13:36Z","publishedAt":"2026-06-25T23:25:52Z","markdown":"# AnythingLLM Is Now An AI Agent Across Your Os\r\n\r\nWith AnythingLLM 1.15.0 for Desktop we have been working *hard* on what it means to bring your agent **to you**. Something that is still local, but outside of the walls of an app or a browser. This release features our first 3 features about this effort - we hope you enjoy them.\r\n\r\n\r\n## Introducing Magic Features\r\n\r\nMagic Features bring AI to your entire computer — not just inside AnythingLLM. Dictation, text actions, and autocomplete that work in any app, fully on-device. \r\n\r\nAll Magic Features are free to use — no signup required. Pro removes the daily limits.\r\n\r\n#### AnythingLLM Pro\r\n\r\nNothing about AnythingLLM is changing. Pro is purely additive — no existing features are affected, nothing is being locked away. \r\n\r\nEvery Pro feature will always have a free daily tier, no signup required.\r\n\r\nYou can read more about what AnythingLLM Pro is [here](https://docs.anythingllm.com/pro/overview).\r\n\r\n## Magic Echo - [Docs](https://docs.anythingllm.com/pro/magic-echo)\r\n\r\n> A smarter voice-to-text dictation that works anywhere on your OS. Can replace tools like SuperWhisper or WhisprFlow entirely. Fully on-device.\r\n\r\nSpeak naturally and your words appear right where your cursor is — transcribed, cleaned up, and punctuated. Echo can see what's on your screen to make dictations smarter and more contextual. \r\n\r\nIncludes custom dictionary support, voice commands, and more.\r\n\r\n<video src=\"https://github.com/user-attachments/assets/8c04002f-04e7-4c93-8ea8-21bda0871293\"></video>\r\n\r\n## Magic Beacon - [Docs](https://docs.anythingllm.com/pro/magic-beacon)\r\n\r\n> Highlight text in any app and instantly act on it with AI.\r\n\r\nHighlight any text on your screen and instantly act on it — summarize, translate, rewrite, research, or run a custom action. Beacon works in any app without switching windows. \r\n\r\nIt also has full access to your agent skills, MCPs, and tools — AnythingLLM's entire capability set, available anywhere your cursor is.\r\n\r\n<video src=\"https://github.com/user-attachments/assets/b8131375-5530-41ae-9fc8-620944552c51\"></video>\r\n\r\n## Magic Tab - [Docs](https://docs.anythingllm.com/pro/magic-tab)\r\n\r\n> Grammarly across your entire computer - fully on-device.\r\n\r\nAs you type, Magic Tab suggests what comes next — in any app, aware of what you're working on so suggestions actually fit. Click into a text field and it'll suggest something before you've typed a single letter. \r\n\r\nIf you use Grammarly, Tab can replace it entirely — privately, on your device.\r\n\r\n<video src=\"https://github.com/user-attachments/assets/8a84189d-efbf-411b-ad22-e3d31ec6273d\"></video>\r\n\r\n----\r\n\r\n\r\n## What's Changed\r\n* Unlock Chat History Cap by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5906\r\n* fix: API update-embeddings fails with Prisma \"filename is missing\" on Windows paths by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5907\r\n* Intelligent Tool Selection (`ToolReranker`) enabled by default by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5893\r\n* feat: add query/passage prefix env vars to GenericOpenAi embedder by @jhsmith409 in https://github.com/Mintplex-Labs/anything-llm/pull/5589\r\n* 1.15.0 tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5909\r\n\r\n## New Contributors\r\n* @jhsmith409 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5589\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.2...v1.15.0","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">AnythingLLM Is Now An AI Agent Across Your Os</h1><a id=\"user-content-anythingllm-is-now-an-ai-agent-across-your-os\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM Is Now An AI Agent Across Your Os\" href=\"#anythingllm-is-now-an-ai-agent-across-your-os\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>With AnythingLLM 1.15.0 for Desktop we have been working <em>hard</em> on what it means to bring your agent <strong>to you</strong>. Something that is still local, but outside of the walls of an app or a browser. This release features our first 3 features about this effort - we hope you enjoy them.</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Introducing Magic Features</h2><a id=\"user-content-introducing-magic-features\" class=\"anchor\" aria-label=\"Permalink: Introducing Magic Features\" href=\"#introducing-magic-features\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Magic Features bring AI to your entire computer — not just inside AnythingLLM. Dictation, text actions, and autocomplete that work in any app, fully on-device.</p>\n<p>All Magic Features are free to use — no signup required. Pro removes the daily limits.</p>\n<div class=\"markdown-heading\"><h4 class=\"heading-element\">AnythingLLM Pro</h4><a id=\"user-content-anythingllm-pro\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM Pro\" href=\"#anythingllm-pro\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Nothing about AnythingLLM is changing. Pro is purely additive — no existing features are affected, nothing is being locked away.</p>\n<p>Every Pro feature will always have a free daily tier, no signup required.</p>\n<p>You can read more about what AnythingLLM Pro is <a href=\"https://docs.anythingllm.com/pro/overview\" rel=\"nofollow\">here</a>.</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Magic Echo - <a href=\"https://docs.anythingllm.com/pro/magic-echo\" rel=\"nofollow\">Docs</a>\n</h2><a id=\"user-content-magic-echo---docs\" class=\"anchor\" aria-label=\"Permalink: Magic Echo - Docs\" href=\"#magic-echo---docs\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<blockquote>\n<p>A smarter voice-to-text dictation that works anywhere on your OS. Can replace tools like SuperWhisper or WhisprFlow entirely. Fully on-device.</p>\n</blockquote>\n<p>Speak naturally and your words appear right where your cursor is — transcribed, cleaned up, and punctuated. Echo can see what's on your screen to make dictations smarter and more contextual.</p>\n<p>Includes custom dictionary support, voice commands, and more.</p>\n<p></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Magic Beacon - <a href=\"https://docs.anythingllm.com/pro/magic-beacon\" rel=\"nofollow\">Docs</a>\n</h2><a id=\"user-content-magic-beacon---docs\" class=\"anchor\" aria-label=\"Permalink: Magic Beacon - Docs\" href=\"#magic-beacon---docs\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<blockquote>\n<p>Highlight text in any app and instantly act on it with AI.</p>\n</blockquote>\n<p>Highlight any text on your screen and instantly act on it — summarize, translate, rewrite, research, or run a custom action. Beacon works in any app without switching windows.</p>\n<p>It also has full access to your agent skills, MCPs, and tools — AnythingLLM's entire capability set, available anywhere your cursor is.</p>\n<p></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Magic Tab - <a href=\"https://docs.anythingllm.com/pro/magic-tab\" rel=\"nofollow\">Docs</a>\n</h2><a id=\"user-content-magic-tab---docs\" class=\"anchor\" aria-label=\"Permalink: Magic Tab - Docs\" href=\"#magic-tab---docs\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<blockquote>\n<p>Grammarly across your entire computer - fully on-device.</p>\n</blockquote>\n<p>As you type, Magic Tab suggests what comes next — in any app, aware of what you're working on so suggestions actually fit. Click into a text field and it'll suggest something before you've typed a single letter.</p>\n<p>If you use Grammarly, Tab can replace it entirely — privately, on your device.</p>\n<p></p>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Unlock Chat History Cap by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5906\">https://github.com/Mintplex-Labs/anything-llm/pull/5906</a>\n</li>\n<li>fix: API update-embeddings fails with Prisma \"filename is missing\" on Windows paths by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5907\">https://github.com/Mintplex-Labs/anything-llm/pull/5907</a>\n</li>\n<li>Intelligent Tool Selection (<code>ToolReranker</code>) enabled by default by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5893\">https://github.com/Mintplex-Labs/anything-llm/pull/5893</a>\n</li>\n<li>feat: add query/passage prefix env vars to GenericOpenAi embedder by @jhsmith409 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5589\">https://github.com/Mintplex-Labs/anything-llm/pull/5589</a>\n</li>\n<li>1.15.0 tags by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5909\">https://github.com/Mintplex-Labs/anything-llm/pull/5909</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@jhsmith409 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5589\">https://github.com/Mintplex-Labs/anything-llm/pull/5589</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.2...v1.15.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.2...v1.15.0</a></p>\n","assets":[{"contentType":"application/octet-stream","size":554451319,"createdAt":"2026-06-25T23:24:27Z","updatedAt":"2026-06-25T23:24:42Z","downloadCount":546,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":541454816,"createdAt":"2026-06-26T23:06:21Z","updatedAt":"2026-06-26T23:06:36Z","downloadCount":781,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":504479476,"createdAt":"2026-06-25T23:24:57Z","updatedAt":"2026-06-25T23:25:11Z","downloadCount":1229,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":575209884,"createdAt":"2026-06-25T23:23:44Z","updatedAt":"2026-06-25T23:24:01Z","downloadCount":2159,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":511074980,"createdAt":"2026-06-25T23:24:01Z","updatedAt":"2026-06-25T23:24:16Z","downloadCount":376,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":394525080,"createdAt":"2026-06-26T23:06:06Z","updatedAt":"2026-06-26T23:06:19Z","downloadCount":17494,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":11669,"createdAt":"2026-06-25T23:25:11Z","updatedAt":"2026-06-25T23:25:11Z","downloadCount":482,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.15.0/installer.sh"}]},{"id":343154199,"tag":"v1.14.2","author":"timothycarambat","name":"AnythingLLM 1.14.2","draft":false,"prerelease":false,"createdAt":"2026-06-22T20:45:11Z","publishedAt":"2026-06-22T20:59:30Z","markdown":"Just some small patches for the upcoming 1.15.0 / 2.0.0-preview initial release for desktop\r\n\r\n## What's Changed\r\n* Migrate AWS Sdk to OpenAI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5848\r\n* Groq STT by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5853\r\n* Fix edit prompt not appearing on user prompt by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5861\r\n* add missing headers to ollama embeder engine isAlive method by @TomaszZakrzewski in https://github.com/Mintplex-Labs/anything-llm/pull/5863\r\n* docs: update collector language in project structure by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5866\r\n* Fix attached file context and citations in empty workspace and agent chat by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5849\r\n* Only show mass thread delete on hover by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5871\r\n* add Brave Search provider by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5872\r\n* feat: add fastCRW web search provider by @us in https://github.com/Mintplex-Labs/anything-llm/pull/5824\r\n* fix: omit temperature for opus 4.7/4.8 in anthropic llm provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5882\r\n* 1.14.2 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5897\r\n\r\n## New Contributors\r\n* @TomaszZakrzewski made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5863\r\n* @us made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5824\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.1...v1.14.2","html":"<p>Just some small patches for the upcoming 1.15.0 / 2.0.0-preview initial release for desktop</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Migrate AWS Sdk to OpenAI by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5848\">https://github.com/Mintplex-Labs/anything-llm/pull/5848</a>\n</li>\n<li>Groq STT by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5853\">https://github.com/Mintplex-Labs/anything-llm/pull/5853</a>\n</li>\n<li>Fix edit prompt not appearing on user prompt by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5861\">https://github.com/Mintplex-Labs/anything-llm/pull/5861</a>\n</li>\n<li>add missing headers to ollama embeder engine isAlive method by @TomaszZakrzewski in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5863\">https://github.com/Mintplex-Labs/anything-llm/pull/5863</a>\n</li>\n<li>docs: update collector language in project structure by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5866\">https://github.com/Mintplex-Labs/anything-llm/pull/5866</a>\n</li>\n<li>Fix attached file context and citations in empty workspace and agent chat by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5849\">https://github.com/Mintplex-Labs/anything-llm/pull/5849</a>\n</li>\n<li>Only show mass thread delete on hover by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5871\">https://github.com/Mintplex-Labs/anything-llm/pull/5871</a>\n</li>\n<li>add Brave Search provider by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5872\">https://github.com/Mintplex-Labs/anything-llm/pull/5872</a>\n</li>\n<li>feat: add fastCRW web search provider by @us in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5824\">https://github.com/Mintplex-Labs/anything-llm/pull/5824</a>\n</li>\n<li>fix: omit temperature for opus 4.7/4.8 in anthropic llm provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5882\">https://github.com/Mintplex-Labs/anything-llm/pull/5882</a>\n</li>\n<li>1.14.2 by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5897\">https://github.com/Mintplex-Labs/anything-llm/pull/5897</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@TomaszZakrzewski made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5863\">https://github.com/Mintplex-Labs/anything-llm/pull/5863</a>\n</li>\n<li>@us made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5824\">https://github.com/Mintplex-Labs/anything-llm/pull/5824</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.1...v1.14.2\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.1...v1.14.2</a></p>\n","assets":[{"contentType":"application/octet-stream","size":543322129,"createdAt":"2026-06-22T20:46:43Z","updatedAt":"2026-06-22T20:46:57Z","downloadCount":54,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":530822448,"createdAt":"2026-06-22T20:46:57Z","updatedAt":"2026-06-22T20:47:13Z","downloadCount":100,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":490702576,"createdAt":"2026-06-22T20:47:13Z","updatedAt":"2026-06-22T20:47:26Z","downloadCount":85,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":564085323,"createdAt":"2026-06-22T20:46:00Z","updatedAt":"2026-06-22T20:46:17Z","downloadCount":131,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":500232755,"createdAt":"2026-06-22T20:46:17Z","updatedAt":"2026-06-22T20:46:32Z","downloadCount":62,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":377062032,"createdAt":"2026-06-22T20:46:32Z","updatedAt":"2026-06-22T20:46:43Z","downloadCount":751,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":11669,"createdAt":"2026-06-22T20:47:26Z","updatedAt":"2026-06-22T20:47:26Z","downloadCount":118,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/installer.sh"},{"contentType":"text/plain","size":6,"createdAt":"2026-06-22T20:47:26Z","updatedAt":"2026-06-22T20:47:26Z","downloadCount":240,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.2/version.txt"}]},{"id":340389709,"tag":"v1.14.1","author":"timothycarambat","name":"AnythingLLM v1.14.1","draft":false,"prerelease":false,"createdAt":"2026-06-16T21:09:30Z","publishedAt":"2026-06-16T21:17:40Z","markdown":"## Meeting Assistant Overhaul\r\n\r\n_Meeting Assistant is desktop app only_\r\n\r\nWe have overhauled a large portion of the Meeting Assistant to make it smaller, faster, and more efficient across all devices and platforms.\r\n\r\n- [x] Now supports Intel, AMD, and NVIDIA GPUs for a 92% smaller binary and 15% faster processing times.\r\n   - If you already have the NVIDIA GPU binary installed, you can safely delete it if you want. It will still work and is backwards compatible.\r\n\r\n- [x] Support for Developer API for transcription on audio (POST: `/v1/transcription/transcribe`)\r\n- [x] Meeting Assistant context window overflow handling is much better now - so small models can summarize longer meetings.\r\n- [x] Introduction of [Basic Speaker Identification](https://docs.anythingllm.com/meeting-assistant/features#speaker-identification) for 60% better summarizes from any audio.\r\n- [x] Dual channel stero recordings for meetings now - leading to 80% better speaker identification in \"Full Diarization\" mode.\r\n\r\n## Improvements\r\n\r\n- [x] Linux AppImage now **91%** smaller in size and caches Ollama engine downloads for faster startup times.\r\n- [x] Meeting Assistant title fix on meetings post-summary now auto-updates in UI\r\n- [x] AgentFLow variable highlight so its clear what is and is not a valid variable\r\n- [x] \"Copy chat link\" in UI to quickly re-open a chat in the desktop/self-hosted app via deeplinking.\r\n- [x] Re-enabled audio and video uploads via chat UI - uses Tinyscribe engine now.\r\n- [x] Export Chat as (PDF, JSON, Markdown, etc) from chat UI.\r\n- [x] Desktop Assistant Setting - HD screenshots now available for screenshot capture area.\r\n- [x] Request approval internal function is now available for custom skills.\r\n\r\n## Bug Fixes\r\n\r\n- [x] Removed DPAIS and HuggingFace providers from AnythingLLM (unmaintained)\r\n- [x] Fixed memory leak in embedder from it constantly reloading in server process\r\n- [x] Fixed text clearing bug when dragging and dropping files into the chat and text was already present in prompt.\r\n- [x] Massive performance improvements to the frontend UI for long running chats.\r\n- [x] Cohere SDK removed and ported to OpenAI SDK for compatibility.\r\n- [x] Desktop Assistant Capture Area not showing on windows multi-monitor setups.\r\n- [x] Strip thinking from fork thread name when forking a chat that had thoughts.\r\n- [x] Fix toast light mode always showing regardless of system theme.\r\n- [x] Mistral embedder encoding issue fixed.\r\n- [x] Better error messages for API\r\n- [x] Omit temp in Claude Bedrock for Claude 4.8\r\n- [x] Fixed event emitter leak in server process for web-scraping and summarize process\r\n\r\n----\r\n\r\n## What's Changed\r\n* fix: prevent EventEmitter memory warning in AIbitat agent framework by @simongonzalezdc in https://github.com/Mintplex-Labs/anything-llm/pull/5790\r\n* Remove unused providers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5793\r\n* Patch reloading of embedder and lanceDB connection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5804\r\n* Better API errors by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5805\r\n* Mistral Embedding Encoding by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5806\r\n* fix: omit temperature param for Bedrock Claude Opus 4.8 by @kimnamu in https://github.com/Mintplex-Labs/anything-llm/pull/5822\r\n* feat: expose requestToolApproval to custom agent skills by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5795\r\n* feat: highlight variable references in agent flow blocks by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5799\r\n* chat link in chat settings by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5837\r\n* WorkspaceChat refactor by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5833\r\n* More Frontend optimizations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5838\r\n* Migrate Cohere to OpenAI sdk by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5813\r\n* feat: export workspace chat/chat thread to pdf by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5800\r\n\r\n## New Contributors\r\n* @simongonzalezdc made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5790\r\n* @kimnamu made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5822\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.0...v1.14.1","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Meeting Assistant Overhaul</h2><a id=\"user-content-meeting-assistant-overhaul\" class=\"anchor\" aria-label=\"Permalink: Meeting Assistant Overhaul\" href=\"#meeting-assistant-overhaul\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><em>Meeting Assistant is desktop app only</em></p>\n<p>We have overhauled a large portion of the Meeting Assistant to make it smaller, faster, and more efficient across all devices and platforms.</p>\n<ul>\n<li>\n<p>[x] Now supports Intel, AMD, and NVIDIA GPUs for a 92% smaller binary and 15% faster processing times.</p>\n<ul>\n<li>If you already have the NVIDIA GPU binary installed, you can safely delete it if you want. It will still work and is backwards compatible.</li>\n</ul>\n</li>\n<li>\n<p>[x] Support for Developer API for transcription on audio (POST: <code>/v1/transcription/transcribe</code>)</p>\n</li>\n<li>\n<p>[x] Meeting Assistant context window overflow handling is much better now - so small models can summarize longer meetings.</p>\n</li>\n<li>\n<p>[x] Introduction of <a href=\"https://docs.anythingllm.com/meeting-assistant/features#speaker-identification\" rel=\"nofollow\">Basic Speaker Identification</a> for 60% better summarizes from any audio.</p>\n</li>\n<li>\n<p>[x] Dual channel stero recordings for meetings now - leading to 80% better speaker identification in \"Full Diarization\" mode.</p>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Improvements</h2><a id=\"user-content-improvements\" class=\"anchor\" aria-label=\"Permalink: Improvements\" href=\"#improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Linux AppImage now <strong>91%</strong> smaller in size and caches Ollama engine downloads for faster startup times.</li>\n<li>[x] Meeting Assistant title fix on meetings post-summary now auto-updates in UI</li>\n<li>[x] AgentFLow variable highlight so its clear what is and is not a valid variable</li>\n<li>[x] \"Copy chat link\" in UI to quickly re-open a chat in the desktop/self-hosted app via deeplinking.</li>\n<li>[x] Re-enabled audio and video uploads via chat UI - uses Tinyscribe engine now.</li>\n<li>[x] Export Chat as (PDF, JSON, Markdown, etc) from chat UI.</li>\n<li>[x] Desktop Assistant Setting - HD screenshots now available for screenshot capture area.</li>\n<li>[x] Request approval internal function is now available for custom skills.</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Bug Fixes</h2><a id=\"user-content-bug-fixes\" class=\"anchor\" aria-label=\"Permalink: Bug Fixes\" href=\"#bug-fixes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Removed DPAIS and HuggingFace providers from AnythingLLM (unmaintained)</li>\n<li>[x] Fixed memory leak in embedder from it constantly reloading in server process</li>\n<li>[x] Fixed text clearing bug when dragging and dropping files into the chat and text was already present in prompt.</li>\n<li>[x] Massive performance improvements to the frontend UI for long running chats.</li>\n<li>[x] Cohere SDK removed and ported to OpenAI SDK for compatibility.</li>\n<li>[x] Desktop Assistant Capture Area not showing on windows multi-monitor setups.</li>\n<li>[x] Strip thinking from fork thread name when forking a chat that had thoughts.</li>\n<li>[x] Fix toast light mode always showing regardless of system theme.</li>\n<li>[x] Mistral embedder encoding issue fixed.</li>\n<li>[x] Better error messages for API</li>\n<li>[x] Omit temp in Claude Bedrock for Claude 4.8</li>\n<li>[x] Fixed event emitter leak in server process for web-scraping and summarize process</li>\n</ul>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix: prevent EventEmitter memory warning in AIbitat agent framework by @simongonzalezdc in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5790\">https://github.com/Mintplex-Labs/anything-llm/pull/5790</a>\n</li>\n<li>Remove unused providers by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5793\">https://github.com/Mintplex-Labs/anything-llm/pull/5793</a>\n</li>\n<li>Patch reloading of embedder and lanceDB connection by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5804\">https://github.com/Mintplex-Labs/anything-llm/pull/5804</a>\n</li>\n<li>Better API errors by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5805\">https://github.com/Mintplex-Labs/anything-llm/pull/5805</a>\n</li>\n<li>Mistral Embedding Encoding by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5806\">https://github.com/Mintplex-Labs/anything-llm/pull/5806</a>\n</li>\n<li>fix: omit temperature param for Bedrock Claude Opus 4.8 by @kimnamu in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5822\">https://github.com/Mintplex-Labs/anything-llm/pull/5822</a>\n</li>\n<li>feat: expose requestToolApproval to custom agent skills by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5795\">https://github.com/Mintplex-Labs/anything-llm/pull/5795</a>\n</li>\n<li>feat: highlight variable references in agent flow blocks by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5799\">https://github.com/Mintplex-Labs/anything-llm/pull/5799</a>\n</li>\n<li>chat link in chat settings by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5837\">https://github.com/Mintplex-Labs/anything-llm/pull/5837</a>\n</li>\n<li>WorkspaceChat refactor by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5833\">https://github.com/Mintplex-Labs/anything-llm/pull/5833</a>\n</li>\n<li>More Frontend optimizations by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5838\">https://github.com/Mintplex-Labs/anything-llm/pull/5838</a>\n</li>\n<li>Migrate Cohere to OpenAI sdk by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5813\">https://github.com/Mintplex-Labs/anything-llm/pull/5813</a>\n</li>\n<li>feat: export workspace chat/chat thread to pdf by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5800\">https://github.com/Mintplex-Labs/anything-llm/pull/5800</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@simongonzalezdc made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5790\">https://github.com/Mintplex-Labs/anything-llm/pull/5790</a>\n</li>\n<li>@kimnamu made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5822\">https://github.com/Mintplex-Labs/anything-llm/pull/5822</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.0...v1.14.1\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.14.0...v1.14.1</a></p>\n","assets":[{"contentType":"application/octet-stream","size":544065136,"createdAt":"2026-06-16T20:15:03Z","updatedAt":"2026-06-16T20:15:20Z","downloadCount":229,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.1/AnythingLLMDesktop-Arm64.AppImage"},{"contentType":"application/x-msdownload","size":530734144,"createdAt":"2026-06-16T20:15:20Z","updatedAt":"2026-06-16T20:15:36Z","downloadCount":213,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.1/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/octet-stream","size":494924122,"createdAt":"2026-06-16T20:15:36Z","updatedAt":"2026-06-16T20:15:51Z","downloadCount":231,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.1/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":564827257,"createdAt":"2026-06-16T20:15:51Z","updatedAt":"2026-06-16T20:16:07Z","downloadCount":446,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.1/AnythingLLMDesktop.AppImage"},{"contentType":"application/octet-stream","size":501079159,"createdAt":"2026-06-16T20:16:07Z","updatedAt":"2026-06-16T20:16:39Z","downloadCount":106,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.1/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":387908696,"createdAt":"2026-06-16T20:16:39Z","updatedAt":"2026-06-16T20:16:57Z","downloadCount":1907,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.1/AnythingLLMDesktop.exe"}]},{"id":336352928,"tag":"v1.14.0","author":"timothycarambat","name":"AnythingLLM v1.14.0","draft":false,"prerelease":false,"createdAt":"2026-06-09T13:45:56Z","publishedAt":"2026-06-09T13:46:36Z","markdown":"## Improvements\r\n\r\n- [x] Cerebres provider\r\n- [x] The default chat thread is now killed when you create a new thread. If you have chats on the default thread, it will be available still. New workspaces or workspaces with no chats on default will no longer show it.\r\n- [x] All model providers are now *opt-out* of tool calling by default. Everything will call tools by default unless you opt-out offering better performance for agents everywhere\r\n- [x] STT Support for Deepgram, GenericOAI, Lemonade, & OpenAI\r\n- [x] TTS Support for KokoroTTS\r\n- [x] Web-scraping now will convert to markdown for better parsing and chat followup tasks with minimal context bloat\r\n- [x] Summary tool was overhauled. Now it will so better summaries with transparency as well as ask before continuing for longer summaries\r\n- [x] Improvements to the GenericOAI provider\r\n- [x] 24hour system variable formats\r\n- [x] Better LaTex rendering support\r\n\r\n## Bug Fixes\r\n\r\n- [x] Context limit detection issue for agents: https://github.com/Mintplex-Labs/anything-llm/pull/5716\r\n- [x] SEARXNG double encoding: https://github.com/Mintplex-Labs/anything-llm/pull/5723\r\n- [x] Timeouts for all fetch requests https://github.com/Mintplex-Labs/anything-llm/pull/5721\r\n- [x] Escape illegal XML in word docs, etc https://github.com/Mintplex-Labs/anything-llm/pull/5760\r\n- [x] (Windows) On unisntall, checkbox to remove **all** AnythingLLM data is now present\r\n- [x] Tray Fixes when app starts in background or Desktop Assistant feature is toggled.\r\n\r\n## What's Changed\r\n* docs: list all cloud embedding providers by @narutamaaurum in https://github.com/Mintplex-Labs/anything-llm/pull/5701\r\n* feat: add Cerebras as an LLM provider by @officialasishkumar in https://github.com/Mintplex-Labs/anything-llm/pull/5699\r\n* fix provider override in agents by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5716\r\n* docs: fix self-hosted terms wording by @Zhao73 in https://github.com/Mintplex-Labs/anything-llm/pull/5737\r\n* fix: avoid double-encoding SearXNG search queries by @trick77 in https://github.com/Mintplex-Labs/anything-llm/pull/5723\r\n* Kill `default` thread by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5739\r\n* feat: add server-side speech-to-text with OpenAI provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5596\r\n* Kokoro TTS provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5679\r\n* add windows paths to isWithin by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5685\r\n* apply universal sdk timeout by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5721\r\n* fix: support Azure & Dell Pro AI Studio providers in agent summarization fallback by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5738\r\n* Turn HTML scraped sites to Markdown for better research by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5742\r\n* Improve agent summarizer tool by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5719\r\n* Generic OpenAI improvements by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5746\r\n* feat: make document sync stale-after interval configurable by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5747\r\n* fix: strip XML-illegal control characters from generated documents by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5760\r\n* feat(embed): opt-in deny-by-default for embeds with no allowlist by @dmitrymaranik in https://github.com/Mintplex-Labs/anything-llm/pull/5759\r\n* add 24 hours date and time formats to SystemVariables by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5778\r\n* Make native tool calling opt-out instead of opt-in by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5783\r\n* better LaTex support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5779\r\n\r\n## New Contributors\r\n* @narutamaaurum made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5701\r\n* @Zhao73 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5737\r\n* @trick77 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5723\r\n* @sanidhyasin made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5738\r\n* @dmitrymaranik made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5759\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.13.0...v1.14.0","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Improvements</h2><a id=\"user-content-improvements\" class=\"anchor\" aria-label=\"Permalink: Improvements\" href=\"#improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Cerebres provider</li>\n<li>[x] The default chat thread is now killed when you create a new thread. If you have chats on the default thread, it will be available still. New workspaces or workspaces with no chats on default will no longer show it.</li>\n<li>[x] All model providers are now <em>opt-out</em> of tool calling by default. Everything will call tools by default unless you opt-out offering better performance for agents everywhere</li>\n<li>[x] STT Support for Deepgram, GenericOAI, Lemonade, &amp; OpenAI</li>\n<li>[x] TTS Support for KokoroTTS</li>\n<li>[x] Web-scraping now will convert to markdown for better parsing and chat followup tasks with minimal context bloat</li>\n<li>[x] Summary tool was overhauled. Now it will so better summaries with transparency as well as ask before continuing for longer summaries</li>\n<li>[x] Improvements to the GenericOAI provider</li>\n<li>[x] 24hour system variable formats</li>\n<li>[x] Better LaTex rendering support</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Bug Fixes</h2><a id=\"user-content-bug-fixes\" class=\"anchor\" aria-label=\"Permalink: Bug Fixes\" href=\"#bug-fixes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Context limit detection issue for agents: <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5716\">https://github.com/Mintplex-Labs/anything-llm/pull/5716</a>\n</li>\n<li>[x] SEARXNG double encoding: <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5723\">https://github.com/Mintplex-Labs/anything-llm/pull/5723</a>\n</li>\n<li>[x] Timeouts for all fetch requests <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5721\">https://github.com/Mintplex-Labs/anything-llm/pull/5721</a>\n</li>\n<li>[x] Escape illegal XML in word docs, etc <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5760\">https://github.com/Mintplex-Labs/anything-llm/pull/5760</a>\n</li>\n<li>[x] (Windows) On unisntall, checkbox to remove <strong>all</strong> AnythingLLM data is now present</li>\n<li>[x] Tray Fixes when app starts in background or Desktop Assistant feature is toggled.</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>docs: list all cloud embedding providers by @narutamaaurum in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5701\">https://github.com/Mintplex-Labs/anything-llm/pull/5701</a>\n</li>\n<li>feat: add Cerebras as an LLM provider by @officialasishkumar in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5699\">https://github.com/Mintplex-Labs/anything-llm/pull/5699</a>\n</li>\n<li>fix provider override in agents by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5716\">https://github.com/Mintplex-Labs/anything-llm/pull/5716</a>\n</li>\n<li>docs: fix self-hosted terms wording by @Zhao73 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5737\">https://github.com/Mintplex-Labs/anything-llm/pull/5737</a>\n</li>\n<li>fix: avoid double-encoding SearXNG search queries by @trick77 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5723\">https://github.com/Mintplex-Labs/anything-llm/pull/5723</a>\n</li>\n<li>Kill <code>default</code> thread by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5739\">https://github.com/Mintplex-Labs/anything-llm/pull/5739</a>\n</li>\n<li>feat: add server-side speech-to-text with OpenAI provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5596\">https://github.com/Mintplex-Labs/anything-llm/pull/5596</a>\n</li>\n<li>Kokoro TTS provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5679\">https://github.com/Mintplex-Labs/anything-llm/pull/5679</a>\n</li>\n<li>add windows paths to isWithin by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5685\">https://github.com/Mintplex-Labs/anything-llm/pull/5685</a>\n</li>\n<li>apply universal sdk timeout by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5721\">https://github.com/Mintplex-Labs/anything-llm/pull/5721</a>\n</li>\n<li>fix: support Azure &amp; Dell Pro AI Studio providers in agent summarization fallback by @sanidhyasin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5738\">https://github.com/Mintplex-Labs/anything-llm/pull/5738</a>\n</li>\n<li>Turn HTML scraped sites to Markdown for better research by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5742\">https://github.com/Mintplex-Labs/anything-llm/pull/5742</a>\n</li>\n<li>Improve agent summarizer tool by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5719\">https://github.com/Mintplex-Labs/anything-llm/pull/5719</a>\n</li>\n<li>Generic OpenAI improvements by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5746\">https://github.com/Mintplex-Labs/anything-llm/pull/5746</a>\n</li>\n<li>feat: make document sync stale-after interval configurable by @sanidhyasin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5747\">https://github.com/Mintplex-Labs/anything-llm/pull/5747</a>\n</li>\n<li>fix: strip XML-illegal control characters from generated documents by @sanidhyasin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5760\">https://github.com/Mintplex-Labs/anything-llm/pull/5760</a>\n</li>\n<li>feat(embed): opt-in deny-by-default for embeds with no allowlist by @dmitrymaranik in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5759\">https://github.com/Mintplex-Labs/anything-llm/pull/5759</a>\n</li>\n<li>add 24 hours date and time formats to SystemVariables by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5778\">https://github.com/Mintplex-Labs/anything-llm/pull/5778</a>\n</li>\n<li>Make native tool calling opt-out instead of opt-in by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5783\">https://github.com/Mintplex-Labs/anything-llm/pull/5783</a>\n</li>\n<li>better LaTex support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5779\">https://github.com/Mintplex-Labs/anything-llm/pull/5779</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@narutamaaurum made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5701\">https://github.com/Mintplex-Labs/anything-llm/pull/5701</a>\n</li>\n<li>@Zhao73 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5737\">https://github.com/Mintplex-Labs/anything-llm/pull/5737</a>\n</li>\n<li>@trick77 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5723\">https://github.com/Mintplex-Labs/anything-llm/pull/5723</a>\n</li>\n<li>@sanidhyasin made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5738\">https://github.com/Mintplex-Labs/anything-llm/pull/5738</a>\n</li>\n<li>@dmitrymaranik made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5759\">https://github.com/Mintplex-Labs/anything-llm/pull/5759</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.13.0...v1.14.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.13.0...v1.14.0</a></p>\n","assets":[{"contentType":"application/x-msdownload","size":392265904,"createdAt":"2026-06-15T03:28:16Z","updatedAt":"2026-06-15T03:28:37Z","downloadCount":497,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.14.0/AnythingLLMDesktop.exe"}]},{"id":328428142,"tag":"v1.13.0","author":"timothycarambat","name":"AnythingLLM v1.13.0 - A Hybrid AI Experience","draft":false,"prerelease":false,"createdAt":"2026-05-26T19:04:13Z","publishedAt":"2026-05-26T19:08:06Z","markdown":"This release is focused on improving the agent experience and adding new features to the agent system as well as moving towards a more passive, personal, and **hybrid** AI experience.\r\n\r\n## Model Router: The First Consumer Hybrid AI Experience\r\n\r\nThe Model Router feature is the first-ever user-defined intelligent routing system that seamlessly blends local and cloud AI into a single, unified experience that is entirely under your control. Until now, you had to choose: run everything locally, or send everything to the cloud. That tradeoff is over.\r\n\r\nWith Model Router, you define the rules. Every message you send is automatically analyzed and routed to the perfect model for that specific task, whether that's a lightweight local model for quick questions, a reasoning model for complex math, or your most powerful cloud model for nuanced legal analysis. All from the same chat. All invisible to the user. All defined by you.\r\n\r\n**What makes this so exciting:**\r\n\r\n- **Hybrid AI.** Mix and match local models (Ollama, LM Studio, etc.) with cloud providers (OpenAI, Anthropic, Google) in a single conversation. No manual switching!\r\n- **You're in complete control.** Create [calculated rules](https://docs.anythingllm.com/model-router/setup#calculated-rules) that trigger on keywords, token counts, time of day, or image attachments **instantaneously**. Or use [LLM-classified rules](https://docs.anythingllm.com/model-router/setup#llm-classified-rules) that understand intent in plain English.\r\n- **Save money without sacrificing quality.** Route simple queries to cheap or local models. Reserve expensive API calls for the messages that actually need them.\r\n- **Intelligent caching.** Our advanced sticky routing system keeps you on the same model during a conversation thread, so you're not bouncing between models on every message.\r\n\r\nThis is, we believe, a fundamental shift in how AI assistants work. For the first time, you get the privacy of local models, the power of cloud models, and the intelligence to know when to use each. And it's 100% open source.\r\n\r\n[Learn how to set up your first router →](https://docs.anythingllm.com/model-router/setup)\r\n\r\n<img width=\"1920\" height=\"1080\" alt=\"chat-routed\" src=\"https://github.com/user-attachments/assets/2c7fe638-e071-436c-b2be-a00fe9a6498d\" />\r\n\r\n\r\n## Scheduled Jobs: Your AI That Works While You Don't\r\n\r\nWhat if your AI assistant could work for you in the background, automatically, on a schedule you define, without you lifting a finger?\r\n\r\n**Scheduled Jobs** turns AnythingLLM into an always-on AI workforce. Create recurring tasks that run themselves: morning briefings, weekly reports, data monitoring, research digests. Anything you'd normally ask an agent to do, but automated and hands-free. Has job specific skills you can set so the model is not overwhelmed with tools and outcomes are repeatable.\r\n\r\n**Why this changes everything:**\r\n\r\n- **Set it and forget it.** Define a prompt, pick your tools, choose a schedule, and walk away. Your agent runs exactly when you need it: every morning at 8 AM, every Monday at noon, every hour on the hour.\r\n- **No technical knowledge required.** Our visual Cron Builder lets you schedule jobs with simple dropdowns. No cryptic cron syntax, no command line, no code. Just point and click.\r\n- **Full agent power, fully automated.** Scheduled jobs have access to the same tools as your regular chats: web search, document analysis, custom skills, MCP integrations, and more. If an agent can do it in a conversation, it can do it on a schedule.\r\n- **Complete run history.** Every execution is logged with the agent's full reasoning, tool calls, generated files, and final response. Review past runs anytime, or continue where the agent left off in a new thread.\r\n- **Push notifications.** Get alerted the moment a job finishes, even when AnythingLLM is in the background. Click to jump straight to results.\r\n\r\nEnterprise tools charge thousands for this kind of automation. Cloud-only platforms require you to trust your data to third parties. AnythingLLM gives you scheduled AI agents that run entirely on your machine, with your data, under your control.\r\n\r\nWake up to a summary of overnight emails. Get weekly progress reports written automatically. Monitor websites for changes. The possibilities are endless, and it all happens while you focus on what matters.\r\n\r\n[Learn how to create your first scheduled job →](https://docs.anythingllm.com/scheduled-jobs/getting-started)\r\n \r\n<img width=\"3489\" height=\"2019\" alt=\"scheduled-job\" src=\"https://github.com/user-attachments/assets/82b9b2e8-cb5c-4f87-92d4-962ec96c0f1e\" />\r\n\r\n## Automatic Memories & Personalization\r\n\r\nAnythingLLM now supports automatic memory extraction and personalization so your AI assistant can remember what you've talked about and use that knowledge to personalize its responses.\r\n\r\nAnythingLLM runs a background job to extract memories from your chats and store them in a memory bank. This memory bank is then used to personalize the responses of your AI assistant - you have full control over what is remembered and how it is used\r\nyou can even add memories manually to the memory bank if you dont want to have the model spend cycles reviewing chat history.\r\n\r\nThere are two types of memories:\r\n- Workspace memories: These are memories that are specific to the current workspace (like what you are working on, projects-specific information, etc.)\r\n- Global memories: These are memories that are specific to the entire AnythingLLM instance (like your name, preferences, etc.)\r\n\r\nMemories are injected into the system prompt of your AI assistant so it can use them to personalize its responses and are a welcome addition to your AI assistant's knowledge base.\r\n\r\n[Learn how to enable and manage memories →](https://docs.anythingllm.com/features/memories)\r\n\r\n<img width=\"1814\" height=\"886\" alt=\"memories-sidebar\" src=\"https://github.com/user-attachments/assets/293dd888-8816-4359-8819-cb02bff4189f\" />\r\n\r\n\r\n## Agent Surveys (special tool)\r\n\r\nAgent Surveys is a special tool that allows your AI assistant to ask clarifying questions before proceeding. This is useful when you are working with a complex task and the agent needs more information to proceed.\r\n\r\nThis is off by default and must be enabled in the agent settings. Answers to the questions are saved alongside the chat message so the agent can use them in future turns.\r\n\r\n[Learn how to enable and manage agent surveys →](https://docs.anythingllm.com/features/agent-surveys)\r\n\r\n<img width=\"3442\" height=\"1790\" alt=\"multi-choice\" src=\"https://github.com/user-attachments/assets/d66462ec-a583-4d15-8861-8a657239ac34\" />\r\n\r\n----\r\n## What's Changed\r\n* Show agent skills, flows, and MCP tools in chat tools menu by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5444\r\n* [FEAT] Add native Baidu Search provider for Agent web browsing by @jimmyzhuu in https://github.com/Mintplex-Labs/anything-llm/pull/5388\r\n* fix(embedder): surface Mistral embedding failures by @haimingZZ in https://github.com/Mintplex-Labs/anything-llm/pull/5513\r\n* fix: invalid docs links in FileSystemSkillPanel by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5518\r\n* Claude Feedback by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5524\r\n* Fix deepseek v4 reasoning inject thoughts by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5527\r\n* fix(agent): check auto-approved skills env correctly by @haimingZZ in https://github.com/Mintplex-Labs/anything-llm/pull/5511\r\n* Fix double /reset in agent mode by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5516\r\n* fix: support OpenShift arbitrary UID/GID-0 in Docker image by @petre in https://github.com/Mintplex-Labs/anything-llm/pull/5136\r\n* Normalize lemonade embedder error handling by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5547\r\n* feat: Scheduled Jobs by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5322\r\n* Rename auto mode to agent mode by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5551\r\n* Auto-rename thread in agent mode by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5550\r\n* update scheduled job continue CTA by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5558\r\n* fix(tts): strip Markdown syntax before sending text to TTS engines by @GopalGB in https://github.com/Mintplex-Labs/anything-llm/pull/5560\r\n* Fix Community Hub import page responsiveness on narrow widths by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5544\r\n* fix: SPA nav for thread/workspace switching by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5528\r\n* fix: tools popover overflowing screen on small viewports by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5549\r\n* fix: scope thread options hover state by @officialasishkumar in https://github.com/Mintplex-Labs/anything-llm/pull/5606\r\n* feat: allow configurable collector port by @officialasishkumar in https://github.com/Mintplex-Labs/anything-llm/pull/5607\r\n* fix: add font fallback for form controls by @markov12 in https://github.com/Mintplex-Labs/anything-llm/pull/5618\r\n* fix: auto-speak not playing in agent mode by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5595\r\n* feat: adding MiniMax LLM provider by @dandandandaann in https://github.com/Mintplex-Labs/anything-llm/pull/5450\r\n* fix: prevent gemini agent 400s from parallel tool calls by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5630\r\n* Support reasoning content in v2 stream handler by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5654\r\n* Update DeviceTokens to already-admin user on MUM migration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5655\r\n* Support pulling generated documents from API calls by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5658\r\n* Embed logos in docker prod build by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5660\r\n* feat: Memories/Personalization by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5269\r\n* Workspace deletion protection by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5662\r\n* Model router by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5324\r\n* Agent Skill: User Survey by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5577\r\n* Migrate slash commands to admin user on multi-user-mode by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5684\r\n* router-models: accurate token/message counting for model router decisions by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5680\r\n* refactor Prompt to not block main chat content by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5691\r\n\r\n## New Contributors\r\n* @jimmyzhuu made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5388\r\n* @haimingZZ made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5513\r\n* @petre made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5136\r\n* @GopalGB made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5560\r\n* @markov12 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5618\r\n* @dandandandaann made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5450\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.1...v1.13.0","html":"<p>This release is focused on improving the agent experience and adding new features to the agent system as well as moving towards a more passive, personal, and <strong>hybrid</strong> AI experience.</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Model Router: The First Consumer Hybrid AI Experience</h2><a id=\"user-content-model-router-the-first-consumer-hybrid-ai-experience\" class=\"anchor\" aria-label=\"Permalink: Model Router: The First Consumer Hybrid AI Experience\" href=\"#model-router-the-first-consumer-hybrid-ai-experience\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>The Model Router feature is the first-ever user-defined intelligent routing system that seamlessly blends local and cloud AI into a single, unified experience that is entirely under your control. Until now, you had to choose: run everything locally, or send everything to the cloud. That tradeoff is over.</p>\n<p>With Model Router, you define the rules. Every message you send is automatically analyzed and routed to the perfect model for that specific task, whether that's a lightweight local model for quick questions, a reasoning model for complex math, or your most powerful cloud model for nuanced legal analysis. All from the same chat. All invisible to the user. All defined by you.</p>\n<p><strong>What makes this so exciting:</strong></p>\n<ul>\n<li>\n<strong>Hybrid AI.</strong> Mix and match local models (Ollama, LM Studio, etc.) with cloud providers (OpenAI, Anthropic, Google) in a single conversation. No manual switching!</li>\n<li>\n<strong>You're in complete control.</strong> Create <a href=\"https://docs.anythingllm.com/model-router/setup#calculated-rules\" rel=\"nofollow\">calculated rules</a> that trigger on keywords, token counts, time of day, or image attachments <strong>instantaneously</strong>. Or use <a href=\"https://docs.anythingllm.com/model-router/setup#llm-classified-rules\" rel=\"nofollow\">LLM-classified rules</a> that understand intent in plain English.</li>\n<li>\n<strong>Save money without sacrificing quality.</strong> Route simple queries to cheap or local models. Reserve expensive API calls for the messages that actually need them.</li>\n<li>\n<strong>Intelligent caching.</strong> Our advanced sticky routing system keeps you on the same model during a conversation thread, so you're not bouncing between models on every message.</li>\n</ul>\n<p>This is, we believe, a fundamental shift in how AI assistants work. For the first time, you get the privacy of local models, the power of cloud models, and the intelligence to know when to use each. And it's 100% open source.</p>\n<p><a href=\"https://docs.anythingllm.com/model-router/setup\" rel=\"nofollow\">Learn how to set up your first router →</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/2c7fe638-e071-436c-b2be-a00fe9a6498d\"><img width=\"1920\" height=\"1080\" alt=\"chat-routed\" src=\"https://github.com/user-attachments/assets/2c7fe638-e071-436c-b2be-a00fe9a6498d\" style=\"max-width: 100%; height: auto; max-height: 1080px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Scheduled Jobs: Your AI That Works While You Don't</h2><a id=\"user-content-scheduled-jobs-your-ai-that-works-while-you-dont\" class=\"anchor\" aria-label=\"Permalink: Scheduled Jobs: Your AI That Works While You Don't\" href=\"#scheduled-jobs-your-ai-that-works-while-you-dont\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>What if your AI assistant could work for you in the background, automatically, on a schedule you define, without you lifting a finger?</p>\n<p><strong>Scheduled Jobs</strong> turns AnythingLLM into an always-on AI workforce. Create recurring tasks that run themselves: morning briefings, weekly reports, data monitoring, research digests. Anything you'd normally ask an agent to do, but automated and hands-free. Has job specific skills you can set so the model is not overwhelmed with tools and outcomes are repeatable.</p>\n<p><strong>Why this changes everything:</strong></p>\n<ul>\n<li>\n<strong>Set it and forget it.</strong> Define a prompt, pick your tools, choose a schedule, and walk away. Your agent runs exactly when you need it: every morning at 8 AM, every Monday at noon, every hour on the hour.</li>\n<li>\n<strong>No technical knowledge required.</strong> Our visual Cron Builder lets you schedule jobs with simple dropdowns. No cryptic cron syntax, no command line, no code. Just point and click.</li>\n<li>\n<strong>Full agent power, fully automated.</strong> Scheduled jobs have access to the same tools as your regular chats: web search, document analysis, custom skills, MCP integrations, and more. If an agent can do it in a conversation, it can do it on a schedule.</li>\n<li>\n<strong>Complete run history.</strong> Every execution is logged with the agent's full reasoning, tool calls, generated files, and final response. Review past runs anytime, or continue where the agent left off in a new thread.</li>\n<li>\n<strong>Push notifications.</strong> Get alerted the moment a job finishes, even when AnythingLLM is in the background. Click to jump straight to results.</li>\n</ul>\n<p>Enterprise tools charge thousands for this kind of automation. Cloud-only platforms require you to trust your data to third parties. AnythingLLM gives you scheduled AI agents that run entirely on your machine, with your data, under your control.</p>\n<p>Wake up to a summary of overnight emails. Get weekly progress reports written automatically. Monitor websites for changes. The possibilities are endless, and it all happens while you focus on what matters.</p>\n<p><a href=\"https://docs.anythingllm.com/scheduled-jobs/getting-started\" rel=\"nofollow\">Learn how to create your first scheduled job →</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/82b9b2e8-cb5c-4f87-92d4-962ec96c0f1e\"><img width=\"2000\" height=\"1157\" alt=\"scheduled-job\" src=\"https://github.com/user-attachments/assets/82b9b2e8-cb5c-4f87-92d4-962ec96c0f1e\" style=\"max-width: 100%; height: auto; max-height: 1157px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Automatic Memories &amp; Personalization</h2><a id=\"user-content-automatic-memories--personalization\" class=\"anchor\" aria-label=\"Permalink: Automatic Memories &amp; Personalization\" href=\"#automatic-memories--personalization\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>AnythingLLM now supports automatic memory extraction and personalization so your AI assistant can remember what you've talked about and use that knowledge to personalize its responses.</p>\n<p>AnythingLLM runs a background job to extract memories from your chats and store them in a memory bank. This memory bank is then used to personalize the responses of your AI assistant - you have full control over what is remembered and how it is used\nyou can even add memories manually to the memory bank if you dont want to have the model spend cycles reviewing chat history.</p>\n<p>There are two types of memories:</p>\n<ul>\n<li>Workspace memories: These are memories that are specific to the current workspace (like what you are working on, projects-specific information, etc.)</li>\n<li>Global memories: These are memories that are specific to the entire AnythingLLM instance (like your name, preferences, etc.)</li>\n</ul>\n<p>Memories are injected into the system prompt of your AI assistant so it can use them to personalize its responses and are a welcome addition to your AI assistant's knowledge base.</p>\n<p><a href=\"https://docs.anythingllm.com/features/memories\" rel=\"nofollow\">Learn how to enable and manage memories →</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/293dd888-8816-4359-8819-cb02bff4189f\"><img width=\"1814\" height=\"886\" alt=\"memories-sidebar\" src=\"https://github.com/user-attachments/assets/293dd888-8816-4359-8819-cb02bff4189f\" style=\"max-width: 100%; height: auto; max-height: 886px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Agent Surveys (special tool)</h2><a id=\"user-content-agent-surveys-special-tool\" class=\"anchor\" aria-label=\"Permalink: Agent Surveys (special tool)\" href=\"#agent-surveys-special-tool\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Agent Surveys is a special tool that allows your AI assistant to ask clarifying questions before proceeding. This is useful when you are working with a complex task and the agent needs more information to proceed.</p>\n<p>This is off by default and must be enabled in the agent settings. Answers to the questions are saved alongside the chat message so the agent can use them in future turns.</p>\n<p><a href=\"https://docs.anythingllm.com/features/agent-surveys\" rel=\"nofollow\">Learn how to enable and manage agent surveys →</a></p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/d66462ec-a583-4d15-8861-8a657239ac34\"><img width=\"2000\" height=\"1040\" alt=\"multi-choice\" src=\"https://github.com/user-attachments/assets/d66462ec-a583-4d15-8861-8a657239ac34\" style=\"max-width: 100%; height: auto; max-height: 1040px;\"></a></p>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Show agent skills, flows, and MCP tools in chat tools menu by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5444\">https://github.com/Mintplex-Labs/anything-llm/pull/5444</a>\n</li>\n<li>[FEAT] Add native Baidu Search provider for Agent web browsing by @jimmyzhuu in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5388\">https://github.com/Mintplex-Labs/anything-llm/pull/5388</a>\n</li>\n<li>fix(embedder): surface Mistral embedding failures by @haimingZZ in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5513\">https://github.com/Mintplex-Labs/anything-llm/pull/5513</a>\n</li>\n<li>fix: invalid docs links in FileSystemSkillPanel by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5518\">https://github.com/Mintplex-Labs/anything-llm/pull/5518</a>\n</li>\n<li>Claude Feedback by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5524\">https://github.com/Mintplex-Labs/anything-llm/pull/5524</a>\n</li>\n<li>Fix deepseek v4 reasoning inject thoughts by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5527\">https://github.com/Mintplex-Labs/anything-llm/pull/5527</a>\n</li>\n<li>fix(agent): check auto-approved skills env correctly by @haimingZZ in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5511\">https://github.com/Mintplex-Labs/anything-llm/pull/5511</a>\n</li>\n<li>Fix double /reset in agent mode by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5516\">https://github.com/Mintplex-Labs/anything-llm/pull/5516</a>\n</li>\n<li>fix: support OpenShift arbitrary UID/GID-0 in Docker image by @petre in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5136\">https://github.com/Mintplex-Labs/anything-llm/pull/5136</a>\n</li>\n<li>Normalize lemonade embedder error handling by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5547\">https://github.com/Mintplex-Labs/anything-llm/pull/5547</a>\n</li>\n<li>feat: Scheduled Jobs by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5322\">https://github.com/Mintplex-Labs/anything-llm/pull/5322</a>\n</li>\n<li>Rename auto mode to agent mode by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5551\">https://github.com/Mintplex-Labs/anything-llm/pull/5551</a>\n</li>\n<li>Auto-rename thread in agent mode by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5550\">https://github.com/Mintplex-Labs/anything-llm/pull/5550</a>\n</li>\n<li>update scheduled job continue CTA by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5558\">https://github.com/Mintplex-Labs/anything-llm/pull/5558</a>\n</li>\n<li>fix(tts): strip Markdown syntax before sending text to TTS engines by @GopalGB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5560\">https://github.com/Mintplex-Labs/anything-llm/pull/5560</a>\n</li>\n<li>Fix Community Hub import page responsiveness on narrow widths by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5544\">https://github.com/Mintplex-Labs/anything-llm/pull/5544</a>\n</li>\n<li>fix: SPA nav for thread/workspace switching by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5528\">https://github.com/Mintplex-Labs/anything-llm/pull/5528</a>\n</li>\n<li>fix: tools popover overflowing screen on small viewports by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5549\">https://github.com/Mintplex-Labs/anything-llm/pull/5549</a>\n</li>\n<li>fix: scope thread options hover state by @officialasishkumar in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5606\">https://github.com/Mintplex-Labs/anything-llm/pull/5606</a>\n</li>\n<li>feat: allow configurable collector port by @officialasishkumar in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5607\">https://github.com/Mintplex-Labs/anything-llm/pull/5607</a>\n</li>\n<li>fix: add font fallback for form controls by @markov12 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5618\">https://github.com/Mintplex-Labs/anything-llm/pull/5618</a>\n</li>\n<li>fix: auto-speak not playing in agent mode by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5595\">https://github.com/Mintplex-Labs/anything-llm/pull/5595</a>\n</li>\n<li>feat: adding MiniMax LLM provider by @dandandandaann in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5450\">https://github.com/Mintplex-Labs/anything-llm/pull/5450</a>\n</li>\n<li>fix: prevent gemini agent 400s from parallel tool calls by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5630\">https://github.com/Mintplex-Labs/anything-llm/pull/5630</a>\n</li>\n<li>Support reasoning content in v2 stream handler by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5654\">https://github.com/Mintplex-Labs/anything-llm/pull/5654</a>\n</li>\n<li>Update DeviceTokens to already-admin user on MUM migration by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5655\">https://github.com/Mintplex-Labs/anything-llm/pull/5655</a>\n</li>\n<li>Support pulling generated documents from API calls by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5658\">https://github.com/Mintplex-Labs/anything-llm/pull/5658</a>\n</li>\n<li>Embed logos in docker prod build by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5660\">https://github.com/Mintplex-Labs/anything-llm/pull/5660</a>\n</li>\n<li>feat: Memories/Personalization by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5269\">https://github.com/Mintplex-Labs/anything-llm/pull/5269</a>\n</li>\n<li>Workspace deletion protection by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5662\">https://github.com/Mintplex-Labs/anything-llm/pull/5662</a>\n</li>\n<li>Model router by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5324\">https://github.com/Mintplex-Labs/anything-llm/pull/5324</a>\n</li>\n<li>Agent Skill: User Survey by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5577\">https://github.com/Mintplex-Labs/anything-llm/pull/5577</a>\n</li>\n<li>Migrate slash commands to admin user on multi-user-mode by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5684\">https://github.com/Mintplex-Labs/anything-llm/pull/5684</a>\n</li>\n<li>router-models: accurate token/message counting for model router decisions by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5680\">https://github.com/Mintplex-Labs/anything-llm/pull/5680</a>\n</li>\n<li>refactor Prompt to not block main chat content by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5691\">https://github.com/Mintplex-Labs/anything-llm/pull/5691</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@jimmyzhuu made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5388\">https://github.com/Mintplex-Labs/anything-llm/pull/5388</a>\n</li>\n<li>@haimingZZ made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5513\">https://github.com/Mintplex-Labs/anything-llm/pull/5513</a>\n</li>\n<li>@petre made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5136\">https://github.com/Mintplex-Labs/anything-llm/pull/5136</a>\n</li>\n<li>@GopalGB made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5560\">https://github.com/Mintplex-Labs/anything-llm/pull/5560</a>\n</li>\n<li>@markov12 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5618\">https://github.com/Mintplex-Labs/anything-llm/pull/5618</a>\n</li>\n<li>@dandandandaann made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5450\">https://github.com/Mintplex-Labs/anything-llm/pull/5450</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.1...v1.13.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.1...v1.13.0</a></p>\n","assets":[]},{"id":312470230,"tag":"v1.12.1","author":"timothycarambat","name":"AnythingLLM v1.12.1","draft":false,"prerelease":false,"createdAt":"2026-04-22T22:15:59Z","publishedAt":"2026-04-22T22:41:12Z","markdown":"\r\n## Notable Improvements\r\n\r\n### Streamed Document Embedding\r\n\r\nNow, when you upload a document to the workspace the process per-document is now reported during embedding. This is a huge improvement in performance and user experience. During this process you can add and remove documents to the queue as well as even close and navigate away from the page without losing your progress.\r\n\r\n\r\n<img width=\"1745\" height=\"1011\" alt=\"queue-embedding\" src=\"https://github.com/user-attachments/assets/ffbd06ad-cd2c-480a-89ba-bb7a0068abbc\" />\r\n\r\n\r\n### App integrations\r\n\r\nThere are now built in integrations for the following apps with minimal to zero setup required for Agent skills:\r\n- [Gmail](https://docs.anythingllm.com/agent/usage/gmail-agent)\r\n- [Outlook](https://docs.anythingllm.com/agent/usage/outlook-agent)\r\n- [Google Calendar](https://docs.anythingllm.com/agent/usage/google-calendar-agent)\r\n\r\n## Other Improvements\r\n\r\n- [x] Image Lightbox in main UI\r\n- [x] Enabled Korean, Chinese, & Japanese character support for PDF generation via custom mdpdf fork\r\n- [x] Better citations for app integrations\r\n- [x] DDG default web-search in agent skills\r\n- [x] Open documents in native application on machine when generated by Document Generation Agent\r\n- [x] Auto approve agent skill via ENV setting\r\n- [x] Ollama bumped to 0.20.7 (Qwen3.5 support, Gemma 4, etc)\r\n- [x] New Customization > Chat setting for `Unload model when closed` to unload the model when the user closes the chat window.\r\n- [x] Generic OpenAI Capability detection/ENV setting\r\n- [x] Update Lemonade to support 1.10.0 changes\r\n- [x] Catalan translations\r\n- [x] Name field added to API keys\r\n- [x] Chat ID reported in agent sessions so now you can regenerate chats, TTS, and more actions without page reloads.\r\n\r\n\r\n## What's Changed\r\n* German translation fixes by @neuhaus in https://github.com/Mintplex-Labs/anything-llm/pull/5319\r\n* fix(lemonade): throw on embedding failures instead of returning empty by @nehaaprasad in https://github.com/Mintplex-Labs/anything-llm/pull/5325\r\n* Fix light mode docgen page by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5347\r\n* fix(agent-flows): keep flow menu visible in narrow windows by @suyua9 in https://github.com/Mintplex-Labs/anything-llm/pull/5341\r\n* Fix Agent Flow toggle state sync by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5348\r\n* Remove illegal chars for Windows on files by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5364\r\n* feat: Document Embedding Status Events | Refactor Document Embedding to Job Queue and Forked Process by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5254\r\n* Update Lemonade Integration to support v10.1.0 changes by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5378\r\n* Enable final tool call in MAX_STACK to run by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5381\r\n* Fix streaming issue for LLM instruction blocks by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5382\r\n* Add retry handling to TG for transient failures by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5391\r\n* Migrate to org-maintained mdpdf for lang support (Hangul, Simplified Chinese, Kanji) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5392\r\n* feat: adds name field to api keys by @guilopesn in https://github.com/Mintplex-Labs/anything-llm/pull/5366\r\n* Add automatic agent skill aproval via ENV Flag by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5405\r\n* GMail Agent Skill by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5400\r\n* Helm chart updates by @bustapipes in https://github.com/Mintplex-Labs/anything-llm/pull/5410\r\n* feat: add Catalan translation by @jordimas in https://github.com/Mintplex-Labs/anything-llm/pull/5411\r\n* fix: preserve Confluence context paths by @officialasishkumar in https://github.com/Mintplex-Labs/anything-llm/pull/5415\r\n* Enable chatId reporting during agent sessions by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5407\r\n* 5427 translations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5429\r\n* Outlook agent via Entra Application by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5427\r\n* Refactor Gmail Agent by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5439\r\n* Google calendar skill by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5442\r\n* Image lightbox for chat attachments by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5441\r\n* Add capability detection and streaming usage for Generic OpenAI provider by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5477\r\n* fix: omit temperature param for Bedrock Claude Opus 4.7 by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5472\r\n* fix: long-prompt bubble flicker & See More collapse on streaming/scroll by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5473\r\n* fix: surface readable error messages in web-scraping agent and ai-provider by @Akhil373 in https://github.com/Mintplex-Labs/anything-llm/pull/5476\r\n* 1.12.1 release tags by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5483\r\n\r\n## New Contributors\r\n* @neuhaus made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5319\r\n* @suyua9 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5341\r\n* @guilopesn made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5366\r\n* @bustapipes made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5410\r\n* @jordimas made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5411\r\n* @officialasishkumar made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5415\r\n* @Akhil373 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5476\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.0...v1.12.1","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Improvements</h2><a id=\"user-content-notable-improvements\" class=\"anchor\" aria-label=\"Permalink: Notable Improvements\" href=\"#notable-improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Streamed Document Embedding</h3><a id=\"user-content-streamed-document-embedding\" class=\"anchor\" aria-label=\"Permalink: Streamed Document Embedding\" href=\"#streamed-document-embedding\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, when you upload a document to the workspace the process per-document is now reported during embedding. This is a huge improvement in performance and user experience. During this process you can add and remove documents to the queue as well as even close and navigate away from the page without losing your progress.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/ffbd06ad-cd2c-480a-89ba-bb7a0068abbc\"><img width=\"1745\" height=\"1011\" alt=\"queue-embedding\" src=\"https://github.com/user-attachments/assets/ffbd06ad-cd2c-480a-89ba-bb7a0068abbc\" style=\"max-width: 100%; height: auto; max-height: 1011px;\"></a></p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">App integrations</h3><a id=\"user-content-app-integrations\" class=\"anchor\" aria-label=\"Permalink: App integrations\" href=\"#app-integrations\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>There are now built in integrations for the following apps with minimal to zero setup required for Agent skills:</p>\n<ul>\n<li><a href=\"https://docs.anythingllm.com/agent/usage/gmail-agent\" rel=\"nofollow\">Gmail</a></li>\n<li><a href=\"https://docs.anythingllm.com/agent/usage/outlook-agent\" rel=\"nofollow\">Outlook</a></li>\n<li><a href=\"https://docs.anythingllm.com/agent/usage/google-calendar-agent\" rel=\"nofollow\">Google Calendar</a></li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Other Improvements</h2><a id=\"user-content-other-improvements\" class=\"anchor\" aria-label=\"Permalink: Other Improvements\" href=\"#other-improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>[x] Image Lightbox in main UI</li>\n<li>[x] Enabled Korean, Chinese, &amp; Japanese character support for PDF generation via custom mdpdf fork</li>\n<li>[x] Better citations for app integrations</li>\n<li>[x] DDG default web-search in agent skills</li>\n<li>[x] Open documents in native application on machine when generated by Document Generation Agent</li>\n<li>[x] Auto approve agent skill via ENV setting</li>\n<li>[x] Ollama bumped to 0.20.7 (Qwen3.5 support, Gemma 4, etc)</li>\n<li>[x] New Customization &gt; Chat setting for <code>Unload model when closed</code> to unload the model when the user closes the chat window.</li>\n<li>[x] Generic OpenAI Capability detection/ENV setting</li>\n<li>[x] Update Lemonade to support 1.10.0 changes</li>\n<li>[x] Catalan translations</li>\n<li>[x] Name field added to API keys</li>\n<li>[x] Chat ID reported in agent sessions so now you can regenerate chats, TTS, and more actions without page reloads.</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>German translation fixes by @neuhaus in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5319\">https://github.com/Mintplex-Labs/anything-llm/pull/5319</a>\n</li>\n<li>fix(lemonade): throw on embedding failures instead of returning empty by @nehaaprasad in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5325\">https://github.com/Mintplex-Labs/anything-llm/pull/5325</a>\n</li>\n<li>Fix light mode docgen page by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5347\">https://github.com/Mintplex-Labs/anything-llm/pull/5347</a>\n</li>\n<li>fix(agent-flows): keep flow menu visible in narrow windows by @suyua9 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5341\">https://github.com/Mintplex-Labs/anything-llm/pull/5341</a>\n</li>\n<li>Fix Agent Flow toggle state sync by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5348\">https://github.com/Mintplex-Labs/anything-llm/pull/5348</a>\n</li>\n<li>Remove illegal chars for Windows on files by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5364\">https://github.com/Mintplex-Labs/anything-llm/pull/5364</a>\n</li>\n<li>feat: Document Embedding Status Events | Refactor Document Embedding to Job Queue and Forked Process by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5254\">https://github.com/Mintplex-Labs/anything-llm/pull/5254</a>\n</li>\n<li>Update Lemonade Integration to support v10.1.0 changes by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5378\">https://github.com/Mintplex-Labs/anything-llm/pull/5378</a>\n</li>\n<li>Enable final tool call in MAX_STACK to run by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5381\">https://github.com/Mintplex-Labs/anything-llm/pull/5381</a>\n</li>\n<li>Fix streaming issue for LLM instruction blocks by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5382\">https://github.com/Mintplex-Labs/anything-llm/pull/5382</a>\n</li>\n<li>Add retry handling to TG for transient failures by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5391\">https://github.com/Mintplex-Labs/anything-llm/pull/5391</a>\n</li>\n<li>Migrate to org-maintained mdpdf for lang support (Hangul, Simplified Chinese, Kanji) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5392\">https://github.com/Mintplex-Labs/anything-llm/pull/5392</a>\n</li>\n<li>feat: adds name field to api keys by @guilopesn in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5366\">https://github.com/Mintplex-Labs/anything-llm/pull/5366</a>\n</li>\n<li>Add automatic agent skill aproval via ENV Flag by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5405\">https://github.com/Mintplex-Labs/anything-llm/pull/5405</a>\n</li>\n<li>GMail Agent Skill by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5400\">https://github.com/Mintplex-Labs/anything-llm/pull/5400</a>\n</li>\n<li>Helm chart updates by @bustapipes in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5410\">https://github.com/Mintplex-Labs/anything-llm/pull/5410</a>\n</li>\n<li>feat: add Catalan translation by @jordimas in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5411\">https://github.com/Mintplex-Labs/anything-llm/pull/5411</a>\n</li>\n<li>fix: preserve Confluence context paths by @officialasishkumar in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5415\">https://github.com/Mintplex-Labs/anything-llm/pull/5415</a>\n</li>\n<li>Enable chatId reporting during agent sessions by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5407\">https://github.com/Mintplex-Labs/anything-llm/pull/5407</a>\n</li>\n<li>5427 translations by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5429\">https://github.com/Mintplex-Labs/anything-llm/pull/5429</a>\n</li>\n<li>Outlook agent via Entra Application by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5427\">https://github.com/Mintplex-Labs/anything-llm/pull/5427</a>\n</li>\n<li>Refactor Gmail Agent by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5439\">https://github.com/Mintplex-Labs/anything-llm/pull/5439</a>\n</li>\n<li>Google calendar skill by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5442\">https://github.com/Mintplex-Labs/anything-llm/pull/5442</a>\n</li>\n<li>Image lightbox for chat attachments by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5441\">https://github.com/Mintplex-Labs/anything-llm/pull/5441</a>\n</li>\n<li>Add capability detection and streaming usage for Generic OpenAI provider by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5477\">https://github.com/Mintplex-Labs/anything-llm/pull/5477</a>\n</li>\n<li>fix: omit temperature param for Bedrock Claude Opus 4.7 by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5472\">https://github.com/Mintplex-Labs/anything-llm/pull/5472</a>\n</li>\n<li>fix: long-prompt bubble flicker &amp; See More collapse on streaming/scroll by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5473\">https://github.com/Mintplex-Labs/anything-llm/pull/5473</a>\n</li>\n<li>fix: surface readable error messages in web-scraping agent and ai-provider by @Akhil373 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5476\">https://github.com/Mintplex-Labs/anything-llm/pull/5476</a>\n</li>\n<li>1.12.1 release tags by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5483\">https://github.com/Mintplex-Labs/anything-llm/pull/5483</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@neuhaus made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5319\">https://github.com/Mintplex-Labs/anything-llm/pull/5319</a>\n</li>\n<li>@suyua9 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5341\">https://github.com/Mintplex-Labs/anything-llm/pull/5341</a>\n</li>\n<li>@guilopesn made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5366\">https://github.com/Mintplex-Labs/anything-llm/pull/5366</a>\n</li>\n<li>@bustapipes made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5410\">https://github.com/Mintplex-Labs/anything-llm/pull/5410</a>\n</li>\n<li>@jordimas made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5411\">https://github.com/Mintplex-Labs/anything-llm/pull/5411</a>\n</li>\n<li>@officialasishkumar made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5415\">https://github.com/Mintplex-Labs/anything-llm/pull/5415</a>\n</li>\n<li>@Akhil373 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5476\">https://github.com/Mintplex-Labs/anything-llm/pull/5476</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.0...v1.12.1\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.12.0...v1.12.1</a></p>\n","assets":[]},{"id":304840982,"tag":"v1.12.0","author":"timothycarambat","name":"AnythingLLM v1.12.0","draft":false,"prerelease":false,"createdAt":"2026-04-02T20:52:00Z","publishedAt":"2026-04-02T20:56:02Z","markdown":"## Major Features\r\n\r\n\r\n### Automatic Mode for native tool calling\r\n\r\nFor [Select providers](https://docs.anythingllm.com/features/chat-modes#available-chat-modes) that support native tool calling, you no longer need to use `@agent` to use tools. You can now just use the tools without asking.\r\n\r\nIf your prompt input does not have the \"@\" symbol, your chats will automatically use tools as needed.\r\n\r\nhttps://github.com/user-attachments/assets/2ab6af9a-98d0-4d52-a3d3-849d70e64004\r\n\r\n## Intelligent Tool Selection\r\n\r\nWe have added a new feature called [Intelligent Tool Selection](https://docs.anythingllm.com/agent/intelligent-tool-selection). This feature allows you to load **unlimited** tools for your agent to use into context with better performance and save up to 80% on token usage every single chat.\r\n\r\n<img width=\"1713\" height=\"898\" alt=\"settings-menu-icon-location\" src=\"https://github.com/user-attachments/assets/06d2eb83-6eff-4ab2-92ba-43ecda5e7523\" />\r\n\r\n## Filesystem Agent\r\n\r\nWe have added a new feature called [Filesystem Agent](https://docs.anythingllm.com/agent/usage#file-system-agent). This feature allows you to use the filesystem of your host machine to search for files and directories.\r\n\r\n<img width=\"3456\" height=\"1810\" alt=\"fs-main-panel\" src=\"https://github.com/user-attachments/assets/142dd8c3-ebb4-4fb9-81dd-ede225c93227\" />\r\n\r\n## Document Generation Agent\r\n\r\nWe have added a new built-in agent for [Document Generation](https://docs.anythingllm.com/agent/usage#document-generation-agent). With document generation, you can generate text files, PDFs, Excel files, Docx, and even entire PowerPoint presentations.\r\n\r\n\r\nhttps://github.com/user-attachments/assets/493e27bb-4944-4a8d-8995-a7c8b3eaadd5\r\n\r\n\r\n## Telegram Bot\r\n\r\nAnythingLLM Docker and Desktop now support a [Telegram bot](https://docs.anythingllm.com/channels/telegram) so you can connect to your AnythingLLM instance anywhere in the world.\r\n\r\n**Supports**:\r\n- Text chat (streaming & thinking)\r\n- Image understanding\r\n- Voice messages & Attachments\r\n- Automatic mode and @agent support\r\n- Workspace and thread selection\r\n- Model selection\r\n- Citations\r\n- Any agent skill available in AnythingLLM\r\n\r\n<img width=\"400\" height=\"800\" alt=\"image-understanding\" src=\"https://github.com/user-attachments/assets/2208bfda-1385-44ef-af1e-704da5c4be25\" />\r\n\r\n## What's Changed\r\n* update exa search provider description by @theishangoswami in https://github.com/Mintplex-Labs/anything-llm/pull/5225\r\n* Automatic mode for workspace (Agent mode default) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5143\r\n* MCP tool manager by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5230\r\n* Intelligent Skill Selection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5236\r\n* README updates by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5238\r\n* fix(collector): infer file extension from Content-Type for URLs without explicit extensions by @Lyt060814 in https://github.com/Mintplex-Labs/anything-llm/pull/5252\r\n* feat: add Lithuanian locale and register in resources by @arvydev in https://github.com/Mintplex-Labs/anything-llm/pull/5243\r\n* Telegram bot connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5190\r\n* Add User-Agent header for Anthropic API calls by @mikelambert in https://github.com/Mintplex-Labs/anything-llm/pull/5174\r\n* add Dynamic `max_tokens` retreival for Anthropic models by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5255\r\n* fix Firefox LaTeX rendering by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5258\r\n* add ask to run prompt for tool calls (demo) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5261\r\n* Refactor onboarding welcome screen to v2 design by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5262\r\n* Filesystem Agent Skill overhaul by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5260\r\n* feat : auto-select newly uploaded docs/URLs in my documents list by @nehaaprasad in https://github.com/Mintplex-Labs/anything-llm/pull/5222\r\n* feat: add missing Lemonade LLM provider env vars to .env.example by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5275\r\n* feat: add optional API key support for Lemonade provider by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5281\r\n* File creation agent skills by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5280\r\n* Redesign Telegram bot settings UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5306\r\n* Fix chat UI event listener bloat by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5323\r\n\r\n## New Contributors\r\n* @theishangoswami made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5225\r\n* @Lyt060814 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5252\r\n* @arvydev made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5243\r\n* @mikelambert made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5174\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.2...v1.12.0","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Major Features</h2><a id=\"user-content-major-features\" class=\"anchor\" aria-label=\"Permalink: Major Features\" href=\"#major-features\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Automatic Mode for native tool calling</h3><a id=\"user-content-automatic-mode-for-native-tool-calling\" class=\"anchor\" aria-label=\"Permalink: Automatic Mode for native tool calling\" href=\"#automatic-mode-for-native-tool-calling\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>For <a href=\"https://docs.anythingllm.com/features/chat-modes#available-chat-modes\" rel=\"nofollow\">Select providers</a> that support native tool calling, you no longer need to use <code>@agent</code> to use tools. You can now just use the tools without asking.</p>\n<p>If your prompt input does not have the \"@\" symbol, your chats will automatically use tools as needed.</p>\n<p><a href=\"https://github.com/user-attachments/assets/2ab6af9a-98d0-4d52-a3d3-849d70e64004\">https://github.com/user-attachments/assets/2ab6af9a-98d0-4d52-a3d3-849d70e64004</a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Intelligent Tool Selection</h2><a id=\"user-content-intelligent-tool-selection\" class=\"anchor\" aria-label=\"Permalink: Intelligent Tool Selection\" href=\"#intelligent-tool-selection\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>We have added a new feature called <a href=\"https://docs.anythingllm.com/agent/intelligent-tool-selection\" rel=\"nofollow\">Intelligent Tool Selection</a>. This feature allows you to load <strong>unlimited</strong> tools for your agent to use into context with better performance and save up to 80% on token usage every single chat.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/06d2eb83-6eff-4ab2-92ba-43ecda5e7523\"><img width=\"1713\" height=\"898\" alt=\"settings-menu-icon-location\" src=\"https://github.com/user-attachments/assets/06d2eb83-6eff-4ab2-92ba-43ecda5e7523\" style=\"max-width: 100%; height: auto; max-height: 898px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Filesystem Agent</h2><a id=\"user-content-filesystem-agent\" class=\"anchor\" aria-label=\"Permalink: Filesystem Agent\" href=\"#filesystem-agent\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>We have added a new feature called <a href=\"https://docs.anythingllm.com/agent/usage#file-system-agent\" rel=\"nofollow\">Filesystem Agent</a>. This feature allows you to use the filesystem of your host machine to search for files and directories.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/142dd8c3-ebb4-4fb9-81dd-ede225c93227\"><img width=\"2000\" height=\"1047\" alt=\"fs-main-panel\" src=\"https://github.com/user-attachments/assets/142dd8c3-ebb4-4fb9-81dd-ede225c93227\" style=\"max-width: 100%; height: auto; max-height: 1047px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Document Generation Agent</h2><a id=\"user-content-document-generation-agent\" class=\"anchor\" aria-label=\"Permalink: Document Generation Agent\" href=\"#document-generation-agent\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>We have added a new built-in agent for <a href=\"https://docs.anythingllm.com/agent/usage#document-generation-agent\" rel=\"nofollow\">Document Generation</a>. With document generation, you can generate text files, PDFs, Excel files, Docx, and even entire PowerPoint presentations.</p>\n<p><a href=\"https://github.com/user-attachments/assets/493e27bb-4944-4a8d-8995-a7c8b3eaadd5\">https://github.com/user-attachments/assets/493e27bb-4944-4a8d-8995-a7c8b3eaadd5</a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Telegram Bot</h2><a id=\"user-content-telegram-bot\" class=\"anchor\" aria-label=\"Permalink: Telegram Bot\" href=\"#telegram-bot\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>AnythingLLM Docker and Desktop now support a <a href=\"https://docs.anythingllm.com/channels/telegram\" rel=\"nofollow\">Telegram bot</a> so you can connect to your AnythingLLM instance anywhere in the world.</p>\n<p><strong>Supports</strong>:</p>\n<ul>\n<li>Text chat (streaming &amp; thinking)</li>\n<li>Image understanding</li>\n<li>Voice messages &amp; Attachments</li>\n<li>Automatic mode and @agent support</li>\n<li>Workspace and thread selection</li>\n<li>Model selection</li>\n<li>Citations</li>\n<li>Any agent skill available in AnythingLLM</li>\n</ul>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/2208bfda-1385-44ef-af1e-704da5c4be25\"><img width=\"400\" height=\"800\" alt=\"image-understanding\" src=\"https://github.com/user-attachments/assets/2208bfda-1385-44ef-af1e-704da5c4be25\" style=\"max-width: 100%; height: auto; max-height: 800px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>update exa search provider description by @theishangoswami in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5225\">https://github.com/Mintplex-Labs/anything-llm/pull/5225</a>\n</li>\n<li>Automatic mode for workspace (Agent mode default) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5143\">https://github.com/Mintplex-Labs/anything-llm/pull/5143</a>\n</li>\n<li>MCP tool manager by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5230\">https://github.com/Mintplex-Labs/anything-llm/pull/5230</a>\n</li>\n<li>Intelligent Skill Selection by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5236\">https://github.com/Mintplex-Labs/anything-llm/pull/5236</a>\n</li>\n<li>README updates by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5238\">https://github.com/Mintplex-Labs/anything-llm/pull/5238</a>\n</li>\n<li>fix(collector): infer file extension from Content-Type for URLs without explicit extensions by @Lyt060814 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5252\">https://github.com/Mintplex-Labs/anything-llm/pull/5252</a>\n</li>\n<li>feat: add Lithuanian locale and register in resources by @arvydev in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5243\">https://github.com/Mintplex-Labs/anything-llm/pull/5243</a>\n</li>\n<li>Telegram bot connector by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5190\">https://github.com/Mintplex-Labs/anything-llm/pull/5190</a>\n</li>\n<li>Add User-Agent header for Anthropic API calls by @mikelambert in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5174\">https://github.com/Mintplex-Labs/anything-llm/pull/5174</a>\n</li>\n<li>add Dynamic <code>max_tokens</code> retreival for Anthropic models by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5255\">https://github.com/Mintplex-Labs/anything-llm/pull/5255</a>\n</li>\n<li>fix Firefox LaTeX rendering by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5258\">https://github.com/Mintplex-Labs/anything-llm/pull/5258</a>\n</li>\n<li>add ask to run prompt for tool calls (demo) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5261\">https://github.com/Mintplex-Labs/anything-llm/pull/5261</a>\n</li>\n<li>Refactor onboarding welcome screen to v2 design by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5262\">https://github.com/Mintplex-Labs/anything-llm/pull/5262</a>\n</li>\n<li>Filesystem Agent Skill overhaul by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5260\">https://github.com/Mintplex-Labs/anything-llm/pull/5260</a>\n</li>\n<li>feat : auto-select newly uploaded docs/URLs in my documents list by @nehaaprasad in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5222\">https://github.com/Mintplex-Labs/anything-llm/pull/5222</a>\n</li>\n<li>feat: add missing Lemonade LLM provider env vars to .env.example by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5275\">https://github.com/Mintplex-Labs/anything-llm/pull/5275</a>\n</li>\n<li>feat: add optional API key support for Lemonade provider by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5281\">https://github.com/Mintplex-Labs/anything-llm/pull/5281</a>\n</li>\n<li>File creation agent skills by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5280\">https://github.com/Mintplex-Labs/anything-llm/pull/5280</a>\n</li>\n<li>Redesign Telegram bot settings UI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5306\">https://github.com/Mintplex-Labs/anything-llm/pull/5306</a>\n</li>\n<li>Fix chat UI event listener bloat by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5323\">https://github.com/Mintplex-Labs/anything-llm/pull/5323</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@theishangoswami made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5225\">https://github.com/Mintplex-Labs/anything-llm/pull/5225</a>\n</li>\n<li>@Lyt060814 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5252\">https://github.com/Mintplex-Labs/anything-llm/pull/5252</a>\n</li>\n<li>@arvydev made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5243\">https://github.com/Mintplex-Labs/anything-llm/pull/5243</a>\n</li>\n<li>@mikelambert made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5174\">https://github.com/Mintplex-Labs/anything-llm/pull/5174</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.2...v1.12.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.2...v1.12.0</a></p>\n","assets":[]},{"id":298198229,"tag":"v1.11.2","author":"timothycarambat","name":"AnythingLLM v1.11.2","draft":false,"prerelease":false,"createdAt":"2026-03-18T16:26:09Z","publishedAt":"2026-03-18T16:57:50Z","markdown":"## More UI Improvements\r\n\r\nhttps://github.com/user-attachments/assets/9f2a0363-e905-420e-9c80-3b96fdb07368\r\n\r\nNow, in the main chat UI we added some much desired UI improvements and fixes.\r\n- [x] New prompt input\r\n- [x] Better Citations UI and reporting\r\n- [x] Metrics for Agent calls\r\n- [x] Report document and web-search citations during Agent calls!\r\n- [x] Ability to each toggle on/off Agent skills from the prompt\r\n- [x] Ability to select the provider and model for the workspace without leaving the page.\r\n\r\n----\r\n\r\n## What's Changed\r\n* 5112 or stream metrics and finish reason by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5117\r\n* Fix bug where `yarn setup:envs` fails if any .env file already exists. by @brianpursley in https://github.com/Mintplex-Labs/anything-llm/pull/5116\r\n* fix: show actionable error when LMStudio model listing fails or returns empty by @elevatingcreativity in https://github.com/Mintplex-Labs/anything-llm/pull/5131\r\n* Add automatic chat mode with native tool calling support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5140\r\n* Sidebar updates by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5154\r\n* Remove Google web-search Programmable SERP by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5156\r\n* refactor: refactor agent skills settings page to use i18n translation keys by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5146\r\n* chore: add ESLint to `/collector` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5128\r\n* chore: add ESLint to `/server` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5126\r\n* Fix: Azure OpenAI model key collision by @RALaBarge in https://github.com/Mintplex-Labs/anything-llm/pull/5092\r\n* feat: Add tooltip for paperclip attach button when no files are parsed by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5139\r\n* fix: add missing /wiki to Confluence cloud citation URLs by @MaxwellCalkin in https://github.com/Mintplex-Labs/anything-llm/pull/5167\r\n* Strip thinking from copy message outputs by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5179\r\n* Add custom fetch to embedder for Ollama by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5180\r\n* chore: add script to detect and prune unused translation keys by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5141\r\n* chore: add ESLint CI workflow by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5160\r\n* Implement v2 chat layout designs by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5074\r\n* Improve zh_TW Traditional Chinese locale by @PeterDaveHello in https://github.com/Mintplex-Labs/anything-llm/pull/5187\r\n* Improve build times for tests and lint by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5193\r\n* Support Agent stream metric reporting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5197\r\n* Report citations for Agent call stacks by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5199\r\n* Add FileRow Indentation on Documents Picker by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5201\r\n* Remove `WelcomeMessages` from app - no longer used by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5206\r\n* feat: Add document count indicators to workspace document management modal by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5207\r\n* feat(agents): Add Perplexity Search API as web search provider by @kesku in https://github.com/Mintplex-Labs/anything-llm/pull/5210\r\n\r\n## New Contributors\r\n* @brianpursley made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5116\r\n* @elevatingcreativity made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5131\r\n* @RALaBarge made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5092\r\n* @MaxwellCalkin made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5167\r\n* @PeterDaveHello made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5187\r\n* @kesku made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5210\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.1...v1.11.2","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">More UI Improvements</h2><a id=\"user-content-more-ui-improvements\" class=\"anchor\" aria-label=\"Permalink: More UI Improvements\" href=\"#more-ui-improvements\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a href=\"https://github.com/user-attachments/assets/9f2a0363-e905-420e-9c80-3b96fdb07368\">https://github.com/user-attachments/assets/9f2a0363-e905-420e-9c80-3b96fdb07368</a></p>\n<p>Now, in the main chat UI we added some much desired UI improvements and fixes.</p>\n<ul>\n<li>[x] New prompt input</li>\n<li>[x] Better Citations UI and reporting</li>\n<li>[x] Metrics for Agent calls</li>\n<li>[x] Report document and web-search citations during Agent calls!</li>\n<li>[x] Ability to each toggle on/off Agent skills from the prompt</li>\n<li>[x] Ability to select the provider and model for the workspace without leaving the page.</li>\n</ul>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>5112 or stream metrics and finish reason by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5117\">https://github.com/Mintplex-Labs/anything-llm/pull/5117</a>\n</li>\n<li>Fix bug where <code>yarn setup:envs</code> fails if any .env file already exists. by @brianpursley in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5116\">https://github.com/Mintplex-Labs/anything-llm/pull/5116</a>\n</li>\n<li>fix: show actionable error when LMStudio model listing fails or returns empty by @elevatingcreativity in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5131\">https://github.com/Mintplex-Labs/anything-llm/pull/5131</a>\n</li>\n<li>Add automatic chat mode with native tool calling support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5140\">https://github.com/Mintplex-Labs/anything-llm/pull/5140</a>\n</li>\n<li>Sidebar updates by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5154\">https://github.com/Mintplex-Labs/anything-llm/pull/5154</a>\n</li>\n<li>Remove Google web-search Programmable SERP by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5156\">https://github.com/Mintplex-Labs/anything-llm/pull/5156</a>\n</li>\n<li>refactor: refactor agent skills settings page to use i18n translation keys by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5146\">https://github.com/Mintplex-Labs/anything-llm/pull/5146</a>\n</li>\n<li>chore: add ESLint to <code>/collector</code> by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5128\">https://github.com/Mintplex-Labs/anything-llm/pull/5128</a>\n</li>\n<li>chore: add ESLint to <code>/server</code> by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5126\">https://github.com/Mintplex-Labs/anything-llm/pull/5126</a>\n</li>\n<li>Fix: Azure OpenAI model key collision by @RALaBarge in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5092\">https://github.com/Mintplex-Labs/anything-llm/pull/5092</a>\n</li>\n<li>feat: Add tooltip for paperclip attach button when no files are parsed by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5139\">https://github.com/Mintplex-Labs/anything-llm/pull/5139</a>\n</li>\n<li>fix: add missing /wiki to Confluence cloud citation URLs by @MaxwellCalkin in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5167\">https://github.com/Mintplex-Labs/anything-llm/pull/5167</a>\n</li>\n<li>Strip thinking from copy message outputs by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5179\">https://github.com/Mintplex-Labs/anything-llm/pull/5179</a>\n</li>\n<li>Add custom fetch to embedder for Ollama by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5180\">https://github.com/Mintplex-Labs/anything-llm/pull/5180</a>\n</li>\n<li>chore: add script to detect and prune unused translation keys by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5141\">https://github.com/Mintplex-Labs/anything-llm/pull/5141</a>\n</li>\n<li>chore: add ESLint CI workflow by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5160\">https://github.com/Mintplex-Labs/anything-llm/pull/5160</a>\n</li>\n<li>Implement v2 chat layout designs by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5074\">https://github.com/Mintplex-Labs/anything-llm/pull/5074</a>\n</li>\n<li>Improve zh_TW Traditional Chinese locale by @PeterDaveHello in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5187\">https://github.com/Mintplex-Labs/anything-llm/pull/5187</a>\n</li>\n<li>Improve build times for tests and lint by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5193\">https://github.com/Mintplex-Labs/anything-llm/pull/5193</a>\n</li>\n<li>Support Agent stream metric reporting by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5197\">https://github.com/Mintplex-Labs/anything-llm/pull/5197</a>\n</li>\n<li>Report citations for Agent call stacks by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5199\">https://github.com/Mintplex-Labs/anything-llm/pull/5199</a>\n</li>\n<li>Add FileRow Indentation on Documents Picker by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5201\">https://github.com/Mintplex-Labs/anything-llm/pull/5201</a>\n</li>\n<li>Remove <code>WelcomeMessages</code> from app - no longer used by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5206\">https://github.com/Mintplex-Labs/anything-llm/pull/5206</a>\n</li>\n<li>feat: Add document count indicators to workspace document management modal by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5207\">https://github.com/Mintplex-Labs/anything-llm/pull/5207</a>\n</li>\n<li>feat(agents): Add Perplexity Search API as web search provider by @kesku in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5210\">https://github.com/Mintplex-Labs/anything-llm/pull/5210</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@brianpursley made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5116\">https://github.com/Mintplex-Labs/anything-llm/pull/5116</a>\n</li>\n<li>@elevatingcreativity made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5131\">https://github.com/Mintplex-Labs/anything-llm/pull/5131</a>\n</li>\n<li>@RALaBarge made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5092\">https://github.com/Mintplex-Labs/anything-llm/pull/5092</a>\n</li>\n<li>@MaxwellCalkin made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5167\">https://github.com/Mintplex-Labs/anything-llm/pull/5167</a>\n</li>\n<li>@PeterDaveHello made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5187\">https://github.com/Mintplex-Labs/anything-llm/pull/5187</a>\n</li>\n<li>@kesku made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5210\">https://github.com/Mintplex-Labs/anything-llm/pull/5210</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.1...v1.11.2\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.1...v1.11.2</a></p>\n","assets":[{"contentType":"image/gif","size":31147746,"createdAt":"2026-03-19T19:06:46Z","updatedAt":"2026-03-19T19:06:49Z","downloadCount":547092,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.11.2/AnythingLLM720p.gif"}]},{"id":292168930,"tag":"v1.11.1","author":"timothycarambat","name":"AnythingLLM v1.11.1","draft":false,"prerelease":false,"createdAt":"2026-03-02T17:25:06Z","publishedAt":"2026-03-02T17:26:08Z","markdown":"## Homepage Redesign\r\n\r\nThe main AnythingLLM homepage has been completely redesigned to be more modern and user-friendly so you can instantly start chatting the second you open the app after onboarding.\r\n\r\n<img width=\"3680\" height=\"2212\" alt=\"homepage\" src=\"https://github.com/user-attachments/assets/b7b202b1-3a22-42c9-b46e-434b694c2ec5\" />\r\n\r\n\r\n## Native Tool Calling\r\n\r\n<Callout type=\"info\">\r\n  Native tool calling is the best performance and experience for tool calling with your LLM provider and model. If you can enable it, you should.\r\n  \r\n  _this only applies to local LLM providers. It has no impact on cloud LLMs like OpenAI, Anthropic, or Azure._\r\n</Callout>\r\n\r\nWe have completely overhauled how `@agent` tool calling works. Now, we will leverage the new native tool calling abilities of your LLM provider and model.\r\n\r\n**What this means for you:**\r\n- You can now run complex, **multi-step** tool calls with your LLM provider and model.\r\n- Your model will now continue to work until your final response is generated or determined to be complete.\r\n- You will get 100x better responses from even small tool-calling models\r\n\r\nWe have implemented safeguards as well to prevent infinite loops with a maximum of 10 tool calls per response to prevent runaway tasks.\r\n\r\n<img width=\"3680\" height=\"2212\" alt=\"native-tool-calling\" src=\"https://github.com/user-attachments/assets/52676899-77ca-4fdc-b728-9d61c7834536\" />\r\n\r\n\r\n### Limitations\r\n\r\nMost providers do not allow us to probe for if a model supports native tool calling.\r\n\r\nThe following local LLM providers will automatically support native tool calling if your model supports it:\r\n- Default Built in LLM Provider (AnythingLLM Default)\r\n- Ollama\r\n- LM Studio\r\n\r\nFor others, you will need to set an ENV variable to enable native tool calling for supported providers.\r\n- Generic OpenAI\r\n- Groq\r\n- AWS Bedrock\r\n- Lemonade\r\n- LiteLLM\r\n- Local AI\r\n- OpenRouter\r\n\r\nThis can be set via the [`PROVIDER_SUPPORTS_NATIVE_TOOL_CALLING`](/configuration#native-tool-calling-for-llm-providers) environment variable.\r\n```\r\nPROVIDER_SUPPORTS_NATIVE_TOOL_CALLING=\"bedrock,generic-openai,groq,lemonade,litellm,local-ai,openrouter\"\r\n```\r\n\r\n## Lemonade by AMD Integration\r\n<img width=\"3440\" height=\"1624\" alt=\"lemonade\" src=\"https://github.com/user-attachments/assets/9f1b56bc-0ad4-48ac-972d-a6541b2225f7\" />\r\n\r\n[Lemonade](https://lemonade-server.ai) by AMD is an [open-source](https://github.com/lemonade-sdk/lemonade) local model runtime that optimizes performance and efficiency for local models (LLM, ASR, TTS, Image Generation, etc.) for all types of hardware including AMD GPUs and NPUs.\r\n\r\nWe have added first class support so you can use your local models running via Lemonade within AnythingLLM for the best application experience on top of your local hardware.\r\n\r\n\r\n-----\r\n\r\n## What's Changed\r\n* fix: typo in contribution guidelines, update project metadata  and pull_request_temp...md by @dipanshurdev in https://github.com/Mintplex-Labs/anything-llm/pull/5010\r\n* feat: update light mode UI sidebar by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4996\r\n* fix(frontend): fix event listener memory leak in useIsDisabled hook by @dipanshurdev in https://github.com/Mintplex-Labs/anything-llm/pull/5027\r\n* feat: dedicated dark theme option with system preference support by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5007\r\n* Implement new home page redesign by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4931\r\n* fix: GitLab connector infinite loop and rate limit crash for large repos by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5021\r\n* fix: add password character validation to onboarding single-user setup by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5037\r\n* Native Tool calling by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5071\r\n* fix: resolve Gemini agent 400 error on tool call responses by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5054\r\n* fix: prevent CMD/CTRL+Arrow scroll from overriding textarea cursor movement by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/5053\r\n* Normalize scraper runtimeargs for bulk-scraper by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5083\r\n* Lemonade integration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5077\r\n\r\n## New Contributors\r\n* @dipanshurdev made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5010\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.0...v1.11.1","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Homepage Redesign</h2><a id=\"user-content-homepage-redesign\" class=\"anchor\" aria-label=\"Permalink: Homepage Redesign\" href=\"#homepage-redesign\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>The main AnythingLLM homepage has been completely redesigned to be more modern and user-friendly so you can instantly start chatting the second you open the app after onboarding.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/b7b202b1-3a22-42c9-b46e-434b694c2ec5\"><img width=\"2000\" height=\"1202\" alt=\"homepage\" src=\"https://github.com/user-attachments/assets/b7b202b1-3a22-42c9-b46e-434b694c2ec5\" style=\"max-width: 100%; height: auto; max-height: 1202px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Native Tool Calling</h2><a id=\"user-content-native-tool-calling\" class=\"anchor\" aria-label=\"Permalink: Native Tool Calling\" href=\"#native-tool-calling\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n\n  Native tool calling is the best performance and experience for tool calling with your LLM provider and model. If you can enable it, you should.\n<p><em>this only applies to local LLM providers. It has no impact on cloud LLMs like OpenAI, Anthropic, or Azure.</em>\n</p>\n<p>We have completely overhauled how <code>@agent</code> tool calling works. Now, we will leverage the new native tool calling abilities of your LLM provider and model.</p>\n<p><strong>What this means for you:</strong></p>\n<ul>\n<li>You can now run complex, <strong>multi-step</strong> tool calls with your LLM provider and model.</li>\n<li>Your model will now continue to work until your final response is generated or determined to be complete.</li>\n<li>You will get 100x better responses from even small tool-calling models</li>\n</ul>\n<p>We have implemented safeguards as well to prevent infinite loops with a maximum of 10 tool calls per response to prevent runaway tasks.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/52676899-77ca-4fdc-b728-9d61c7834536\"><img width=\"2000\" height=\"1202\" alt=\"native-tool-calling\" src=\"https://github.com/user-attachments/assets/52676899-77ca-4fdc-b728-9d61c7834536\" style=\"max-width: 100%; height: auto; max-height: 1202px;\"></a></p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Limitations</h3><a id=\"user-content-limitations\" class=\"anchor\" aria-label=\"Permalink: Limitations\" href=\"#limitations\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Most providers do not allow us to probe for if a model supports native tool calling.</p>\n<p>The following local LLM providers will automatically support native tool calling if your model supports it:</p>\n<ul>\n<li>Default Built in LLM Provider (AnythingLLM Default)</li>\n<li>Ollama</li>\n<li>LM Studio</li>\n</ul>\n<p>For others, you will need to set an ENV variable to enable native tool calling for supported providers.</p>\n<ul>\n<li>Generic OpenAI</li>\n<li>Groq</li>\n<li>AWS Bedrock</li>\n<li>Lemonade</li>\n<li>LiteLLM</li>\n<li>Local AI</li>\n<li>OpenRouter</li>\n</ul>\n<p>This can be set via the <a href=\"/configuration#native-tool-calling-for-llm-providers\"><code>PROVIDER_SUPPORTS_NATIVE_TOOL_CALLING</code></a> environment variable.</p>\n<pre><code>PROVIDER_SUPPORTS_NATIVE_TOOL_CALLING=\"bedrock,generic-openai,groq,lemonade,litellm,local-ai,openrouter\"\n</code></pre>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Lemonade by AMD Integration</h2><a id=\"user-content-lemonade-by-amd-integration\" class=\"anchor\" aria-label=\"Permalink: Lemonade by AMD Integration\" href=\"#lemonade-by-amd-integration\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/9f1b56bc-0ad4-48ac-972d-a6541b2225f7\"><img width=\"2000\" height=\"944\" alt=\"lemonade\" src=\"https://github.com/user-attachments/assets/9f1b56bc-0ad4-48ac-972d-a6541b2225f7\" style=\"max-width: 100%; height: auto; max-height: 944px;\"></a></p>\n<p><a href=\"https://lemonade-server.ai\" rel=\"nofollow\">Lemonade</a> by AMD is an <a href=\"https://github.com/lemonade-sdk/lemonade\">open-source</a> local model runtime that optimizes performance and efficiency for local models (LLM, ASR, TTS, Image Generation, etc.) for all types of hardware including AMD GPUs and NPUs.</p>\n<p>We have added first class support so you can use your local models running via Lemonade within AnythingLLM for the best application experience on top of your local hardware.</p>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix: typo in contribution guidelines, update project metadata  and pull_request_temp...md by @dipanshurdev in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5010\">https://github.com/Mintplex-Labs/anything-llm/pull/5010</a>\n</li>\n<li>feat: update light mode UI sidebar by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4996\">https://github.com/Mintplex-Labs/anything-llm/pull/4996</a>\n</li>\n<li>fix(frontend): fix event listener memory leak in useIsDisabled hook by @dipanshurdev in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5027\">https://github.com/Mintplex-Labs/anything-llm/pull/5027</a>\n</li>\n<li>feat: dedicated dark theme option with system preference support by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5007\">https://github.com/Mintplex-Labs/anything-llm/pull/5007</a>\n</li>\n<li>Implement new home page redesign by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4931\">https://github.com/Mintplex-Labs/anything-llm/pull/4931</a>\n</li>\n<li>fix: GitLab connector infinite loop and rate limit crash for large repos by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5021\">https://github.com/Mintplex-Labs/anything-llm/pull/5021</a>\n</li>\n<li>fix: add password character validation to onboarding single-user setup by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5037\">https://github.com/Mintplex-Labs/anything-llm/pull/5037</a>\n</li>\n<li>Native Tool calling by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5071\">https://github.com/Mintplex-Labs/anything-llm/pull/5071</a>\n</li>\n<li>fix: resolve Gemini agent 400 error on tool call responses by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5054\">https://github.com/Mintplex-Labs/anything-llm/pull/5054</a>\n</li>\n<li>fix: prevent CMD/CTRL+Arrow scroll from overriding textarea cursor movement by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5053\">https://github.com/Mintplex-Labs/anything-llm/pull/5053</a>\n</li>\n<li>Normalize scraper runtimeargs for bulk-scraper by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5083\">https://github.com/Mintplex-Labs/anything-llm/pull/5083</a>\n</li>\n<li>Lemonade integration by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5077\">https://github.com/Mintplex-Labs/anything-llm/pull/5077</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@dipanshurdev made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/5010\">https://github.com/Mintplex-Labs/anything-llm/pull/5010</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.0...v1.11.1\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.11.0...v1.11.1</a></p>\n","assets":[]},{"id":287769284,"tag":"v1.11.0","author":"timothycarambat","name":"AnythingLLM v1.11.0","draft":false,"prerelease":false,"createdAt":"2026-02-18T16:47:47Z","publishedAt":"2026-02-18T17:08:45Z","markdown":"# AnythingLLM Desktop overlay is live!\r\n> _this is a free & desktop specific feature!_\r\n\r\nNow, AnythingLLM Desktop has an OS-level and application aware panel that opens in a single keystroke. Seamlessly ingest your current open applications alongside all other chat functionality you use like document chat, RAG, agents, and more.\r\n\r\nThis panel is such a smoother and more convenient way to use AnythingLLM - we highly recommend this for daily use!\r\n\r\nhttps://github.com/user-attachments/assets/0d3c260a-4d55-46e8-b11a-c6ecbf63e94d\r\n\r\n-----\r\n\r\n## What's Changed\r\n* Update common.js by @j0rDy in https://github.com/Mintplex-Labs/anything-llm/pull/4894\r\n* Add keyboard shortcuts to scroll to top and bottom of chat history by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4870\r\n* 4825 patch yt file collector api by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4904\r\n* Refine and Standardize Username Constraints by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4828\r\n* New login page UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4862\r\n* [Chore] Autotranslation tool using DMR by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4907\r\n* Persist Ollama context preferences in LC tools by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4908\r\n* Refactor Ollama context window setting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4909\r\n* Patch AzureOpenAI tool calling from `function` to `tool` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4922\r\n* Thinking block persist toggle state by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4916\r\n* Manage Onboarding decision via DB flag by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4926\r\n* Fix sidebar thread layer by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4881\r\n* Toggle switch component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4890\r\n* Fix: Clean username already exists error by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4914\r\n* fix: prevent Citations UI glitching during streaming chats by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4897\r\n* Support PrivateModeAI Integration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4937\r\n* feat: Add ability to edit existing SQL agent connections by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4848\r\n* Fix double scroll container in agent flow builder by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4933\r\n* feat: Enable essential ESLint rules and refactor frontend lint config by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4923\r\n* SambaNova Integration by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4943\r\n* Update LMStudio LLM & Embedder for API token by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4948\r\n* Web push notifications by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4942\r\n* Fix agent workspace settings loading forever by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4956\r\n* add provider field to chats by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4959\r\n* UAE region support for bedrock models by @vigorous-ride in https://github.com/Mintplex-Labs/anything-llm/pull/4964\r\n* fix: scroll active sidebar items into view by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4965\r\n* refactor: Migrate system preferences to field-based endpoint and remove deprecated endpoint by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4958\r\n* Refactor: Remove redundant message state sync in ChatContainer by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4941\r\n* chore: bump ollama SDK from 0.5.10 to 0.6.3 by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4977\r\n* set embedder output dimensions for LocalAI and Gemini (gemini-embedding-001) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4980\r\n* Fix Sidebar Clipping When Closed by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4970\r\n* fix: correct TPS calculation for Generic OpenAI provider with llama.cpp by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4981\r\n* add support for custom headers for LLM Generic OpenAI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4999\r\n\r\n## New Contributors\r\n* @j0rDy made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4894\r\n* @vigorous-ride made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4964\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.10.0...v1.11.0","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">AnythingLLM Desktop overlay is live!</h1><a id=\"user-content-anythingllm-desktop-overlay-is-live\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM Desktop overlay is live!\" href=\"#anythingllm-desktop-overlay-is-live\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<blockquote>\n<p><em>this is a free &amp; desktop specific feature!</em></p>\n</blockquote>\n<p>Now, AnythingLLM Desktop has an OS-level and application aware panel that opens in a single keystroke. Seamlessly ingest your current open applications alongside all other chat functionality you use like document chat, RAG, agents, and more.</p>\n<p>This panel is such a smoother and more convenient way to use AnythingLLM - we highly recommend this for daily use!</p>\n<p><a href=\"https://github.com/user-attachments/assets/0d3c260a-4d55-46e8-b11a-c6ecbf63e94d\">https://github.com/user-attachments/assets/0d3c260a-4d55-46e8-b11a-c6ecbf63e94d</a></p>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Update common.js by @j0rDy in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4894\">https://github.com/Mintplex-Labs/anything-llm/pull/4894</a>\n</li>\n<li>Add keyboard shortcuts to scroll to top and bottom of chat history by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4870\">https://github.com/Mintplex-Labs/anything-llm/pull/4870</a>\n</li>\n<li>4825 patch yt file collector api by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4904\">https://github.com/Mintplex-Labs/anything-llm/pull/4904</a>\n</li>\n<li>Refine and Standardize Username Constraints by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4828\">https://github.com/Mintplex-Labs/anything-llm/pull/4828</a>\n</li>\n<li>New login page UI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4862\">https://github.com/Mintplex-Labs/anything-llm/pull/4862</a>\n</li>\n<li>[Chore] Autotranslation tool using DMR by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4907\">https://github.com/Mintplex-Labs/anything-llm/pull/4907</a>\n</li>\n<li>Persist Ollama context preferences in LC tools by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4908\">https://github.com/Mintplex-Labs/anything-llm/pull/4908</a>\n</li>\n<li>Refactor Ollama context window setting by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4909\">https://github.com/Mintplex-Labs/anything-llm/pull/4909</a>\n</li>\n<li>Patch AzureOpenAI tool calling from <code>function</code> to <code>tool</code> by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4922\">https://github.com/Mintplex-Labs/anything-llm/pull/4922</a>\n</li>\n<li>Thinking block persist toggle state by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4916\">https://github.com/Mintplex-Labs/anything-llm/pull/4916</a>\n</li>\n<li>Manage Onboarding decision via DB flag by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4926\">https://github.com/Mintplex-Labs/anything-llm/pull/4926</a>\n</li>\n<li>Fix sidebar thread layer by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4881\">https://github.com/Mintplex-Labs/anything-llm/pull/4881</a>\n</li>\n<li>Toggle switch component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4890\">https://github.com/Mintplex-Labs/anything-llm/pull/4890</a>\n</li>\n<li>Fix: Clean username already exists error by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4914\">https://github.com/Mintplex-Labs/anything-llm/pull/4914</a>\n</li>\n<li>fix: prevent Citations UI glitching during streaming chats by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4897\">https://github.com/Mintplex-Labs/anything-llm/pull/4897</a>\n</li>\n<li>Support PrivateModeAI Integration by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4937\">https://github.com/Mintplex-Labs/anything-llm/pull/4937</a>\n</li>\n<li>feat: Add ability to edit existing SQL agent connections by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4848\">https://github.com/Mintplex-Labs/anything-llm/pull/4848</a>\n</li>\n<li>Fix double scroll container in agent flow builder by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4933\">https://github.com/Mintplex-Labs/anything-llm/pull/4933</a>\n</li>\n<li>feat: Enable essential ESLint rules and refactor frontend lint config by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4923\">https://github.com/Mintplex-Labs/anything-llm/pull/4923</a>\n</li>\n<li>SambaNova Integration by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4943\">https://github.com/Mintplex-Labs/anything-llm/pull/4943</a>\n</li>\n<li>Update LMStudio LLM &amp; Embedder for API token by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4948\">https://github.com/Mintplex-Labs/anything-llm/pull/4948</a>\n</li>\n<li>Web push notifications by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4942\">https://github.com/Mintplex-Labs/anything-llm/pull/4942</a>\n</li>\n<li>Fix agent workspace settings loading forever by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4956\">https://github.com/Mintplex-Labs/anything-llm/pull/4956</a>\n</li>\n<li>add provider field to chats by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4959\">https://github.com/Mintplex-Labs/anything-llm/pull/4959</a>\n</li>\n<li>UAE region support for bedrock models by @vigorous-ride in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4964\">https://github.com/Mintplex-Labs/anything-llm/pull/4964</a>\n</li>\n<li>fix: scroll active sidebar items into view by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4965\">https://github.com/Mintplex-Labs/anything-llm/pull/4965</a>\n</li>\n<li>refactor: Migrate system preferences to field-based endpoint and remove deprecated endpoint by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4958\">https://github.com/Mintplex-Labs/anything-llm/pull/4958</a>\n</li>\n<li>Refactor: Remove redundant message state sync in ChatContainer by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4941\">https://github.com/Mintplex-Labs/anything-llm/pull/4941</a>\n</li>\n<li>chore: bump ollama SDK from 0.5.10 to 0.6.3 by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4977\">https://github.com/Mintplex-Labs/anything-llm/pull/4977</a>\n</li>\n<li>set embedder output dimensions for LocalAI and Gemini (gemini-embedding-001) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4980\">https://github.com/Mintplex-Labs/anything-llm/pull/4980</a>\n</li>\n<li>Fix Sidebar Clipping When Closed by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4970\">https://github.com/Mintplex-Labs/anything-llm/pull/4970</a>\n</li>\n<li>fix: correct TPS calculation for Generic OpenAI provider with llama.cpp by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4981\">https://github.com/Mintplex-Labs/anything-llm/pull/4981</a>\n</li>\n<li>add support for custom headers for LLM Generic OpenAI by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4999\">https://github.com/Mintplex-Labs/anything-llm/pull/4999</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@j0rDy made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4894\">https://github.com/Mintplex-Labs/anything-llm/pull/4894</a>\n</li>\n<li>@vigorous-ride made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4964\">https://github.com/Mintplex-Labs/anything-llm/pull/4964</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.10.0...v1.11.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.10.0...v1.11.0</a></p>\n","assets":[]},{"id":278828738,"tag":"v1.10.0","author":"timothycarambat","name":"AnythingLLM v1.10.0","draft":false,"prerelease":false,"createdAt":"2026-01-22T00:10:07Z","publishedAt":"2026-01-22T15:52:48Z","markdown":"<img width=\"2560\" height=\"700\" alt=\"v1 10 0 (1)\" src=\"https://github.com/user-attachments/assets/39285372-787a-4b2d-b493-06e9d8044932\" />\r\n\r\n## Highlighted Changes\r\n\r\n### AnythingLLM Desktop Assistant is live!\r\nNow, AnythingLLM Desktop is a drop-in replacement for paid tools like Granola, Otter, Fireflies, and more.\r\n- Runs entirely on your device, can record meetings without joining or summarize arbitrary files\r\n- Powered by NVIDIA Parakeet + AnythingLLM's on-device orchastration\r\n- Can call any agent tool, MCP, or anything else you already use with AnythingLLM!\r\n- Custom summary templates, chat with the transcript, and even speaker identification.\r\n- \"Joined Meeting\" Desktop notification to start a new recording with a click. For any meeting software (Zoom, Slack, Discord, Teams, etc)\r\n- **No rate limits, usage caps, or restrictions** \r\n\r\nhttps://github.com/user-attachments/assets/355ad2fc-cca1-4e9d-8f08-4a1a08dac48d\r\n\r\n\r\n### AnythingLLM Mobile is live on Google Play\r\nThe [Android AnythingLLM Mobile App](https://play.google.com/store/apps/details?id=com.anythingllm) is live on Google Play now. This syncs with both Cloud/Self-hosted and Desktop versions of AnythingLLM.\r\n\r\nhttps://github.com/user-attachments/assets/e4232dfa-e42e-4d15-af9e-d58f2f0245f9\r\n\r\n## Notable other changes\r\n- Removed onboarding \"Create workspace\" page -> goes straight to home now with new workspace in user native language\r\n- Refactored Workspace file picker to be more performant\r\n- Migrated Azure OpenAI to unified `v1` api with full agent support\r\n- Fixed Pagination bug in paperless-ngx\r\n- Fixed issue where the undocumented YouTube API changed and broke the YT scraper\r\n- Implemented `Cohere` as an agent provider\r\n- A bump of dependency bumps\r\n- Fixed bug where XSLX files dragged and dropped into chat weren't \"visible\" to the model\r\n- MCP fixes for paths on non-Windows machines\r\n- Docker image bumps and patches for a healthy Scout score (B)\r\n- Added Error Boundary to UI to prevent white-page crashes\r\n\r\n## What's Changed\r\n* bump `body-parser` patch version by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4746\r\n* Remove bcrypt from collector - not used by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4747\r\n* `jws` bump by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4748\r\n* Refactor WorkspaceFileRow component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4740\r\n* Fix stale user permissions in UI by refreshing user data on app load by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4751\r\n* Docker base image upgrade to Ubuntu 24 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4754\r\n* Bump expressJS from 4.18.2 -> 4.21.2 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4760\r\n* Migrate Azure OpenAI Integration To v1 API | Enable Streaming for Reasoning Models in Azure OpenAI Basic Inference Provider by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4744\r\n* Bump `form-data` version by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4761\r\n* Lazy load Lancedb by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4764\r\n* Migrate to `bcryptjs` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4767\r\n* Refactor frontend legacy JSON.parse with safeJsonParse by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4759\r\n* Fix pagination bug in paperless-ngx data connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4757\r\n* Fix Stale User Session with Proper `fetch` Error Handling by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4770\r\n* Add Auth Token to Ollama Embedding Client by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4766\r\n* Upgrade to Multer 2.0.0 by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4768\r\n* Implement Global Error Boundary by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4765\r\n* Feat/cohere agent implementation by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4703\r\n* Upgrade MCP SDK to Latest (1.24.3) by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4773\r\n* fix(devcontainer): forward ports 3000/3001 by @lohas1107 in https://github.com/Mintplex-Labs/anything-llm/pull/4779\r\n* 4601 log model on response by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4781\r\n* Update Google Search Option Description To Reference Documentation For Rate Limits by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4789\r\n* Refactor `LLMPerformanceMonitor.measureStream()` to Use Options Object Pattern by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4786\r\n* fix unnecessary scrollbar in workspace general appearance settings tab by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4791\r\n* Add Eslint Config in `/frontend` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4785\r\n* Refactor localWhisper to use custom FFMPEGWrapper class by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4775\r\n* Refactor Managed Services in \"Data Handling & Privacy\" Onboarding Step to Use Their Privacy Policy URL by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4790\r\n* patch ESM import issue by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4819\r\n* Upgrade YT Scraper by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4820\r\n* fix: validate chat message input by @Ocheretovich in https://github.com/Mintplex-Labs/anything-llm/pull/4811\r\n* patch AWS credential issue in docker context by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4842\r\n* support AWS bedrock agents with streaming by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4850\r\n* VectorDB class migration by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4787\r\n* Make XLSX spreadsheets visible in chat by combining sheets by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4847\r\n* Remove Workspace Creation Onboarding Page by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4823\r\n* Improved DMR support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4863\r\n* AnythingLLM Mobile live by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4864\r\n* Adjust fix path to use ESM import by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4867\r\n* Extract Model Table to component by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4871\r\n* feat(i18n): add Czech (cs) language translation to AnythingLLM by @vladaman in https://github.com/Mintplex-Labs/anything-llm/pull/4874\r\n* Docker model runner download from UI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4884\r\n\r\n## New Contributors\r\n* @lohas1107 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4779\r\n* @Ocheretovich made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4811\r\n* @vladaman made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4874\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.1...v1.10.0","html":"<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/39285372-787a-4b2d-b493-06e9d8044932\"><img width=\"2000\" height=\"547\" alt=\"v1 10 0 (1)\" src=\"https://github.com/user-attachments/assets/39285372-787a-4b2d-b493-06e9d8044932\" style=\"max-width: 100%; height: auto; max-height: 547px;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Highlighted Changes</h2><a id=\"user-content-highlighted-changes\" class=\"anchor\" aria-label=\"Permalink: Highlighted Changes\" href=\"#highlighted-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">AnythingLLM Desktop Assistant is live!</h3><a id=\"user-content-anythingllm-desktop-assistant-is-live\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM Desktop Assistant is live!\" href=\"#anythingllm-desktop-assistant-is-live\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, AnythingLLM Desktop is a drop-in replacement for paid tools like Granola, Otter, Fireflies, and more.</p>\n<ul>\n<li>Runs entirely on your device, can record meetings without joining or summarize arbitrary files</li>\n<li>Powered by NVIDIA Parakeet + AnythingLLM's on-device orchastration</li>\n<li>Can call any agent tool, MCP, or anything else you already use with AnythingLLM!</li>\n<li>Custom summary templates, chat with the transcript, and even speaker identification.</li>\n<li>\"Joined Meeting\" Desktop notification to start a new recording with a click. For any meeting software (Zoom, Slack, Discord, Teams, etc)</li>\n<li><strong>No rate limits, usage caps, or restrictions</strong></li>\n</ul>\n<p><a href=\"https://github.com/user-attachments/assets/355ad2fc-cca1-4e9d-8f08-4a1a08dac48d\">https://github.com/user-attachments/assets/355ad2fc-cca1-4e9d-8f08-4a1a08dac48d</a></p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">AnythingLLM Mobile is live on Google Play</h3><a id=\"user-content-anythingllm-mobile-is-live-on-google-play\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM Mobile is live on Google Play\" href=\"#anythingllm-mobile-is-live-on-google-play\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>The <a href=\"https://play.google.com/store/apps/details?id=com.anythingllm\" rel=\"nofollow\">Android AnythingLLM Mobile App</a> is live on Google Play now. This syncs with both Cloud/Self-hosted and Desktop versions of AnythingLLM.</p>\n<p><a href=\"https://github.com/user-attachments/assets/e4232dfa-e42e-4d15-af9e-d58f2f0245f9\">https://github.com/user-attachments/assets/e4232dfa-e42e-4d15-af9e-d58f2f0245f9</a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable other changes</h2><a id=\"user-content-notable-other-changes\" class=\"anchor\" aria-label=\"Permalink: Notable other changes\" href=\"#notable-other-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Removed onboarding \"Create workspace\" page -&gt; goes straight to home now with new workspace in user native language</li>\n<li>Refactored Workspace file picker to be more performant</li>\n<li>Migrated Azure OpenAI to unified <code>v1</code> api with full agent support</li>\n<li>Fixed Pagination bug in paperless-ngx</li>\n<li>Fixed issue where the undocumented YouTube API changed and broke the YT scraper</li>\n<li>Implemented <code>Cohere</code> as an agent provider</li>\n<li>A bump of dependency bumps</li>\n<li>Fixed bug where XSLX files dragged and dropped into chat weren't \"visible\" to the model</li>\n<li>MCP fixes for paths on non-Windows machines</li>\n<li>Docker image bumps and patches for a healthy Scout score (B)</li>\n<li>Added Error Boundary to UI to prevent white-page crashes</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>bump <code>body-parser</code> patch version by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4746\">https://github.com/Mintplex-Labs/anything-llm/pull/4746</a>\n</li>\n<li>Remove bcrypt from collector - not used by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4747\">https://github.com/Mintplex-Labs/anything-llm/pull/4747</a>\n</li>\n<li>\n<code>jws</code> bump by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4748\">https://github.com/Mintplex-Labs/anything-llm/pull/4748</a>\n</li>\n<li>Refactor WorkspaceFileRow component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4740\">https://github.com/Mintplex-Labs/anything-llm/pull/4740</a>\n</li>\n<li>Fix stale user permissions in UI by refreshing user data on app load by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4751\">https://github.com/Mintplex-Labs/anything-llm/pull/4751</a>\n</li>\n<li>Docker base image upgrade to Ubuntu 24 by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4754\">https://github.com/Mintplex-Labs/anything-llm/pull/4754</a>\n</li>\n<li>Bump expressJS from 4.18.2 -&gt; 4.21.2 by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4760\">https://github.com/Mintplex-Labs/anything-llm/pull/4760</a>\n</li>\n<li>Migrate Azure OpenAI Integration To v1 API | Enable Streaming for Reasoning Models in Azure OpenAI Basic Inference Provider by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4744\">https://github.com/Mintplex-Labs/anything-llm/pull/4744</a>\n</li>\n<li>Bump <code>form-data</code> version by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4761\">https://github.com/Mintplex-Labs/anything-llm/pull/4761</a>\n</li>\n<li>Lazy load Lancedb by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4764\">https://github.com/Mintplex-Labs/anything-llm/pull/4764</a>\n</li>\n<li>Migrate to <code>bcryptjs</code> by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4767\">https://github.com/Mintplex-Labs/anything-llm/pull/4767</a>\n</li>\n<li>Refactor frontend legacy JSON.parse with safeJsonParse by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4759\">https://github.com/Mintplex-Labs/anything-llm/pull/4759</a>\n</li>\n<li>Fix pagination bug in paperless-ngx data connector by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4757\">https://github.com/Mintplex-Labs/anything-llm/pull/4757</a>\n</li>\n<li>Fix Stale User Session with Proper <code>fetch</code> Error Handling by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4770\">https://github.com/Mintplex-Labs/anything-llm/pull/4770</a>\n</li>\n<li>Add Auth Token to Ollama Embedding Client by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4766\">https://github.com/Mintplex-Labs/anything-llm/pull/4766</a>\n</li>\n<li>Upgrade to Multer 2.0.0 by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4768\">https://github.com/Mintplex-Labs/anything-llm/pull/4768</a>\n</li>\n<li>Implement Global Error Boundary by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4765\">https://github.com/Mintplex-Labs/anything-llm/pull/4765</a>\n</li>\n<li>Feat/cohere agent implementation by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4703\">https://github.com/Mintplex-Labs/anything-llm/pull/4703</a>\n</li>\n<li>Upgrade MCP SDK to Latest (1.24.3) by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4773\">https://github.com/Mintplex-Labs/anything-llm/pull/4773</a>\n</li>\n<li>fix(devcontainer): forward ports 3000/3001 by @lohas1107 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4779\">https://github.com/Mintplex-Labs/anything-llm/pull/4779</a>\n</li>\n<li>4601 log model on response by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4781\">https://github.com/Mintplex-Labs/anything-llm/pull/4781</a>\n</li>\n<li>Update Google Search Option Description To Reference Documentation For Rate Limits by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4789\">https://github.com/Mintplex-Labs/anything-llm/pull/4789</a>\n</li>\n<li>Refactor <code>LLMPerformanceMonitor.measureStream()</code> to Use Options Object Pattern by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4786\">https://github.com/Mintplex-Labs/anything-llm/pull/4786</a>\n</li>\n<li>fix unnecessary scrollbar in workspace general appearance settings tab by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4791\">https://github.com/Mintplex-Labs/anything-llm/pull/4791</a>\n</li>\n<li>Add Eslint Config in <code>/frontend</code> by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4785\">https://github.com/Mintplex-Labs/anything-llm/pull/4785</a>\n</li>\n<li>Refactor localWhisper to use custom FFMPEGWrapper class by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4775\">https://github.com/Mintplex-Labs/anything-llm/pull/4775</a>\n</li>\n<li>Refactor Managed Services in \"Data Handling &amp; Privacy\" Onboarding Step to Use Their Privacy Policy URL by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4790\">https://github.com/Mintplex-Labs/anything-llm/pull/4790</a>\n</li>\n<li>patch ESM import issue by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4819\">https://github.com/Mintplex-Labs/anything-llm/pull/4819</a>\n</li>\n<li>Upgrade YT Scraper by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4820\">https://github.com/Mintplex-Labs/anything-llm/pull/4820</a>\n</li>\n<li>fix: validate chat message input by @Ocheretovich in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4811\">https://github.com/Mintplex-Labs/anything-llm/pull/4811</a>\n</li>\n<li>patch AWS credential issue in docker context by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4842\">https://github.com/Mintplex-Labs/anything-llm/pull/4842</a>\n</li>\n<li>support AWS bedrock agents with streaming by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4850\">https://github.com/Mintplex-Labs/anything-llm/pull/4850</a>\n</li>\n<li>VectorDB class migration by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4787\">https://github.com/Mintplex-Labs/anything-llm/pull/4787</a>\n</li>\n<li>Make XLSX spreadsheets visible in chat by combining sheets by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4847\">https://github.com/Mintplex-Labs/anything-llm/pull/4847</a>\n</li>\n<li>Remove Workspace Creation Onboarding Page by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4823\">https://github.com/Mintplex-Labs/anything-llm/pull/4823</a>\n</li>\n<li>Improved DMR support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4863\">https://github.com/Mintplex-Labs/anything-llm/pull/4863</a>\n</li>\n<li>AnythingLLM Mobile live by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4864\">https://github.com/Mintplex-Labs/anything-llm/pull/4864</a>\n</li>\n<li>Adjust fix path to use ESM import by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4867\">https://github.com/Mintplex-Labs/anything-llm/pull/4867</a>\n</li>\n<li>Extract Model Table to component by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4871\">https://github.com/Mintplex-Labs/anything-llm/pull/4871</a>\n</li>\n<li>feat(i18n): add Czech (cs) language translation to AnythingLLM by @vladaman in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4874\">https://github.com/Mintplex-Labs/anything-llm/pull/4874</a>\n</li>\n<li>Docker model runner download from UI by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4884\">https://github.com/Mintplex-Labs/anything-llm/pull/4884</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@lohas1107 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4779\">https://github.com/Mintplex-Labs/anything-llm/pull/4779</a>\n</li>\n<li>@Ocheretovich made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4811\">https://github.com/Mintplex-Labs/anything-llm/pull/4811</a>\n</li>\n<li>@vladaman made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4874\">https://github.com/Mintplex-Labs/anything-llm/pull/4874</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.1...v1.10.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.1...v1.10.0</a></p>\n","assets":[]},{"id":268887125,"tag":"v1.9.1","author":"timothycarambat","name":"AnythingLLM 1.9.1","draft":false,"prerelease":false,"createdAt":"2025-12-05T21:31:15Z","publishedAt":"2025-12-09T20:56:11Z","markdown":"## Notable Changes\r\n* **PWA Support**: https://github.com/Mintplex-Labs/anything-llm/pull/4664\r\n* Enable keyboard nav of slash commands with arrow keys on mount https://github.com/Mintplex-Labs/anything-llm/pull/4543\r\n* Add ability to auto-handle YT video URLs in uploader & chat  https://github.com/Mintplex-Labs/anything-llm/pull/4547\r\n* Paperless ngx data connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4121\r\n* Add SerpApi web search by @alexbarron in https://github.com/Mintplex-Labs/anything-llm/pull/4623\r\n* Z.ai LLM & agent provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4573\r\n\r\n----\r\n\r\n## What's Changed\r\n* Fix KoboldCPP agent provider max tokens by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4519\r\n* Enable Microsoft Foundry Local for workspace agent provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4539\r\n* Enable keyboard nav of slash commands with arrow keys on mount by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4543\r\n* Add ability to auto-handle YT video URLs in uploader & chat by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4547\r\n* fix(server): correct Qdrant batching logic for large uploads by @aeromech-1 in https://github.com/Mintplex-Labs/anything-llm/pull/4545\r\n* Agent workspace system prompt with variable expansion by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4526\r\n* Refactor `DefaultChatContainer` To Display A Simple Welcome Message  by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4542\r\n* Refactor `loadYouTubeTranscript()` to include YouTube Video Metadata in Content When `parseOnly` is `true` by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4552\r\n* Patch agent thoughts UI bug by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4549\r\n* feat: support northflank deployment by @AdeboyeDN in https://github.com/Mintplex-Labs/anything-llm/pull/4570\r\n* Install `patch-package` in `/collector` and Apply Patch to Fix EPub Upload Bug by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4630\r\n* Failover invalid vector db identifier to lanceDB by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4661\r\n* fix: unhelpful error message for invite link user creation by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4621\r\n* feat: Allow email addresses as usernames by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4619\r\n* Fix loop logic for `fetchNextPage` use in GitLabLoader by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4662\r\n* add `svelte` rendering to markdown renderer by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4663\r\n* Disable Prisma CLI Telemetry in Entrypoint Shell Script by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4609\r\n* Support PWA installation by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4664\r\n* Disable swagger docs endpoint with environment variable by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4665\r\n* Paperless ngx data connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4121\r\n* Implement full chat and `@agent` chat `user` indentificiation for OpenRouter by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4668\r\n* fix: Use eval_duration for output TPS calculations in Ollama LLM provider by @jonathanortega2023 in https://github.com/Mintplex-Labs/anything-llm/pull/4568\r\n* Add SerpApi web search by @alexbarron in https://github.com/Mintplex-Labs/anything-llm/pull/4623\r\n* feature: Support for AWS Bedrock API Keys by @chetan in https://github.com/Mintplex-Labs/anything-llm/pull/4651\r\n* Update Ollama AI Provider to Support Parsing \"Thinking\" Content From New Message Schema by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4587\r\n* Z.ai LLM & agent provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4573\r\n* Simplify cache condition for LMStudio and Ollama to prevent race condition by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4669\r\n* Prompt caching for Anthropic LLM and Agent providers by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4488\r\n* Fix undefined result in llm-instruction agent flow executor by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4676\r\n* Custom Default System Prompt by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4487\r\n* feat: add base64 document attachment support to API chat endpoints by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4672\r\n* fixed typos in General Settings: settings/embedding-preferences by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4683\r\n* Feat/add openrouter embedding models by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4682\r\n* Add batch embedding support for Ollama embedding provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4553\r\n* Support Gitee AI(LLM Provider) by @fchange in https://github.com/Mintplex-Labs/anything-llm/pull/3361\r\n* feat: Add SSL certificate bypass support for self-hosted Confluence instances   by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4219\r\n* dev build with new `epub2` build target and remove patch work by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4694\r\n* docs(zh-TW): correct traditional Chinese translations in home section by @ascodeasice in https://github.com/Mintplex-Labs/anything-llm/pull/4702\r\n* docs(i18n): Complete French translations by @raphael-bynome in https://github.com/Mintplex-Labs/anything-llm/pull/4697\r\n* Store Chat Prompt Input Value in Local Storage by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4680\r\n* Migrate to react router createBrowserRouter by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4693\r\n* fixed empty scroll track in citations dropdown by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4685\r\n* Modify ChromaCloud provider to check base limitations of chroma cloud before upsert to prevent 422 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4705\r\n* Improve MCP functionality by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4709\r\n* Patch dev pupeeteer crash for MacOS 15 by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4713\r\n* Fix broken citations in Zilliz Cloud by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4716\r\n* Fix similarity score not showing in citation UI for Astra, Qdrant, Weaviate by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4718\r\n* Dell model capability patch by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4719\r\n\r\n## New Contributors\r\n* @aeromech-1 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4545\r\n* @AdeboyeDN made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4570\r\n* @jonathanortega2023 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4568\r\n* @alexbarron made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4623\r\n* @chetan made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4651\r\n* @fchange made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3361\r\n* @ascodeasice made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4702\r\n* @raphael-bynome made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4697\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.0...v1.9.1","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Changes</h2><a id=\"user-content-notable-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Changes\" href=\"#notable-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>\n<strong>PWA Support</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4664\">https://github.com/Mintplex-Labs/anything-llm/pull/4664</a>\n</li>\n<li>Enable keyboard nav of slash commands with arrow keys on mount <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4543\">https://github.com/Mintplex-Labs/anything-llm/pull/4543</a>\n</li>\n<li>Add ability to auto-handle YT video URLs in uploader &amp; chat  <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4547\">https://github.com/Mintplex-Labs/anything-llm/pull/4547</a>\n</li>\n<li>Paperless ngx data connector by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4121\">https://github.com/Mintplex-Labs/anything-llm/pull/4121</a>\n</li>\n<li>Add SerpApi web search by @alexbarron in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4623\">https://github.com/Mintplex-Labs/anything-llm/pull/4623</a>\n</li>\n<li>Z.ai LLM &amp; agent provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4573\">https://github.com/Mintplex-Labs/anything-llm/pull/4573</a>\n</li>\n</ul>\n<hr>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Fix KoboldCPP agent provider max tokens by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4519\">https://github.com/Mintplex-Labs/anything-llm/pull/4519</a>\n</li>\n<li>Enable Microsoft Foundry Local for workspace agent provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4539\">https://github.com/Mintplex-Labs/anything-llm/pull/4539</a>\n</li>\n<li>Enable keyboard nav of slash commands with arrow keys on mount by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4543\">https://github.com/Mintplex-Labs/anything-llm/pull/4543</a>\n</li>\n<li>Add ability to auto-handle YT video URLs in uploader &amp; chat by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4547\">https://github.com/Mintplex-Labs/anything-llm/pull/4547</a>\n</li>\n<li>fix(server): correct Qdrant batching logic for large uploads by @aeromech-1 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4545\">https://github.com/Mintplex-Labs/anything-llm/pull/4545</a>\n</li>\n<li>Agent workspace system prompt with variable expansion by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4526\">https://github.com/Mintplex-Labs/anything-llm/pull/4526</a>\n</li>\n<li>Refactor <code>DefaultChatContainer</code> To Display A Simple Welcome Message  by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4542\">https://github.com/Mintplex-Labs/anything-llm/pull/4542</a>\n</li>\n<li>Refactor <code>loadYouTubeTranscript()</code> to include YouTube Video Metadata in Content When <code>parseOnly</code> is <code>true</code> by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4552\">https://github.com/Mintplex-Labs/anything-llm/pull/4552</a>\n</li>\n<li>Patch agent thoughts UI bug by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4549\">https://github.com/Mintplex-Labs/anything-llm/pull/4549</a>\n</li>\n<li>feat: support northflank deployment by @AdeboyeDN in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4570\">https://github.com/Mintplex-Labs/anything-llm/pull/4570</a>\n</li>\n<li>Install <code>patch-package</code> in <code>/collector</code> and Apply Patch to Fix EPub Upload Bug by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4630\">https://github.com/Mintplex-Labs/anything-llm/pull/4630</a>\n</li>\n<li>Failover invalid vector db identifier to lanceDB by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4661\">https://github.com/Mintplex-Labs/anything-llm/pull/4661</a>\n</li>\n<li>fix: unhelpful error message for invite link user creation by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4621\">https://github.com/Mintplex-Labs/anything-llm/pull/4621</a>\n</li>\n<li>feat: Allow email addresses as usernames by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4619\">https://github.com/Mintplex-Labs/anything-llm/pull/4619</a>\n</li>\n<li>Fix loop logic for <code>fetchNextPage</code> use in GitLabLoader by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4662\">https://github.com/Mintplex-Labs/anything-llm/pull/4662</a>\n</li>\n<li>add <code>svelte</code> rendering to markdown renderer by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4663\">https://github.com/Mintplex-Labs/anything-llm/pull/4663</a>\n</li>\n<li>Disable Prisma CLI Telemetry in Entrypoint Shell Script by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4609\">https://github.com/Mintplex-Labs/anything-llm/pull/4609</a>\n</li>\n<li>Support PWA installation by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4664\">https://github.com/Mintplex-Labs/anything-llm/pull/4664</a>\n</li>\n<li>Disable swagger docs endpoint with environment variable by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4665\">https://github.com/Mintplex-Labs/anything-llm/pull/4665</a>\n</li>\n<li>Paperless ngx data connector by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4121\">https://github.com/Mintplex-Labs/anything-llm/pull/4121</a>\n</li>\n<li>Implement full chat and <code>@agent</code> chat <code>user</code> indentificiation for OpenRouter by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4668\">https://github.com/Mintplex-Labs/anything-llm/pull/4668</a>\n</li>\n<li>fix: Use eval_duration for output TPS calculations in Ollama LLM provider by @jonathanortega2023 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4568\">https://github.com/Mintplex-Labs/anything-llm/pull/4568</a>\n</li>\n<li>Add SerpApi web search by @alexbarron in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4623\">https://github.com/Mintplex-Labs/anything-llm/pull/4623</a>\n</li>\n<li>feature: Support for AWS Bedrock API Keys by @chetan in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4651\">https://github.com/Mintplex-Labs/anything-llm/pull/4651</a>\n</li>\n<li>Update Ollama AI Provider to Support Parsing \"Thinking\" Content From New Message Schema by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4587\">https://github.com/Mintplex-Labs/anything-llm/pull/4587</a>\n</li>\n<li>Z.ai LLM &amp; agent provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4573\">https://github.com/Mintplex-Labs/anything-llm/pull/4573</a>\n</li>\n<li>Simplify cache condition for LMStudio and Ollama to prevent race condition by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4669\">https://github.com/Mintplex-Labs/anything-llm/pull/4669</a>\n</li>\n<li>Prompt caching for Anthropic LLM and Agent providers by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4488\">https://github.com/Mintplex-Labs/anything-llm/pull/4488</a>\n</li>\n<li>Fix undefined result in llm-instruction agent flow executor by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4676\">https://github.com/Mintplex-Labs/anything-llm/pull/4676</a>\n</li>\n<li>Custom Default System Prompt by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4487\">https://github.com/Mintplex-Labs/anything-llm/pull/4487</a>\n</li>\n<li>feat: add base64 document attachment support to API chat endpoints by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4672\">https://github.com/Mintplex-Labs/anything-llm/pull/4672</a>\n</li>\n<li>fixed typos in General Settings: settings/embedding-preferences by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4683\">https://github.com/Mintplex-Labs/anything-llm/pull/4683</a>\n</li>\n<li>Feat/add openrouter embedding models by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4682\">https://github.com/Mintplex-Labs/anything-llm/pull/4682</a>\n</li>\n<li>Add batch embedding support for Ollama embedding provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4553\">https://github.com/Mintplex-Labs/anything-llm/pull/4553</a>\n</li>\n<li>Support Gitee AI(LLM Provider) by @fchange in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3361\">https://github.com/Mintplex-Labs/anything-llm/pull/3361</a>\n</li>\n<li>feat: Add SSL certificate bypass support for self-hosted Confluence instances   by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4219\">https://github.com/Mintplex-Labs/anything-llm/pull/4219</a>\n</li>\n<li>dev build with new <code>epub2</code> build target and remove patch work by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4694\">https://github.com/Mintplex-Labs/anything-llm/pull/4694</a>\n</li>\n<li>docs(zh-TW): correct traditional Chinese translations in home section by @ascodeasice in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4702\">https://github.com/Mintplex-Labs/anything-llm/pull/4702</a>\n</li>\n<li>docs(i18n): Complete French translations by @raphael-bynome in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4697\">https://github.com/Mintplex-Labs/anything-llm/pull/4697</a>\n</li>\n<li>Store Chat Prompt Input Value in Local Storage by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4680\">https://github.com/Mintplex-Labs/anything-llm/pull/4680</a>\n</li>\n<li>Migrate to react router createBrowserRouter by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4693\">https://github.com/Mintplex-Labs/anything-llm/pull/4693</a>\n</li>\n<li>fixed empty scroll track in citations dropdown by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4685\">https://github.com/Mintplex-Labs/anything-llm/pull/4685</a>\n</li>\n<li>Modify ChromaCloud provider to check base limitations of chroma cloud before upsert to prevent 422 by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4705\">https://github.com/Mintplex-Labs/anything-llm/pull/4705</a>\n</li>\n<li>Improve MCP functionality by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4709\">https://github.com/Mintplex-Labs/anything-llm/pull/4709</a>\n</li>\n<li>Patch dev pupeeteer crash for MacOS 15 by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4713\">https://github.com/Mintplex-Labs/anything-llm/pull/4713</a>\n</li>\n<li>Fix broken citations in Zilliz Cloud by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4716\">https://github.com/Mintplex-Labs/anything-llm/pull/4716</a>\n</li>\n<li>Fix similarity score not showing in citation UI for Astra, Qdrant, Weaviate by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4718\">https://github.com/Mintplex-Labs/anything-llm/pull/4718</a>\n</li>\n<li>Dell model capability patch by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4719\">https://github.com/Mintplex-Labs/anything-llm/pull/4719</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@aeromech-1 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4545\">https://github.com/Mintplex-Labs/anything-llm/pull/4545</a>\n</li>\n<li>@AdeboyeDN made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4570\">https://github.com/Mintplex-Labs/anything-llm/pull/4570</a>\n</li>\n<li>@jonathanortega2023 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4568\">https://github.com/Mintplex-Labs/anything-llm/pull/4568</a>\n</li>\n<li>@alexbarron made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4623\">https://github.com/Mintplex-Labs/anything-llm/pull/4623</a>\n</li>\n<li>@chetan made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4651\">https://github.com/Mintplex-Labs/anything-llm/pull/4651</a>\n</li>\n<li>@fchange made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3361\">https://github.com/Mintplex-Labs/anything-llm/pull/3361</a>\n</li>\n<li>@ascodeasice made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4702\">https://github.com/Mintplex-Labs/anything-llm/pull/4702</a>\n</li>\n<li>@raphael-bynome made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4697\">https://github.com/Mintplex-Labs/anything-llm/pull/4697</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.0...v1.9.1\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.9.0...v1.9.1</a></p>\n","assets":[]},{"id":253490461,"tag":"v1.9.0","author":"timothycarambat","name":"AnythingLLM v1.9.0","draft":false,"prerelease":false,"createdAt":"2025-10-09T22:11:59Z","publishedAt":"2025-10-09T22:20:12Z","markdown":"## `@agent` Overhaul & streaming ⚡️️\r\n\r\n<video src=\"https://github.com/user-attachments/assets/fbbfab37-e1b0-442b-b7d4-277aacfcf9bb\"></video>\r\n\r\nWhen anythingllm first launched, the word \"agent\" was not in the vocabulary of the LLM world. Agents are quickly becoming the standard for building AI applications and also the core experience for interacting with LLMs.\r\n\r\nFor too long, due to the complexity of building agents, spotty tool call support, models that can't even use tools and more nerd stuff, we often had to settle an experience that was not really fun to use since 99% of the time you were just looking at loading spinners waiting for the response.\r\n\r\n### The new agent experience is now here\r\n\r\nStreams tool calls and responses in real time (all providers, all models)\r\nAgents can now real-time download and ingest files from the web (eg: link to PDF, excel, csv). Anything you would use a document can be read in real time by the agent from the web.\r\n\r\n### Upcoming:\r\n- Agent real-time API calling without agent flows\r\n- Agent image understanding\r\n- Agent system prompt passthrough + user context awareness\r\n- Realtime file searching cross-platform default skill\r\n\r\n## Notable Improvements: 🚀\r\n * All models and providers now support agentic streaming\r\n * Microsoft Foundry Local integration\r\n * Ephemerally scrape/download any web-resource via agent or uploader\r\n\r\n## What's Changed\r\n* Allow default users to reorder workspaces by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4292\r\n* Export image support for JSON and JSONL by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4359\r\n* Fix: missing edit icon for prompts by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/4344\r\n* feat(i18n): add missing Portuguese (Brazil) translations by @beckeryuri in https://github.com/Mintplex-Labs/anything-llm/pull/4328\r\n* feat: Implement CometAPI integration for chat completions and model m… by @TensorNull in https://github.com/Mintplex-Labs/anything-llm/pull/4379\r\n* Resize chat textarea on paste by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4369\r\n* update save file agent text by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4389\r\n* Added metadata parameter to document/upload, document/upload/{folderName}, and document/upload-link by @jstawski in https://github.com/Mintplex-Labs/anything-llm/pull/4342\r\n* Add support for `SIMPLE_SSO_NO_LOGIN_REDIRECT` config setting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4394\r\n* patch folder name GET request response by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4395\r\n* Add User-Agent header on the requests sent by Generic OpenAI providers. by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4393\r\n* Report sources in API responses on finalized chunk by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4396\r\n* Allow user to specify args for chromium process so they dont need SYS_ADMIN on container. by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4397\r\n* API request delay for Generic OpenAI embedding engine by @chaserhkj in https://github.com/Mintplex-Labs/anything-llm/pull/4317\r\n* Enhanced Chat Embed History View by @MateKristof in https://github.com/Mintplex-Labs/anything-llm/pull/4281\r\n* Ignore hasOwnProperty linting errors by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4406\r\n* Migrate OpenAI LLM provider to use Responses API by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4404\r\n* Update the timeout value on all stream-timeout providers: by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4412\r\n* [BUGFIX] Update Dell Pro AI Studio Default URL by @spencerbull in https://github.com/Mintplex-Labs/anything-llm/pull/4433\r\n* Add PostgreSQL vector extension in createTableIfNotExists function by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4430\r\n* fix: resolve Firefox search icon overlapping placeholder text by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4390\r\n* Refactor Class Name Logging by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4426\r\n* Change incorrect notation of Weaviate to PG Vector in env.example by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4439\r\n* Enable custom HTTP response timeout for ollama by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4448\r\n* fix: youtube transcript collector not work well with non en or non asr caption by @AoiYamada in https://github.com/Mintplex-Labs/anything-llm/pull/4442\r\n* Add HTTP request/response logging middleware for development mode by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4425\r\n* Sanitize Metadata Before PG Vector Database Insertion by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4434\r\n* New Default System Prompt Variables (User ID, Workspace ID, & Workspace Name) by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4414\r\n* Apply renderer from chat widget history to workspace chats by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4456\r\n* Patch OpenAI metrics by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4458\r\n* fix(uiux): correct typo in System Prompt description text by @vansh2408 in https://github.com/Mintplex-Labs/anything-llm/pull/4461\r\n* Enable real-time agent tool call streaming for all providers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4279\r\n* Add stream options to Gemini LLM for usage tracking by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4466\r\n* Fetch, Parse, and Create Documents for Statically Hosted Files by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4398\r\n* Migrate OpenAI Agent to use ResponsesAPI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4467\r\n* Microsoft Foundry Local LLM provider & agent provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4435\r\n* Model context limit auto-detection for LM Studio and Ollama LLM Providers by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4468\r\n* Sync models from remote for FireworksAI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4475\r\n* Render html optional by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4478\r\n* Adding AnythingLLM Helm Chart by @sculley in https://github.com/Mintplex-Labs/anything-llm/pull/4484\r\n* Reimplement Cohere models for basic chat by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4489\r\n* Tooltips for workspace and threads by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4500\r\n* Improve URL handler for collector processes by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4504\r\n* Migrate gemini agents away from `Untooled` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4505\r\n* Update .gitignore by @jaynedoezy-web in https://github.com/Mintplex-Labs/anything-llm/pull/4507\r\n* refactor: change naming - contextwarpper to authprovider #4510 by @Guru6163 in https://github.com/Mintplex-Labs/anything-llm/pull/4511\r\n* fix label for chunk length setting by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4515\r\n* Fix: File pulling fails with uppercase URL characters by @angelplusultra in https://github.com/Mintplex-Labs/anything-llm/pull/4516\r\n\r\n## New Contributors\r\n* @beckeryuri made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4328\r\n* @TensorNull made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4379\r\n* @jstawski made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4342\r\n* @angelplusultra made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4393\r\n* @chaserhkj made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4317\r\n* @MateKristof made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4281\r\n* @spencerbull made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4433\r\n* @AoiYamada made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4442\r\n* @vansh2408 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4461\r\n* @sculley made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4484\r\n* @jaynedoezy-web made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4507\r\n* @Guru6163 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4511\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.5...v1.9.0","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">\n<code>@agent</code> Overhaul &amp; streaming ⚡️️</h2><a id=\"user-content-agent-overhaul--streaming-️️\" class=\"anchor\" aria-label=\"Permalink: @agent Overhaul &amp; streaming ⚡️️\" href=\"#agent-overhaul--streaming-️️\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p></p>\n<p>When anythingllm first launched, the word \"agent\" was not in the vocabulary of the LLM world. Agents are quickly becoming the standard for building AI applications and also the core experience for interacting with LLMs.</p>\n<p>For too long, due to the complexity of building agents, spotty tool call support, models that can't even use tools and more nerd stuff, we often had to settle an experience that was not really fun to use since 99% of the time you were just looking at loading spinners waiting for the response.</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">The new agent experience is now here</h3><a id=\"user-content-the-new-agent-experience-is-now-here\" class=\"anchor\" aria-label=\"Permalink: The new agent experience is now here\" href=\"#the-new-agent-experience-is-now-here\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Streams tool calls and responses in real time (all providers, all models)\nAgents can now real-time download and ingest files from the web (eg: link to PDF, excel, csv). Anything you would use a document can be read in real time by the agent from the web.</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Upcoming:</h3><a id=\"user-content-upcoming\" class=\"anchor\" aria-label=\"Permalink: Upcoming:\" href=\"#upcoming\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Agent real-time API calling without agent flows</li>\n<li>Agent image understanding</li>\n<li>Agent system prompt passthrough + user context awareness</li>\n<li>Realtime file searching cross-platform default skill</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Improvements: 🚀</h2><a id=\"user-content-notable-improvements-\" class=\"anchor\" aria-label=\"Permalink: Notable Improvements: 🚀\" href=\"#notable-improvements-\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>All models and providers now support agentic streaming</li>\n<li>Microsoft Foundry Local integration</li>\n<li>Ephemerally scrape/download any web-resource via agent or uploader</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Allow default users to reorder workspaces by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4292\">https://github.com/Mintplex-Labs/anything-llm/pull/4292</a>\n</li>\n<li>Export image support for JSON and JSONL by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4359\">https://github.com/Mintplex-Labs/anything-llm/pull/4359</a>\n</li>\n<li>Fix: missing edit icon for prompts by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4344\">https://github.com/Mintplex-Labs/anything-llm/pull/4344</a>\n</li>\n<li>feat(i18n): add missing Portuguese (Brazil) translations by @beckeryuri in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4328\">https://github.com/Mintplex-Labs/anything-llm/pull/4328</a>\n</li>\n<li>feat: Implement CometAPI integration for chat completions and model m… by @TensorNull in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4379\">https://github.com/Mintplex-Labs/anything-llm/pull/4379</a>\n</li>\n<li>Resize chat textarea on paste by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4369\">https://github.com/Mintplex-Labs/anything-llm/pull/4369</a>\n</li>\n<li>update save file agent text by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4389\">https://github.com/Mintplex-Labs/anything-llm/pull/4389</a>\n</li>\n<li>Added metadata parameter to document/upload, document/upload/{folderName}, and document/upload-link by @jstawski in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4342\">https://github.com/Mintplex-Labs/anything-llm/pull/4342</a>\n</li>\n<li>Add support for <code>SIMPLE_SSO_NO_LOGIN_REDIRECT</code> config setting by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4394\">https://github.com/Mintplex-Labs/anything-llm/pull/4394</a>\n</li>\n<li>patch folder name GET request response by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4395\">https://github.com/Mintplex-Labs/anything-llm/pull/4395</a>\n</li>\n<li>Add User-Agent header on the requests sent by Generic OpenAI providers. by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4393\">https://github.com/Mintplex-Labs/anything-llm/pull/4393</a>\n</li>\n<li>Report sources in API responses on finalized chunk by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4396\">https://github.com/Mintplex-Labs/anything-llm/pull/4396</a>\n</li>\n<li>Allow user to specify args for chromium process so they dont need SYS_ADMIN on container. by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4397\">https://github.com/Mintplex-Labs/anything-llm/pull/4397</a>\n</li>\n<li>API request delay for Generic OpenAI embedding engine by @chaserhkj in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4317\">https://github.com/Mintplex-Labs/anything-llm/pull/4317</a>\n</li>\n<li>Enhanced Chat Embed History View by @MateKristof in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4281\">https://github.com/Mintplex-Labs/anything-llm/pull/4281</a>\n</li>\n<li>Ignore hasOwnProperty linting errors by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4406\">https://github.com/Mintplex-Labs/anything-llm/pull/4406</a>\n</li>\n<li>Migrate OpenAI LLM provider to use Responses API by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4404\">https://github.com/Mintplex-Labs/anything-llm/pull/4404</a>\n</li>\n<li>Update the timeout value on all stream-timeout providers: by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4412\">https://github.com/Mintplex-Labs/anything-llm/pull/4412</a>\n</li>\n<li>[BUGFIX] Update Dell Pro AI Studio Default URL by @spencerbull in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4433\">https://github.com/Mintplex-Labs/anything-llm/pull/4433</a>\n</li>\n<li>Add PostgreSQL vector extension in createTableIfNotExists function by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4430\">https://github.com/Mintplex-Labs/anything-llm/pull/4430</a>\n</li>\n<li>fix: resolve Firefox search icon overlapping placeholder text by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4390\">https://github.com/Mintplex-Labs/anything-llm/pull/4390</a>\n</li>\n<li>Refactor Class Name Logging by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4426\">https://github.com/Mintplex-Labs/anything-llm/pull/4426</a>\n</li>\n<li>Change incorrect notation of Weaviate to PG Vector in env.example by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4439\">https://github.com/Mintplex-Labs/anything-llm/pull/4439</a>\n</li>\n<li>Enable custom HTTP response timeout for ollama by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4448\">https://github.com/Mintplex-Labs/anything-llm/pull/4448</a>\n</li>\n<li>fix: youtube transcript collector not work well with non en or non asr caption by @AoiYamada in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4442\">https://github.com/Mintplex-Labs/anything-llm/pull/4442</a>\n</li>\n<li>Add HTTP request/response logging middleware for development mode by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4425\">https://github.com/Mintplex-Labs/anything-llm/pull/4425</a>\n</li>\n<li>Sanitize Metadata Before PG Vector Database Insertion by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4434\">https://github.com/Mintplex-Labs/anything-llm/pull/4434</a>\n</li>\n<li>New Default System Prompt Variables (User ID, Workspace ID, &amp; Workspace Name) by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4414\">https://github.com/Mintplex-Labs/anything-llm/pull/4414</a>\n</li>\n<li>Apply renderer from chat widget history to workspace chats by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4456\">https://github.com/Mintplex-Labs/anything-llm/pull/4456</a>\n</li>\n<li>Patch OpenAI metrics by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4458\">https://github.com/Mintplex-Labs/anything-llm/pull/4458</a>\n</li>\n<li>fix(uiux): correct typo in System Prompt description text by @vansh2408 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4461\">https://github.com/Mintplex-Labs/anything-llm/pull/4461</a>\n</li>\n<li>Enable real-time agent tool call streaming for all providers by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4279\">https://github.com/Mintplex-Labs/anything-llm/pull/4279</a>\n</li>\n<li>Add stream options to Gemini LLM for usage tracking by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4466\">https://github.com/Mintplex-Labs/anything-llm/pull/4466</a>\n</li>\n<li>Fetch, Parse, and Create Documents for Statically Hosted Files by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4398\">https://github.com/Mintplex-Labs/anything-llm/pull/4398</a>\n</li>\n<li>Migrate OpenAI Agent to use ResponsesAPI by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4467\">https://github.com/Mintplex-Labs/anything-llm/pull/4467</a>\n</li>\n<li>Microsoft Foundry Local LLM provider &amp; agent provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4435\">https://github.com/Mintplex-Labs/anything-llm/pull/4435</a>\n</li>\n<li>Model context limit auto-detection for LM Studio and Ollama LLM Providers by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4468\">https://github.com/Mintplex-Labs/anything-llm/pull/4468</a>\n</li>\n<li>Sync models from remote for FireworksAI by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4475\">https://github.com/Mintplex-Labs/anything-llm/pull/4475</a>\n</li>\n<li>Render html optional by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4478\">https://github.com/Mintplex-Labs/anything-llm/pull/4478</a>\n</li>\n<li>Adding AnythingLLM Helm Chart by @sculley in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4484\">https://github.com/Mintplex-Labs/anything-llm/pull/4484</a>\n</li>\n<li>Reimplement Cohere models for basic chat by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4489\">https://github.com/Mintplex-Labs/anything-llm/pull/4489</a>\n</li>\n<li>Tooltips for workspace and threads by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4500\">https://github.com/Mintplex-Labs/anything-llm/pull/4500</a>\n</li>\n<li>Improve URL handler for collector processes by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4504\">https://github.com/Mintplex-Labs/anything-llm/pull/4504</a>\n</li>\n<li>Migrate gemini agents away from <code>Untooled</code> by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4505\">https://github.com/Mintplex-Labs/anything-llm/pull/4505</a>\n</li>\n<li>Update .gitignore by @jaynedoezy-web in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4507\">https://github.com/Mintplex-Labs/anything-llm/pull/4507</a>\n</li>\n<li>refactor: change naming - contextwarpper to authprovider #4510 by @Guru6163 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4511\">https://github.com/Mintplex-Labs/anything-llm/pull/4511</a>\n</li>\n<li>fix label for chunk length setting by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4515\">https://github.com/Mintplex-Labs/anything-llm/pull/4515</a>\n</li>\n<li>Fix: File pulling fails with uppercase URL characters by @angelplusultra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4516\">https://github.com/Mintplex-Labs/anything-llm/pull/4516</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@beckeryuri made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4328\">https://github.com/Mintplex-Labs/anything-llm/pull/4328</a>\n</li>\n<li>@TensorNull made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4379\">https://github.com/Mintplex-Labs/anything-llm/pull/4379</a>\n</li>\n<li>@jstawski made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4342\">https://github.com/Mintplex-Labs/anything-llm/pull/4342</a>\n</li>\n<li>@angelplusultra made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4393\">https://github.com/Mintplex-Labs/anything-llm/pull/4393</a>\n</li>\n<li>@chaserhkj made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4317\">https://github.com/Mintplex-Labs/anything-llm/pull/4317</a>\n</li>\n<li>@MateKristof made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4281\">https://github.com/Mintplex-Labs/anything-llm/pull/4281</a>\n</li>\n<li>@spencerbull made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4433\">https://github.com/Mintplex-Labs/anything-llm/pull/4433</a>\n</li>\n<li>@AoiYamada made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4442\">https://github.com/Mintplex-Labs/anything-llm/pull/4442</a>\n</li>\n<li>@vansh2408 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4461\">https://github.com/Mintplex-Labs/anything-llm/pull/4461</a>\n</li>\n<li>@sculley made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4484\">https://github.com/Mintplex-Labs/anything-llm/pull/4484</a>\n</li>\n<li>@jaynedoezy-web made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4507\">https://github.com/Mintplex-Labs/anything-llm/pull/4507</a>\n</li>\n<li>@Guru6163 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4511\">https://github.com/Mintplex-Labs/anything-llm/pull/4511</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.5...v1.9.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.5...v1.9.0</a></p>\n","assets":[]},{"id":240123881,"tag":"v1.8.5","author":"timothycarambat","name":"AnythingLLM v1.8.5 🎉  Mobile support + RAG improvements","draft":false,"prerelease":false,"createdAt":"2025-08-14T20:40:57Z","publishedAt":"2025-08-15T00:42:56Z","markdown":"# AnythingLLM v1.8.5 is live\r\n\r\n\r\n## Notable Changes\r\n\r\n### Mobile support\r\n\r\nNow, currently under [Experimental features](https://docs.anythingllm.com/beta-preview/enable-feature), you can connect the [AnythingLLM Mobile App - Android Beta](https://anythingllm.com/mobile) to your instance to seamlessly blend an on-device and off-device experience. Leverage your instance Agent Skills and flows all within a single unified interface!\r\n\r\n\r\n### Chat with documents has been overhauled\r\n\r\nhttps://github.com/user-attachments/assets/0e4ab18d-fb58-480a-94f5-907664dd8f3f\r\n\r\nWhen we first built AnythingLLM, the average context window was 4K - hardly anything to fit a full document. So we decided to always be RAG first. This has its drawbacks since RAG is _semantically_ dependent on asking questions about content in the document. This leads to poor results for \"Summarize this document,\" only to be told by the document, \"what are you talking about\".\r\n\r\nWell, now we have the best of both worlds. Documents are scoped to a workspace thread & user and we will attempt to use the full document text when possible and your model can support it. If you overflow this amount, we can then ask you to embed the document so you can unlock that long-term memory.\r\n\r\n<img width=\"1394\" height=\"906\" alt=\"context-warning\" src=\"https://github.com/user-attachments/assets/c28c24d9-a696-4ff6-8d77-7ca708592071\" />\r\n\r\nYou can also easily manage and see your context window to remove files that are no longer relevant, but retain the conversation history.\r\n<img width=\"1804\" height=\"732\" alt=\"manage-attached-docs\" src=\"https://github.com/user-attachments/assets/566c6cbd-e67e-4339-82c6-61dfbddde7fd\" />\r\n\r\n\r\nYou can also still embed files directly in the workspace file manager too :)\r\n\r\n\r\n\r\n\r\n## What's Changed\r\n* Add `model` field parameter for generic OpenAI TTS by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4171\r\n* Clear cached docs on text splitter changes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4163\r\n* Update BARE_METAL.md by @buraktopalyn in https://github.com/Mintplex-Labs/anything-llm/pull/4175\r\n* run jest by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4177\r\n* Moonshot AI LLM & agent provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4178\r\n* Fix multimodal chats via openai compat api by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4135\r\n* Native Embedder model selection (incl: Multilingual support) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3835\r\n* fix: correct some typos and grammatical errors in translation strings and index.jsx by @antonharder in https://github.com/Mintplex-Labs/anything-llm/pull/4195\r\n* Modify the PostgreSQL SQL connector to support querying tables from schemas other than the default public schema. by @romanwu10 in https://github.com/Mintplex-Labs/anything-llm/pull/4202\r\n* Fix app version metrics endpoint by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4209\r\n* Update `writeToServerDocuments` to take config object by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4213\r\n* [Chore]: `sendCommand` non positional call signature by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4218\r\n* Update check for `validFuncCall` to only check required args and for undefined options by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4214\r\n* fix: API export-chats endpoint function import error by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4220\r\n* STT append spoken text by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4216\r\n* Mobile sync support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4173\r\n* Add custom JWT TTL by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4234\r\n* Fix password hint text by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4235\r\n* Update common.js Hebrew language update by @start-life in https://github.com/Mintplex-Labs/anything-llm/pull/4241\r\n* docs(i18n): Complete missing Spanish translations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4263\r\n* feat: add Romanian translation by @dpvue in https://github.com/Mintplex-Labs/anything-llm/pull/4247\r\n* Workspace Chat with documents overhaul by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4261\r\n* feat: Add Exa as a Search Provider by @naaa760 in https://github.com/Mintplex-Labs/anything-llm/pull/4258\r\n* Update common.js by @dpvue in https://github.com/Mintplex-Labs/anything-llm/pull/4278\r\n* Chroma Cloud vector db provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4273\r\n* Update Security UI to match all other Settings by @AshikaAnand12 in https://github.com/Mintplex-Labs/anything-llm/pull/4274\r\n\r\n## New Contributors\r\n* @buraktopalyn made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4175\r\n* @antonharder made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4195\r\n* @romanwu10 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4202\r\n* @naaa760 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4220\r\n* @start-life made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4241\r\n* @dpvue made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4247\r\n* @AshikaAnand12 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4274\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.4...v1.8.5","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">AnythingLLM v1.8.5 is live</h1><a id=\"user-content-anythingllm-v185-is-live\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM v1.8.5 is live\" href=\"#anythingllm-v185-is-live\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Changes</h2><a id=\"user-content-notable-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Changes\" href=\"#notable-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Mobile support</h3><a id=\"user-content-mobile-support\" class=\"anchor\" aria-label=\"Permalink: Mobile support\" href=\"#mobile-support\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, currently under <a href=\"https://docs.anythingllm.com/beta-preview/enable-feature\" rel=\"nofollow\">Experimental features</a>, you can connect the <a href=\"https://anythingllm.com/mobile\" rel=\"nofollow\">AnythingLLM Mobile App - Android Beta</a> to your instance to seamlessly blend an on-device and off-device experience. Leverage your instance Agent Skills and flows all within a single unified interface!</p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Chat with documents has been overhauled</h3><a id=\"user-content-chat-with-documents-has-been-overhauled\" class=\"anchor\" aria-label=\"Permalink: Chat with documents has been overhauled\" href=\"#chat-with-documents-has-been-overhauled\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a href=\"https://github.com/user-attachments/assets/0e4ab18d-fb58-480a-94f5-907664dd8f3f\">https://github.com/user-attachments/assets/0e4ab18d-fb58-480a-94f5-907664dd8f3f</a></p>\n<p>When we first built AnythingLLM, the average context window was 4K - hardly anything to fit a full document. So we decided to always be RAG first. This has its drawbacks since RAG is <em>semantically</em> dependent on asking questions about content in the document. This leads to poor results for \"Summarize this document,\" only to be told by the document, \"what are you talking about\".</p>\n<p>Well, now we have the best of both worlds. Documents are scoped to a workspace thread &amp; user and we will attempt to use the full document text when possible and your model can support it. If you overflow this amount, we can then ask you to embed the document so you can unlock that long-term memory.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/c28c24d9-a696-4ff6-8d77-7ca708592071\"><img width=\"1394\" height=\"906\" alt=\"context-warning\" src=\"https://github.com/user-attachments/assets/c28c24d9-a696-4ff6-8d77-7ca708592071\" style=\"max-width: 100%; height: auto; max-height: 906px;\"></a></p>\n<p>You can also easily manage and see your context window to remove files that are no longer relevant, but retain the conversation history.\n<a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/566c6cbd-e67e-4339-82c6-61dfbddde7fd\"><img width=\"1804\" height=\"732\" alt=\"manage-attached-docs\" src=\"https://github.com/user-attachments/assets/566c6cbd-e67e-4339-82c6-61dfbddde7fd\" style=\"max-width: 100%; height: auto; max-height: 732px;\"></a></p>\n<p>You can also still embed files directly in the workspace file manager too :)</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Add <code>model</code> field parameter for generic OpenAI TTS by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4171\">https://github.com/Mintplex-Labs/anything-llm/pull/4171</a>\n</li>\n<li>Clear cached docs on text splitter changes by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4163\">https://github.com/Mintplex-Labs/anything-llm/pull/4163</a>\n</li>\n<li>Update BARE_METAL.md by @buraktopalyn in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4175\">https://github.com/Mintplex-Labs/anything-llm/pull/4175</a>\n</li>\n<li>run jest by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4177\">https://github.com/Mintplex-Labs/anything-llm/pull/4177</a>\n</li>\n<li>Moonshot AI LLM &amp; agent provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4178\">https://github.com/Mintplex-Labs/anything-llm/pull/4178</a>\n</li>\n<li>Fix multimodal chats via openai compat api by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4135\">https://github.com/Mintplex-Labs/anything-llm/pull/4135</a>\n</li>\n<li>Native Embedder model selection (incl: Multilingual support) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3835\">https://github.com/Mintplex-Labs/anything-llm/pull/3835</a>\n</li>\n<li>fix: correct some typos and grammatical errors in translation strings and index.jsx by @antonharder in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4195\">https://github.com/Mintplex-Labs/anything-llm/pull/4195</a>\n</li>\n<li>Modify the PostgreSQL SQL connector to support querying tables from schemas other than the default public schema. by @romanwu10 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4202\">https://github.com/Mintplex-Labs/anything-llm/pull/4202</a>\n</li>\n<li>Fix app version metrics endpoint by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4209\">https://github.com/Mintplex-Labs/anything-llm/pull/4209</a>\n</li>\n<li>Update <code>writeToServerDocuments</code> to take config object by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4213\">https://github.com/Mintplex-Labs/anything-llm/pull/4213</a>\n</li>\n<li>[Chore]: <code>sendCommand</code> non positional call signature by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4218\">https://github.com/Mintplex-Labs/anything-llm/pull/4218</a>\n</li>\n<li>Update check for <code>validFuncCall</code> to only check required args and for undefined options by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4214\">https://github.com/Mintplex-Labs/anything-llm/pull/4214</a>\n</li>\n<li>fix: API export-chats endpoint function import error by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4220\">https://github.com/Mintplex-Labs/anything-llm/pull/4220</a>\n</li>\n<li>STT append spoken text by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4216\">https://github.com/Mintplex-Labs/anything-llm/pull/4216</a>\n</li>\n<li>Mobile sync support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4173\">https://github.com/Mintplex-Labs/anything-llm/pull/4173</a>\n</li>\n<li>Add custom JWT TTL by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4234\">https://github.com/Mintplex-Labs/anything-llm/pull/4234</a>\n</li>\n<li>Fix password hint text by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4235\">https://github.com/Mintplex-Labs/anything-llm/pull/4235</a>\n</li>\n<li>Update common.js Hebrew language update by @start-life in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4241\">https://github.com/Mintplex-Labs/anything-llm/pull/4241</a>\n</li>\n<li>docs(i18n): Complete missing Spanish translations by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4263\">https://github.com/Mintplex-Labs/anything-llm/pull/4263</a>\n</li>\n<li>feat: add Romanian translation by @dpvue in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4247\">https://github.com/Mintplex-Labs/anything-llm/pull/4247</a>\n</li>\n<li>Workspace Chat with documents overhaul by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4261\">https://github.com/Mintplex-Labs/anything-llm/pull/4261</a>\n</li>\n<li>feat: Add Exa as a Search Provider by @naaa760 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4258\">https://github.com/Mintplex-Labs/anything-llm/pull/4258</a>\n</li>\n<li>Update common.js by @dpvue in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4278\">https://github.com/Mintplex-Labs/anything-llm/pull/4278</a>\n</li>\n<li>Chroma Cloud vector db provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4273\">https://github.com/Mintplex-Labs/anything-llm/pull/4273</a>\n</li>\n<li>Update Security UI to match all other Settings by @AshikaAnand12 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4274\">https://github.com/Mintplex-Labs/anything-llm/pull/4274</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@buraktopalyn made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4175\">https://github.com/Mintplex-Labs/anything-llm/pull/4175</a>\n</li>\n<li>@antonharder made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4195\">https://github.com/Mintplex-Labs/anything-llm/pull/4195</a>\n</li>\n<li>@romanwu10 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4202\">https://github.com/Mintplex-Labs/anything-llm/pull/4202</a>\n</li>\n<li>@naaa760 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4220\">https://github.com/Mintplex-Labs/anything-llm/pull/4220</a>\n</li>\n<li>@start-life made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4241\">https://github.com/Mintplex-Labs/anything-llm/pull/4241</a>\n</li>\n<li>@dpvue made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4247\">https://github.com/Mintplex-Labs/anything-llm/pull/4247</a>\n</li>\n<li>@AshikaAnand12 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4274\">https://github.com/Mintplex-Labs/anything-llm/pull/4274</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.4...v1.8.5\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.4...v1.8.5</a></p>\n","assets":[]},{"id":232934165,"tag":"v1.8.4","author":"timothycarambat","name":"AnythingLLM 1.8.4","draft":false,"prerelease":false,"createdAt":"2025-07-16T17:40:39Z","publishedAt":"2025-07-16T18:06:25Z","markdown":"_this is a minor patch update_\r\n\r\n## Notable Changes\r\n\r\n- Workspace & Thread searching now on the sidebar\r\n- SQL Preflight connection validation (finally)\r\n- Sticky codeblock headers while scrolling\r\n- Codeblock max width to prevent long string overflows in the UI\r\n\r\n## What's Changed\r\n* Handle BigInt in message response by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4110\r\n* Configurable message limit for embed chat widget by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4114\r\n* Add ability to search workspace and threads by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4120\r\n* docs(i18n): Complete missing Chinese translations by @zz22558822 in https://github.com/Mintplex-Labs/anything-llm/pull/4123\r\n* Fix chunking/snippet logs for clarity by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4129\r\n* Sticky code block header by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4130\r\n* docs(zh-cn): Update and improve Simplified Chinese translations by @ChenJiahao1 in https://github.com/Mintplex-Labs/anything-llm/pull/4137\r\n* Sanitize youtube transcription file paths by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4148\r\n* Add option to enable encryption on MSSQL Server db by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4134\r\n* Migrate text size menu to embedded tooltip by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4147\r\n* set max codeblock width to prevent overflows by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4157\r\n* SQL preflight connection validation by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4150\r\n\r\n## New Contributors\r\n* @zz22558822 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4123\r\n* @ChenJiahao1 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4137\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.3...v1.8.4","html":"<p><em>this is a minor patch update</em></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Changes</h2><a id=\"user-content-notable-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Changes\" href=\"#notable-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Workspace &amp; Thread searching now on the sidebar</li>\n<li>SQL Preflight connection validation (finally)</li>\n<li>Sticky codeblock headers while scrolling</li>\n<li>Codeblock max width to prevent long string overflows in the UI</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Handle BigInt in message response by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4110\">https://github.com/Mintplex-Labs/anything-llm/pull/4110</a>\n</li>\n<li>Configurable message limit for embed chat widget by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4114\">https://github.com/Mintplex-Labs/anything-llm/pull/4114</a>\n</li>\n<li>Add ability to search workspace and threads by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4120\">https://github.com/Mintplex-Labs/anything-llm/pull/4120</a>\n</li>\n<li>docs(i18n): Complete missing Chinese translations by @zz22558822 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4123\">https://github.com/Mintplex-Labs/anything-llm/pull/4123</a>\n</li>\n<li>Fix chunking/snippet logs for clarity by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4129\">https://github.com/Mintplex-Labs/anything-llm/pull/4129</a>\n</li>\n<li>Sticky code block header by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4130\">https://github.com/Mintplex-Labs/anything-llm/pull/4130</a>\n</li>\n<li>docs(zh-cn): Update and improve Simplified Chinese translations by @ChenJiahao1 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4137\">https://github.com/Mintplex-Labs/anything-llm/pull/4137</a>\n</li>\n<li>Sanitize youtube transcription file paths by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4148\">https://github.com/Mintplex-Labs/anything-llm/pull/4148</a>\n</li>\n<li>Add option to enable encryption on MSSQL Server db by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4134\">https://github.com/Mintplex-Labs/anything-llm/pull/4134</a>\n</li>\n<li>Migrate text size menu to embedded tooltip by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4147\">https://github.com/Mintplex-Labs/anything-llm/pull/4147</a>\n</li>\n<li>set max codeblock width to prevent overflows by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4157\">https://github.com/Mintplex-Labs/anything-llm/pull/4157</a>\n</li>\n<li>SQL preflight connection validation by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4150\">https://github.com/Mintplex-Labs/anything-llm/pull/4150</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@zz22558822 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4123\">https://github.com/Mintplex-Labs/anything-llm/pull/4123</a>\n</li>\n<li>@ChenJiahao1 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4137\">https://github.com/Mintplex-Labs/anything-llm/pull/4137</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.3...v1.8.4\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.3...v1.8.4</a></p>\n","assets":[]},{"id":231253181,"tag":"v1.8.3","author":"timothycarambat","name":"AnythingLLM v1.8.3","draft":false,"prerelease":false,"createdAt":"2025-07-09T19:17:56Z","publishedAt":"2025-07-09T19:23:35Z","markdown":"# AnythingLLM 1.8.3 is live!\r\n\r\n## News\r\nDont forget to sign up for the [AnythingLLM mobile beta](https://anythingllm.com/mobile)!\r\n- Run small LLMs on device, full on-device RAG, agent tooling, and more. Fully private and on-device\r\n- device-to-device sync between mobile and desktop clients over local networks\r\n\r\n## Notable Desktop Changes\r\n- [**Built in Browser Tool**](https://docs.anythingllm.com/features/browser-tool) You can now scrape private, authenticated, or otherwise gated context for collecting or use during agent web-scraping or agent flows!\r\n- [See the full changelog here](https://docs.anythingllm.com/changelog/v1.8.3)\r\n\r\n## Notable updates and fixes\r\n- Easily publish Agent Flows, Slash Commands, and System Prompts to the [AnythingLLM Community Hub](https://hub.anythingllm.com)\r\n- Patched YouTube transcript collector since it was failing due to Google API changes\r\n\r\n## What's Changed\r\n* Flag to disable login UI and endpoints for credentialed auth by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3984\r\n* Fix Typos in Comments and Documentation by @kilavvy in https://github.com/Mintplex-Labs/anything-llm/pull/3987\r\n* Fix Typos in MetaGenerator.js Documentation Comments by @vtjl10 in https://github.com/Mintplex-Labs/anything-llm/pull/3993\r\n* Fix Typo in Milvus Provider and Update Comment in Prisma Schema by @zeevick10 in https://github.com/Mintplex-Labs/anything-llm/pull/4003\r\n* Fix typos in blog post example and save-file-browser plugin by @maximevtush in https://github.com/Mintplex-Labs/anything-llm/pull/4009\r\n* Publish system prompts to hub by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3976\r\n* Fix Typos in Comments and Documentation by @leopardracer in https://github.com/Mintplex-Labs/anything-llm/pull/4015\r\n* Show app version in system settings sidebar by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4044\r\n* Added missing German translations by @AlefAlfa in https://github.com/Mintplex-Labs/anything-llm/pull/4029\r\n* Fix prompt, model, and temperature overrides in embed chat widget by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4036\r\n* Publish agent flows to hub by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4001\r\n* Publish slash commands to hub by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4019\r\n* Added Estonian translation by @Tarkva in https://github.com/Mintplex-Labs/anything-llm/pull/4067\r\n* Move show scrollbar option to chat settings by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4078\r\n* Update common.js spellcheck for zh_TW by @martin0258 in https://github.com/Mintplex-Labs/anything-llm/pull/4074\r\n* Add option to disable streaming via env for generic openai provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4079\r\n* LMStudio 0 value embeddings patch by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4084\r\n* Allow static defined prompt variables to be accessed by any authorized user by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4086\r\n* Add hint for chats in query mode by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4076\r\n* fix to support: feat2864 - using local credentials file with Amazon Bedrock by @nonatofabio in https://github.com/Mintplex-Labs/anything-llm/pull/3986\r\n* Fix broken YT scraping with YT API by @bobbercheng in https://github.com/Mintplex-Labs/anything-llm/pull/4005\r\n* Patch tokenizer race condition bug by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4091\r\n* Polish translations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4100\r\n* feat: Add Korean (ko) locale translations by @ux-builder in https://github.com/Mintplex-Labs/anything-llm/pull/4096\r\n* update typo in language key files by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/4101\r\n* Fix/drupal wiki (improve table & url handling) by @rexjohannes in https://github.com/Mintplex-Labs/anything-llm/pull/4097\r\n* Fix score reporting for Milvus, Zilliz, and Pinecone vector databases by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/4106\r\n\r\n## New Contributors\r\n* @kilavvy made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3987\r\n* @vtjl10 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3993\r\n* @zeevick10 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4003\r\n* @maximevtush made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4009\r\n* @AlefAlfa made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4029\r\n* @Tarkva made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4067\r\n* @martin0258 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4074\r\n* @nonatofabio made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3986\r\n* @bobbercheng made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/4005\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.2...v1.8.3","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">AnythingLLM 1.8.3 is live!</h1><a id=\"user-content-anythingllm-183-is-live\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM 1.8.3 is live!\" href=\"#anythingllm-183-is-live\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">News</h2><a id=\"user-content-news\" class=\"anchor\" aria-label=\"Permalink: News\" href=\"#news\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Dont forget to sign up for the <a href=\"https://anythingllm.com/mobile\" rel=\"nofollow\">AnythingLLM mobile beta</a>!</p>\n<ul>\n<li>Run small LLMs on device, full on-device RAG, agent tooling, and more. Fully private and on-device</li>\n<li>device-to-device sync between mobile and desktop clients over local networks</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Desktop Changes</h2><a id=\"user-content-notable-desktop-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Desktop Changes\" href=\"#notable-desktop-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>\n<a href=\"https://docs.anythingllm.com/features/browser-tool\" rel=\"nofollow\"><strong>Built in Browser Tool</strong></a> You can now scrape private, authenticated, or otherwise gated context for collecting or use during agent web-scraping or agent flows!</li>\n<li><a href=\"https://docs.anythingllm.com/changelog/v1.8.3\" rel=\"nofollow\">See the full changelog here</a></li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable updates and fixes</h2><a id=\"user-content-notable-updates-and-fixes\" class=\"anchor\" aria-label=\"Permalink: Notable updates and fixes\" href=\"#notable-updates-and-fixes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Easily publish Agent Flows, Slash Commands, and System Prompts to the <a href=\"https://hub.anythingllm.com\" rel=\"nofollow\">AnythingLLM Community Hub</a>\n</li>\n<li>Patched YouTube transcript collector since it was failing due to Google API changes</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Flag to disable login UI and endpoints for credentialed auth by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3984\">https://github.com/Mintplex-Labs/anything-llm/pull/3984</a>\n</li>\n<li>Fix Typos in Comments and Documentation by @kilavvy in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3987\">https://github.com/Mintplex-Labs/anything-llm/pull/3987</a>\n</li>\n<li>Fix Typos in MetaGenerator.js Documentation Comments by @vtjl10 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3993\">https://github.com/Mintplex-Labs/anything-llm/pull/3993</a>\n</li>\n<li>Fix Typo in Milvus Provider and Update Comment in Prisma Schema by @zeevick10 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4003\">https://github.com/Mintplex-Labs/anything-llm/pull/4003</a>\n</li>\n<li>Fix typos in blog post example and save-file-browser plugin by @maximevtush in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4009\">https://github.com/Mintplex-Labs/anything-llm/pull/4009</a>\n</li>\n<li>Publish system prompts to hub by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3976\">https://github.com/Mintplex-Labs/anything-llm/pull/3976</a>\n</li>\n<li>Fix Typos in Comments and Documentation by @leopardracer in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4015\">https://github.com/Mintplex-Labs/anything-llm/pull/4015</a>\n</li>\n<li>Show app version in system settings sidebar by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4044\">https://github.com/Mintplex-Labs/anything-llm/pull/4044</a>\n</li>\n<li>Added missing German translations by @AlefAlfa in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4029\">https://github.com/Mintplex-Labs/anything-llm/pull/4029</a>\n</li>\n<li>Fix prompt, model, and temperature overrides in embed chat widget by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4036\">https://github.com/Mintplex-Labs/anything-llm/pull/4036</a>\n</li>\n<li>Publish agent flows to hub by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4001\">https://github.com/Mintplex-Labs/anything-llm/pull/4001</a>\n</li>\n<li>Publish slash commands to hub by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4019\">https://github.com/Mintplex-Labs/anything-llm/pull/4019</a>\n</li>\n<li>Added Estonian translation by @Tarkva in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4067\">https://github.com/Mintplex-Labs/anything-llm/pull/4067</a>\n</li>\n<li>Move show scrollbar option to chat settings by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4078\">https://github.com/Mintplex-Labs/anything-llm/pull/4078</a>\n</li>\n<li>Update common.js spellcheck for zh_TW by @martin0258 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4074\">https://github.com/Mintplex-Labs/anything-llm/pull/4074</a>\n</li>\n<li>Add option to disable streaming via env for generic openai provider by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4079\">https://github.com/Mintplex-Labs/anything-llm/pull/4079</a>\n</li>\n<li>LMStudio 0 value embeddings patch by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4084\">https://github.com/Mintplex-Labs/anything-llm/pull/4084</a>\n</li>\n<li>Allow static defined prompt variables to be accessed by any authorized user by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4086\">https://github.com/Mintplex-Labs/anything-llm/pull/4086</a>\n</li>\n<li>Add hint for chats in query mode by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4076\">https://github.com/Mintplex-Labs/anything-llm/pull/4076</a>\n</li>\n<li>fix to support: feat2864 - using local credentials file with Amazon Bedrock by @nonatofabio in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3986\">https://github.com/Mintplex-Labs/anything-llm/pull/3986</a>\n</li>\n<li>Fix broken YT scraping with YT API by @bobbercheng in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4005\">https://github.com/Mintplex-Labs/anything-llm/pull/4005</a>\n</li>\n<li>Patch tokenizer race condition bug by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4091\">https://github.com/Mintplex-Labs/anything-llm/pull/4091</a>\n</li>\n<li>Polish translations by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4100\">https://github.com/Mintplex-Labs/anything-llm/pull/4100</a>\n</li>\n<li>feat: Add Korean (ko) locale translations by @ux-builder in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4096\">https://github.com/Mintplex-Labs/anything-llm/pull/4096</a>\n</li>\n<li>update typo in language key files by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4101\">https://github.com/Mintplex-Labs/anything-llm/pull/4101</a>\n</li>\n<li>Fix/drupal wiki (improve table &amp; url handling) by @rexjohannes in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4097\">https://github.com/Mintplex-Labs/anything-llm/pull/4097</a>\n</li>\n<li>Fix score reporting for Milvus, Zilliz, and Pinecone vector databases by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4106\">https://github.com/Mintplex-Labs/anything-llm/pull/4106</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@kilavvy made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3987\">https://github.com/Mintplex-Labs/anything-llm/pull/3987</a>\n</li>\n<li>@vtjl10 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3993\">https://github.com/Mintplex-Labs/anything-llm/pull/3993</a>\n</li>\n<li>@zeevick10 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4003\">https://github.com/Mintplex-Labs/anything-llm/pull/4003</a>\n</li>\n<li>@maximevtush made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4009\">https://github.com/Mintplex-Labs/anything-llm/pull/4009</a>\n</li>\n<li>@AlefAlfa made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4029\">https://github.com/Mintplex-Labs/anything-llm/pull/4029</a>\n</li>\n<li>@Tarkva made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4067\">https://github.com/Mintplex-Labs/anything-llm/pull/4067</a>\n</li>\n<li>@martin0258 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4074\">https://github.com/Mintplex-Labs/anything-llm/pull/4074</a>\n</li>\n<li>@nonatofabio made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3986\">https://github.com/Mintplex-Labs/anything-llm/pull/3986</a>\n</li>\n<li>@bobbercheng made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/4005\">https://github.com/Mintplex-Labs/anything-llm/pull/4005</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.2...v1.8.3\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.2...v1.8.3</a></p>\n","assets":[]},{"id":224464415,"tag":"v1.8.2","author":"timothycarambat","name":"AnythingLLM v1.8.2","draft":false,"prerelease":false,"createdAt":"2025-06-10T16:27:44Z","publishedAt":"2025-06-10T23:59:29Z","markdown":"# AnythingLLM v1.8.2 is LIVE!\r\n\r\n## Other news\r\n\r\nWe were featured on stage at Microsoft Build (how cool???)\r\n\r\n![1747677767492](https://github.com/user-attachments/assets/1e77b3aa-8232-4050-b471-d2eed68ee3f6)\r\n\r\n## Notable Changes\r\n\r\n### Model swap in chat\r\nYou can now easily swap model or provider in the middle of chatting via `cmd/Ctrl + Shift + L` to show a tooltip menu to easily swap models without changing screens\r\n\r\n<img width=\"1132\" alt=\"Screenshot 2025-06-10 at 4 56 29 PM\" src=\"https://github.com/user-attachments/assets/400443ff-4cda-4605-a85b-ac24b80b1e63\" />\r\n\r\n\r\n### System Prompt version tracking\r\nNow, when you edit the system prompt of any workspace we locally store this information so you can easily refer to or restore to previous prompts that might work better for a given model or workspace.\r\n\r\n<img width=\"1138\" alt=\"Screenshot 2025-06-10 at 4 56 21 PM\" src=\"https://github.com/user-attachments/assets/6c121735-8e61-4dff-a1e2-88e659071b10\" />\r\n\r\n## What's Changed\r\n* Fix/dom nesting warnings by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/3773\r\n* Refactor AWS Bedrock Provider for Multi-modal Support & Correct Token Limits by @tristan-stahnke in https://github.com/Mintplex-Labs/anything-llm/pull/3714\r\n* feat: support for iam roles for bedrock client by @dannysteenman in https://github.com/Mintplex-Labs/anything-llm/pull/2632\r\n* feat: support fetch wikis for gitlab data connectors by @lcgash in https://github.com/Mintplex-Labs/anything-llm/pull/3271\r\n* Updated README.md and README.zh_CN.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3775\r\n* Updated README.md and README.zh-CN.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3776\r\n* Enable workflow rule for package verification by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3778\r\n* Update README.zh-CN.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3780\r\n* Chat prompt history menu by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3770\r\n* minor UI patches by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3784\r\n* Updated zh locale by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3786\r\n* locale change by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3787\r\n* Add Disable Spellcheck Option by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/3795\r\n* Update:WorkspaceChat-ChatContainer-PromptInput by @maoguy in https://github.com/Mintplex-Labs/anything-llm/pull/3792\r\n* updated locale by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3796\r\n* PGvector vector database support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3788\r\n* Fix MCP Start/Stop Toast Text by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/3803\r\n* Fixed grammar and typos by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3802\r\n* Obsidian data connector by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3798\r\n* Sponsors by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3816\r\n* Fix typos by @omahs in https://github.com/Mintplex-Labs/anything-llm/pull/3826\r\n* Update light mode designs for system prompt history by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3818\r\n* Warn bad docker command by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3827\r\n* Automatic Context window detection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3817\r\n* Improve UX for API keys and invitations by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3828\r\n* Support Dell Pro AI Studio provider by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3829\r\n* Optional summarization for web-scraping flow block by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3496\r\n* 3416 file picker load times by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3833\r\n* Respect Max Chunk Len set - Generic OpenAI Embedder connection by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3838\r\n* Disable message send while content is embedding by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3832\r\n* Updated Chinese locale by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3852\r\n* Filter malformed post-processed docs from file picker by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3853\r\n* Update Brazilian Portuguese locale (pt_BR) by @JairoMarques in https://github.com/Mintplex-Labs/anything-llm/pull/3879\r\n* Removed redundant scrollbar in search containers by @17ColinMiPerry in https://github.com/Mintplex-Labs/anything-llm/pull/3865\r\n* Fix File attachments are not cleared on second send click when use @a… by @cnjsyyb in https://github.com/Mintplex-Labs/anything-llm/pull/3843\r\n* Update citations UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3837\r\n* Drupal invisible output with connector by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3878\r\n* fixed drupal connector by @rexjohannes in https://github.com/Mintplex-Labs/anything-llm/pull/3893\r\n* Feat/missing localizations by @JairoMarques in https://github.com/Mintplex-Labs/anything-llm/pull/3881\r\n* Keyboard shortcut support by @AshAnand34 in https://github.com/Mintplex-Labs/anything-llm/pull/3890\r\n* Handle invalid response bodies for `ContextWindowFinder` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3896\r\n* Add Latvian language by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3897\r\n* Update styles of attachments uploaded in PromptInput by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3892\r\n* Remove border around image upload component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3900\r\n* fix issue with files loading with watching enabled by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3930\r\n* Update more Brazilian Portuguese locale (pt_BR) by @JairoMarques in https://github.com/Mintplex-Labs/anything-llm/pull/3923\r\n* Fix/mcp environment inheritance by @PaoloC68 in https://github.com/Mintplex-Labs/anything-llm/pull/3909\r\n* Add support for PUT and PATCH in agent flow builder API call block by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3937\r\n* Add missing localizations by @JairoMarques in https://github.com/Mintplex-Labs/anything-llm/pull/3925\r\n* Patch apiChatHandler to include agent chats by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3905\r\n* New embedded chat widget UI/UX by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3899\r\n* JSON Parser from agent flow blocks by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3863\r\n* remove LLM Instruction `inputVariable` requirement by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3954\r\n* ManageWorkspace styles update by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3948\r\n* Direct output for agent flows by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3873\r\n* Implement importing of agent flows from community hub by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3867\r\n* Fix some french translations by @Stoufiler in https://github.com/Mintplex-Labs/anything-llm/pull/3959\r\n* Fix text wrapping in directory tooltip by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3967\r\n* Fix model map staleness behavior or fallback by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3971\r\n* Enable UI/UX for model swapping in chat window by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3969\r\n* Fix Typo in Documentation and Metadata Field Name by @leopardracer in https://github.com/Mintplex-Labs/anything-llm/pull/3979\r\n\r\n## New Contributors\r\n* @17ColinMiPerry made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3773\r\n* @tristan-stahnke made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3714\r\n* @dannysteenman made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2632\r\n* @maoguy made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3792\r\n* @omahs made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3826\r\n* @JairoMarques made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3879\r\n* @cnjsyyb made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3843\r\n* @rexjohannes made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3893\r\n* @AshAnand34 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3890\r\n* @PaoloC68 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3909\r\n* @Stoufiler made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3959\r\n* @leopardracer made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3979\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.1...v.1.8.2","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">AnythingLLM v1.8.2 is LIVE!</h1><a id=\"user-content-anythingllm-v182-is-live\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM v1.8.2 is LIVE!\" href=\"#anythingllm-v182-is-live\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Other news</h2><a id=\"user-content-other-news\" class=\"anchor\" aria-label=\"Permalink: Other news\" href=\"#other-news\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>We were featured on stage at Microsoft Build (how cool???)</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/1e77b3aa-8232-4050-b471-d2eed68ee3f6\"><img src=\"https://github.com/user-attachments/assets/1e77b3aa-8232-4050-b471-d2eed68ee3f6\" alt=\"1747677767492\" style=\"max-width: 100%;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Changes</h2><a id=\"user-content-notable-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Changes\" href=\"#notable-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">Model swap in chat</h3><a id=\"user-content-model-swap-in-chat\" class=\"anchor\" aria-label=\"Permalink: Model swap in chat\" href=\"#model-swap-in-chat\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>You can now easily swap model or provider in the middle of chatting via <code>cmd/Ctrl + Shift + L</code> to show a tooltip menu to easily swap models without changing screens</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/400443ff-4cda-4605-a85b-ac24b80b1e63\"><img width=\"1132\" alt=\"Screenshot 2025-06-10 at 4 56 29 PM\" src=\"https://github.com/user-attachments/assets/400443ff-4cda-4605-a85b-ac24b80b1e63\" style=\"max-width: 100%;\"></a></p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">System Prompt version tracking</h3><a id=\"user-content-system-prompt-version-tracking\" class=\"anchor\" aria-label=\"Permalink: System Prompt version tracking\" href=\"#system-prompt-version-tracking\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, when you edit the system prompt of any workspace we locally store this information so you can easily refer to or restore to previous prompts that might work better for a given model or workspace.</p>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/6c121735-8e61-4dff-a1e2-88e659071b10\"><img width=\"1138\" alt=\"Screenshot 2025-06-10 at 4 56 21 PM\" src=\"https://github.com/user-attachments/assets/6c121735-8e61-4dff-a1e2-88e659071b10\" style=\"max-width: 100%;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Fix/dom nesting warnings by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3773\">https://github.com/Mintplex-Labs/anything-llm/pull/3773</a>\n</li>\n<li>Refactor AWS Bedrock Provider for Multi-modal Support &amp; Correct Token Limits by @tristan-stahnke in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3714\">https://github.com/Mintplex-Labs/anything-llm/pull/3714</a>\n</li>\n<li>feat: support for iam roles for bedrock client by @dannysteenman in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2632\">https://github.com/Mintplex-Labs/anything-llm/pull/2632</a>\n</li>\n<li>feat: support fetch wikis for gitlab data connectors by @lcgash in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3271\">https://github.com/Mintplex-Labs/anything-llm/pull/3271</a>\n</li>\n<li>Updated README.md and README.zh_CN.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3775\">https://github.com/Mintplex-Labs/anything-llm/pull/3775</a>\n</li>\n<li>Updated README.md and README.zh-CN.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3776\">https://github.com/Mintplex-Labs/anything-llm/pull/3776</a>\n</li>\n<li>Enable workflow rule for package verification by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3778\">https://github.com/Mintplex-Labs/anything-llm/pull/3778</a>\n</li>\n<li>Update README.zh-CN.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3780\">https://github.com/Mintplex-Labs/anything-llm/pull/3780</a>\n</li>\n<li>Chat prompt history menu by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3770\">https://github.com/Mintplex-Labs/anything-llm/pull/3770</a>\n</li>\n<li>minor UI patches by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3784\">https://github.com/Mintplex-Labs/anything-llm/pull/3784</a>\n</li>\n<li>Updated zh locale by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3786\">https://github.com/Mintplex-Labs/anything-llm/pull/3786</a>\n</li>\n<li>locale change by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3787\">https://github.com/Mintplex-Labs/anything-llm/pull/3787</a>\n</li>\n<li>Add Disable Spellcheck Option by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3795\">https://github.com/Mintplex-Labs/anything-llm/pull/3795</a>\n</li>\n<li>Update:WorkspaceChat-ChatContainer-PromptInput by @maoguy in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3792\">https://github.com/Mintplex-Labs/anything-llm/pull/3792</a>\n</li>\n<li>updated locale by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3796\">https://github.com/Mintplex-Labs/anything-llm/pull/3796</a>\n</li>\n<li>PGvector vector database support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3788\">https://github.com/Mintplex-Labs/anything-llm/pull/3788</a>\n</li>\n<li>Fix MCP Start/Stop Toast Text by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3803\">https://github.com/Mintplex-Labs/anything-llm/pull/3803</a>\n</li>\n<li>Fixed grammar and typos by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3802\">https://github.com/Mintplex-Labs/anything-llm/pull/3802</a>\n</li>\n<li>Obsidian data connector by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3798\">https://github.com/Mintplex-Labs/anything-llm/pull/3798</a>\n</li>\n<li>Sponsors by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3816\">https://github.com/Mintplex-Labs/anything-llm/pull/3816</a>\n</li>\n<li>Fix typos by @omahs in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3826\">https://github.com/Mintplex-Labs/anything-llm/pull/3826</a>\n</li>\n<li>Update light mode designs for system prompt history by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3818\">https://github.com/Mintplex-Labs/anything-llm/pull/3818</a>\n</li>\n<li>Warn bad docker command by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3827\">https://github.com/Mintplex-Labs/anything-llm/pull/3827</a>\n</li>\n<li>Automatic Context window detection by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3817\">https://github.com/Mintplex-Labs/anything-llm/pull/3817</a>\n</li>\n<li>Improve UX for API keys and invitations by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3828\">https://github.com/Mintplex-Labs/anything-llm/pull/3828</a>\n</li>\n<li>Support Dell Pro AI Studio provider by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3829\">https://github.com/Mintplex-Labs/anything-llm/pull/3829</a>\n</li>\n<li>Optional summarization for web-scraping flow block by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3496\">https://github.com/Mintplex-Labs/anything-llm/pull/3496</a>\n</li>\n<li>3416 file picker load times by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3833\">https://github.com/Mintplex-Labs/anything-llm/pull/3833</a>\n</li>\n<li>Respect Max Chunk Len set - Generic OpenAI Embedder connection by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3838\">https://github.com/Mintplex-Labs/anything-llm/pull/3838</a>\n</li>\n<li>Disable message send while content is embedding by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3832\">https://github.com/Mintplex-Labs/anything-llm/pull/3832</a>\n</li>\n<li>Updated Chinese locale by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3852\">https://github.com/Mintplex-Labs/anything-llm/pull/3852</a>\n</li>\n<li>Filter malformed post-processed docs from file picker by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3853\">https://github.com/Mintplex-Labs/anything-llm/pull/3853</a>\n</li>\n<li>Update Brazilian Portuguese locale (pt_BR) by @JairoMarques in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3879\">https://github.com/Mintplex-Labs/anything-llm/pull/3879</a>\n</li>\n<li>Removed redundant scrollbar in search containers by @17ColinMiPerry in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3865\">https://github.com/Mintplex-Labs/anything-llm/pull/3865</a>\n</li>\n<li>Fix File attachments are not cleared on second send click when use @a… by @cnjsyyb in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3843\">https://github.com/Mintplex-Labs/anything-llm/pull/3843</a>\n</li>\n<li>Update citations UI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3837\">https://github.com/Mintplex-Labs/anything-llm/pull/3837</a>\n</li>\n<li>Drupal invisible output with connector by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3878\">https://github.com/Mintplex-Labs/anything-llm/pull/3878</a>\n</li>\n<li>fixed drupal connector by @rexjohannes in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3893\">https://github.com/Mintplex-Labs/anything-llm/pull/3893</a>\n</li>\n<li>Feat/missing localizations by @JairoMarques in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3881\">https://github.com/Mintplex-Labs/anything-llm/pull/3881</a>\n</li>\n<li>Keyboard shortcut support by @AshAnand34 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3890\">https://github.com/Mintplex-Labs/anything-llm/pull/3890</a>\n</li>\n<li>Handle invalid response bodies for <code>ContextWindowFinder</code> by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3896\">https://github.com/Mintplex-Labs/anything-llm/pull/3896</a>\n</li>\n<li>Add Latvian language by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3897\">https://github.com/Mintplex-Labs/anything-llm/pull/3897</a>\n</li>\n<li>Update styles of attachments uploaded in PromptInput by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3892\">https://github.com/Mintplex-Labs/anything-llm/pull/3892</a>\n</li>\n<li>Remove border around image upload component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3900\">https://github.com/Mintplex-Labs/anything-llm/pull/3900</a>\n</li>\n<li>fix issue with files loading with watching enabled by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3930\">https://github.com/Mintplex-Labs/anything-llm/pull/3930</a>\n</li>\n<li>Update more Brazilian Portuguese locale (pt_BR) by @JairoMarques in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3923\">https://github.com/Mintplex-Labs/anything-llm/pull/3923</a>\n</li>\n<li>Fix/mcp environment inheritance by @PaoloC68 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3909\">https://github.com/Mintplex-Labs/anything-llm/pull/3909</a>\n</li>\n<li>Add support for PUT and PATCH in agent flow builder API call block by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3937\">https://github.com/Mintplex-Labs/anything-llm/pull/3937</a>\n</li>\n<li>Add missing localizations by @JairoMarques in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3925\">https://github.com/Mintplex-Labs/anything-llm/pull/3925</a>\n</li>\n<li>Patch apiChatHandler to include agent chats by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3905\">https://github.com/Mintplex-Labs/anything-llm/pull/3905</a>\n</li>\n<li>New embedded chat widget UI/UX by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3899\">https://github.com/Mintplex-Labs/anything-llm/pull/3899</a>\n</li>\n<li>JSON Parser from agent flow blocks by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3863\">https://github.com/Mintplex-Labs/anything-llm/pull/3863</a>\n</li>\n<li>remove LLM Instruction <code>inputVariable</code> requirement by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3954\">https://github.com/Mintplex-Labs/anything-llm/pull/3954</a>\n</li>\n<li>ManageWorkspace styles update by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3948\">https://github.com/Mintplex-Labs/anything-llm/pull/3948</a>\n</li>\n<li>Direct output for agent flows by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3873\">https://github.com/Mintplex-Labs/anything-llm/pull/3873</a>\n</li>\n<li>Implement importing of agent flows from community hub by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3867\">https://github.com/Mintplex-Labs/anything-llm/pull/3867</a>\n</li>\n<li>Fix some french translations by @Stoufiler in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3959\">https://github.com/Mintplex-Labs/anything-llm/pull/3959</a>\n</li>\n<li>Fix text wrapping in directory tooltip by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3967\">https://github.com/Mintplex-Labs/anything-llm/pull/3967</a>\n</li>\n<li>Fix model map staleness behavior or fallback by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3971\">https://github.com/Mintplex-Labs/anything-llm/pull/3971</a>\n</li>\n<li>Enable UI/UX for model swapping in chat window by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3969\">https://github.com/Mintplex-Labs/anything-llm/pull/3969</a>\n</li>\n<li>Fix Typo in Documentation and Metadata Field Name by @leopardracer in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3979\">https://github.com/Mintplex-Labs/anything-llm/pull/3979</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@17ColinMiPerry made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3773\">https://github.com/Mintplex-Labs/anything-llm/pull/3773</a>\n</li>\n<li>@tristan-stahnke made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3714\">https://github.com/Mintplex-Labs/anything-llm/pull/3714</a>\n</li>\n<li>@dannysteenman made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2632\">https://github.com/Mintplex-Labs/anything-llm/pull/2632</a>\n</li>\n<li>@maoguy made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3792\">https://github.com/Mintplex-Labs/anything-llm/pull/3792</a>\n</li>\n<li>@omahs made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3826\">https://github.com/Mintplex-Labs/anything-llm/pull/3826</a>\n</li>\n<li>@JairoMarques made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3879\">https://github.com/Mintplex-Labs/anything-llm/pull/3879</a>\n</li>\n<li>@cnjsyyb made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3843\">https://github.com/Mintplex-Labs/anything-llm/pull/3843</a>\n</li>\n<li>@rexjohannes made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3893\">https://github.com/Mintplex-Labs/anything-llm/pull/3893</a>\n</li>\n<li>@AshAnand34 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3890\">https://github.com/Mintplex-Labs/anything-llm/pull/3890</a>\n</li>\n<li>@PaoloC68 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3909\">https://github.com/Mintplex-Labs/anything-llm/pull/3909</a>\n</li>\n<li>@Stoufiler made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3959\">https://github.com/Mintplex-Labs/anything-llm/pull/3959</a>\n</li>\n<li>@leopardracer made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3979\">https://github.com/Mintplex-Labs/anything-llm/pull/3979</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.1...v.1.8.2\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.1...v.1.8.2</a></p>\n","assets":[]},{"id":216829085,"tag":"v1.8.1","author":"timothycarambat","name":"AnythingLLM v1.8.1","draft":false,"prerelease":false,"createdAt":"2025-05-05T22:03:31Z","publishedAt":"2025-05-06T17:50:20Z","markdown":"## What's Changed\r\n* enable MCP tool use via `@agent` in API calls by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3683\r\n* Add support for `/v1/document/upload*` endpoints to support auto-add to workspace by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3692\r\n* Feature/drupalwiki collector by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3693\r\n* Enable bypass of ip limitations via ENV in collector processing by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3652\r\n* Translate main page landing by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3699\r\n* Allow custom headers in upload-link endpoint by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3695\r\n* Improve Japanese translation to maintain @agent by @suzuki-shm in https://github.com/Mintplex-Labs/anything-llm/pull/3704\r\n* Update `embed` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3728\r\n* TTS auto-speak and STT auto-submit by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3696\r\n* Update Bing Search API Azure Service copy - Unavailable by @thejjw in https://github.com/Mintplex-Labs/anything-llm/pull/3729\r\n* Update light mode input color by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3734\r\n* Replace @azure/openai with openai, and update openai to version 4.95.1 by @suzuki-shm in https://github.com/Mintplex-Labs/anything-llm/pull/3691\r\n* Remove `@google/generative-ai` from AnythingLLM by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3740\r\n* Update README.zh-CN.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3748\r\n* pt-BR translation by @thisisleobro in https://github.com/Mintplex-Labs/anything-llm/pull/3755\r\n* #3707 added sse and streamable stransport support for mcp servers by @AlekseyKapustyanenko in https://github.com/Mintplex-Labs/anything-llm/pull/3747\r\n* App wide antialiasing by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3752\r\n* Add option to control KoboldCPP max response tokens by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3746\r\n* handle no thoughts in container by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3758\r\n* Remove drop shadow from CTAButton component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3756\r\n* Fix chat alignment borders by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3760\r\n* Data connector CTA button styles by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3759\r\n* Add gemini-embedding-exp-03-07 model support by @sdarioz in https://github.com/Mintplex-Labs/anything-llm/pull/3767\r\n* Filter image models from OpenAI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3768\r\n* more zh translations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3769\r\n\r\n## New Contributors\r\n* @thejjw made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3729\r\n* @thisisleobro made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3755\r\n* @AlekseyKapustyanenko made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3747\r\n* @sdarioz made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3767\r\n\r\n## Desktop App Changelog\r\nhttps://docs.anythingllm.com/changelog/v1.8.1\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.0...v1.8.1","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>enable MCP tool use via <code>@agent</code> in API calls by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3683\">https://github.com/Mintplex-Labs/anything-llm/pull/3683</a>\n</li>\n<li>Add support for <code>/v1/document/upload*</code> endpoints to support auto-add to workspace by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3692\">https://github.com/Mintplex-Labs/anything-llm/pull/3692</a>\n</li>\n<li>Feature/drupalwiki collector by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3693\">https://github.com/Mintplex-Labs/anything-llm/pull/3693</a>\n</li>\n<li>Enable bypass of ip limitations via ENV in collector processing by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3652\">https://github.com/Mintplex-Labs/anything-llm/pull/3652</a>\n</li>\n<li>Translate main page landing by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3699\">https://github.com/Mintplex-Labs/anything-llm/pull/3699</a>\n</li>\n<li>Allow custom headers in upload-link endpoint by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3695\">https://github.com/Mintplex-Labs/anything-llm/pull/3695</a>\n</li>\n<li>Improve Japanese translation to maintain @agent by @suzuki-shm in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3704\">https://github.com/Mintplex-Labs/anything-llm/pull/3704</a>\n</li>\n<li>Update <code>embed</code> by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3728\">https://github.com/Mintplex-Labs/anything-llm/pull/3728</a>\n</li>\n<li>TTS auto-speak and STT auto-submit by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3696\">https://github.com/Mintplex-Labs/anything-llm/pull/3696</a>\n</li>\n<li>Update Bing Search API Azure Service copy - Unavailable by @thejjw in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3729\">https://github.com/Mintplex-Labs/anything-llm/pull/3729</a>\n</li>\n<li>Update light mode input color by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3734\">https://github.com/Mintplex-Labs/anything-llm/pull/3734</a>\n</li>\n<li>Replace @azure/openai with openai, and update openai to version 4.95.1 by @suzuki-shm in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3691\">https://github.com/Mintplex-Labs/anything-llm/pull/3691</a>\n</li>\n<li>Remove <code>@google/generative-ai</code> from AnythingLLM by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3740\">https://github.com/Mintplex-Labs/anything-llm/pull/3740</a>\n</li>\n<li>Update README.zh-CN.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3748\">https://github.com/Mintplex-Labs/anything-llm/pull/3748</a>\n</li>\n<li>pt-BR translation by @thisisleobro in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3755\">https://github.com/Mintplex-Labs/anything-llm/pull/3755</a>\n</li>\n<li>#3707 added sse and streamable stransport support for mcp servers by @AlekseyKapustyanenko in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3747\">https://github.com/Mintplex-Labs/anything-llm/pull/3747</a>\n</li>\n<li>App wide antialiasing by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3752\">https://github.com/Mintplex-Labs/anything-llm/pull/3752</a>\n</li>\n<li>Add option to control KoboldCPP max response tokens by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3746\">https://github.com/Mintplex-Labs/anything-llm/pull/3746</a>\n</li>\n<li>handle no thoughts in container by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3758\">https://github.com/Mintplex-Labs/anything-llm/pull/3758</a>\n</li>\n<li>Remove drop shadow from CTAButton component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3756\">https://github.com/Mintplex-Labs/anything-llm/pull/3756</a>\n</li>\n<li>Fix chat alignment borders by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3760\">https://github.com/Mintplex-Labs/anything-llm/pull/3760</a>\n</li>\n<li>Data connector CTA button styles by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3759\">https://github.com/Mintplex-Labs/anything-llm/pull/3759</a>\n</li>\n<li>Add gemini-embedding-exp-03-07 model support by @sdarioz in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3767\">https://github.com/Mintplex-Labs/anything-llm/pull/3767</a>\n</li>\n<li>Filter image models from OpenAI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3768\">https://github.com/Mintplex-Labs/anything-llm/pull/3768</a>\n</li>\n<li>more zh translations by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3769\">https://github.com/Mintplex-Labs/anything-llm/pull/3769</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@thejjw made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3729\">https://github.com/Mintplex-Labs/anything-llm/pull/3729</a>\n</li>\n<li>@thisisleobro made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3755\">https://github.com/Mintplex-Labs/anything-llm/pull/3755</a>\n</li>\n<li>@AlekseyKapustyanenko made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3747\">https://github.com/Mintplex-Labs/anything-llm/pull/3747</a>\n</li>\n<li>@sdarioz made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3767\">https://github.com/Mintplex-Labs/anything-llm/pull/3767</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Desktop App Changelog</h2><a id=\"user-content-desktop-app-changelog\" class=\"anchor\" aria-label=\"Permalink: Desktop App Changelog\" href=\"#desktop-app-changelog\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a href=\"https://docs.anythingllm.com/changelog/v1.8.1\" rel=\"nofollow\">https://docs.anythingllm.com/changelog/v1.8.1</a></p>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.0...v1.8.1\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.8.0...v1.8.1</a></p>\n","assets":[]},{"id":213149945,"tag":"v1.8.0","author":"timothycarambat","name":"AnythingLLM v1.8.0 | MCP support & UI refresh","draft":false,"prerelease":false,"createdAt":"2025-04-18T21:25:37Z","publishedAt":"2025-04-18T22:17:11Z","markdown":"# AnythingLLM v1.8.0 | MCP tools & a fresh new look!\r\n\r\nhttps://github.com/user-attachments/assets/5639b994-2739-4605-9eee-a923148ceb3a\r\n\r\n## MCP tooling is now easier than ever!\r\n\r\nhttps://github.com/user-attachments/assets/4a62acc7-ec34-4761-b662-29aa48194db1\r\n\r\n- [Full Documentation](https://docs.anythingllm.com/mcp-compatibility/overview)\r\n- Update and reload your MCP config on the fly with no downtime\r\n- Docker includes `npx` and `uv` commands build in\r\n\r\n## A new onboarding experience\r\n\r\n<img width=\"1612\" alt=\"Screenshot 2025-04-18 at 3 16 46 PM\" src=\"https://github.com/user-attachments/assets/e690a80f-9b41-4443-a739-5be35d312fcf\" />\r\n\r\nAin't it pretty?\r\n\r\n\r\n## What's Changed\r\n* Replace connectionString parser for sql-agent by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3560\r\n* Update styles of experimental modal buttons by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3535\r\n* Teal color for onboarding buttons by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3533\r\n* Agent builder UI bug fixes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3522\r\n* ModelContextProtocol (MCP) Full Compatibility by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3547\r\n* Fix broken links in MCP UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3569\r\n* Allow period in username by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3592\r\n* Fix agent flow description bug by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3593\r\n* Sync and publish `embed` widget changes for thought models by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3596\r\n* [CHORE] Consistent table styling across settings pages by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3597\r\n* Gemini model list sync by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3609\r\n* Disable Agent retry to prevent looping on crash by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3617\r\n* Refactor Gemini to use OpenAI interface API by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3616\r\n* Fix bottom border on workspace settings tab switcher by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3615\r\n* Move CTA save buttons to top of workspace setting screens by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3613\r\n* Fix truncation of threads/workspaces by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3610\r\n* New chat home page by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3555\r\n* Main page QA by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3623\r\n* Appearance menu styles by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3627\r\n* Fix customize logo bug by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3628\r\n* Add Japanese translations for AnythingLLM by @suzuki-shm in https://github.com/Mintplex-Labs/anything-llm/pull/3651\r\n* handling of citations in openRouter provider #3581 by @rudimichal in https://github.com/Mintplex-Labs/anything-llm/pull/3620\r\n* Buildx bump to latest to solve GHA cache deprecation by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3653\r\n* Apply `.git` logic handler for repo URLs by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3655\r\n* Updated Russian translation by @aguilam in https://github.com/Mintplex-Labs/anything-llm/pull/3658\r\n* Update Azure AI options and model map with new model configurations by @suzuki-shm in https://github.com/Mintplex-Labs/anything-llm/pull/3660\r\n\r\n## New Contributors\r\n* @suzuki-shm made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3651\r\n* @rudimichal made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3620\r\n* @aguilam made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3658\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.8...v1.8.0","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">AnythingLLM v1.8.0 | MCP tools &amp; a fresh new look!</h1><a id=\"user-content-anythingllm-v180--mcp-tools--a-fresh-new-look\" class=\"anchor\" aria-label=\"Permalink: AnythingLLM v1.8.0 | MCP tools &amp; a fresh new look!\" href=\"#anythingllm-v180--mcp-tools--a-fresh-new-look\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a href=\"https://github.com/user-attachments/assets/5639b994-2739-4605-9eee-a923148ceb3a\">https://github.com/user-attachments/assets/5639b994-2739-4605-9eee-a923148ceb3a</a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">MCP tooling is now easier than ever!</h2><a id=\"user-content-mcp-tooling-is-now-easier-than-ever\" class=\"anchor\" aria-label=\"Permalink: MCP tooling is now easier than ever!\" href=\"#mcp-tooling-is-now-easier-than-ever\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a href=\"https://github.com/user-attachments/assets/4a62acc7-ec34-4761-b662-29aa48194db1\">https://github.com/user-attachments/assets/4a62acc7-ec34-4761-b662-29aa48194db1</a></p>\n<ul>\n<li><a href=\"https://docs.anythingllm.com/mcp-compatibility/overview\" rel=\"nofollow\">Full Documentation</a></li>\n<li>Update and reload your MCP config on the fly with no downtime</li>\n<li>Docker includes <code>npx</code> and <code>uv</code> commands build in</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">A new onboarding experience</h2><a id=\"user-content-a-new-onboarding-experience\" class=\"anchor\" aria-label=\"Permalink: A new onboarding experience\" href=\"#a-new-onboarding-experience\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/e690a80f-9b41-4443-a739-5be35d312fcf\"><img width=\"1612\" alt=\"Screenshot 2025-04-18 at 3 16 46 PM\" src=\"https://github.com/user-attachments/assets/e690a80f-9b41-4443-a739-5be35d312fcf\" style=\"max-width: 100%;\"></a></p>\n<p>Ain't it pretty?</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Replace connectionString parser for sql-agent by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3560\">https://github.com/Mintplex-Labs/anything-llm/pull/3560</a>\n</li>\n<li>Update styles of experimental modal buttons by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3535\">https://github.com/Mintplex-Labs/anything-llm/pull/3535</a>\n</li>\n<li>Teal color for onboarding buttons by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3533\">https://github.com/Mintplex-Labs/anything-llm/pull/3533</a>\n</li>\n<li>Agent builder UI bug fixes by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3522\">https://github.com/Mintplex-Labs/anything-llm/pull/3522</a>\n</li>\n<li>ModelContextProtocol (MCP) Full Compatibility by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3547\">https://github.com/Mintplex-Labs/anything-llm/pull/3547</a>\n</li>\n<li>Fix broken links in MCP UI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3569\">https://github.com/Mintplex-Labs/anything-llm/pull/3569</a>\n</li>\n<li>Allow period in username by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3592\">https://github.com/Mintplex-Labs/anything-llm/pull/3592</a>\n</li>\n<li>Fix agent flow description bug by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3593\">https://github.com/Mintplex-Labs/anything-llm/pull/3593</a>\n</li>\n<li>Sync and publish <code>embed</code> widget changes for thought models by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3596\">https://github.com/Mintplex-Labs/anything-llm/pull/3596</a>\n</li>\n<li>[CHORE] Consistent table styling across settings pages by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3597\">https://github.com/Mintplex-Labs/anything-llm/pull/3597</a>\n</li>\n<li>Gemini model list sync by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3609\">https://github.com/Mintplex-Labs/anything-llm/pull/3609</a>\n</li>\n<li>Disable Agent retry to prevent looping on crash by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3617\">https://github.com/Mintplex-Labs/anything-llm/pull/3617</a>\n</li>\n<li>Refactor Gemini to use OpenAI interface API by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3616\">https://github.com/Mintplex-Labs/anything-llm/pull/3616</a>\n</li>\n<li>Fix bottom border on workspace settings tab switcher by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3615\">https://github.com/Mintplex-Labs/anything-llm/pull/3615</a>\n</li>\n<li>Move CTA save buttons to top of workspace setting screens by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3613\">https://github.com/Mintplex-Labs/anything-llm/pull/3613</a>\n</li>\n<li>Fix truncation of threads/workspaces by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3610\">https://github.com/Mintplex-Labs/anything-llm/pull/3610</a>\n</li>\n<li>New chat home page by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3555\">https://github.com/Mintplex-Labs/anything-llm/pull/3555</a>\n</li>\n<li>Main page QA by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3623\">https://github.com/Mintplex-Labs/anything-llm/pull/3623</a>\n</li>\n<li>Appearance menu styles by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3627\">https://github.com/Mintplex-Labs/anything-llm/pull/3627</a>\n</li>\n<li>Fix customize logo bug by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3628\">https://github.com/Mintplex-Labs/anything-llm/pull/3628</a>\n</li>\n<li>Add Japanese translations for AnythingLLM by @suzuki-shm in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3651\">https://github.com/Mintplex-Labs/anything-llm/pull/3651</a>\n</li>\n<li>handling of citations in openRouter provider #3581 by @rudimichal in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3620\">https://github.com/Mintplex-Labs/anything-llm/pull/3620</a>\n</li>\n<li>Buildx bump to latest to solve GHA cache deprecation by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3653\">https://github.com/Mintplex-Labs/anything-llm/pull/3653</a>\n</li>\n<li>Apply <code>.git</code> logic handler for repo URLs by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3655\">https://github.com/Mintplex-Labs/anything-llm/pull/3655</a>\n</li>\n<li>Updated Russian translation by @aguilam in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3658\">https://github.com/Mintplex-Labs/anything-llm/pull/3658</a>\n</li>\n<li>Update Azure AI options and model map with new model configurations by @suzuki-shm in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3660\">https://github.com/Mintplex-Labs/anything-llm/pull/3660</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@suzuki-shm made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3651\">https://github.com/Mintplex-Labs/anything-llm/pull/3651</a>\n</li>\n<li>@rudimichal made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3620\">https://github.com/Mintplex-Labs/anything-llm/pull/3620</a>\n</li>\n<li>@aguilam made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3658\">https://github.com/Mintplex-Labs/anything-llm/pull/3658</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.8...v1.8.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.8...v1.8.0</a></p>\n","assets":[]},{"id":208793104,"tag":"v1.7.8","author":"timothycarambat","name":"AnythingLLM v1.7.8","draft":false,"prerelease":false,"createdAt":"2025-03-26T21:16:12Z","publishedAt":"2025-03-27T19:59:37Z","markdown":"## What's New\r\n\r\n- Support for Workspace [system prompt variables!](https://docs.anythingllm.com/features/system-prompt-variables)\r\n- NVIDIA NIM support - [AnythingLLM Desktop only](https://docs.anythingllm.com/nvidia-nims/introduction)\r\n\r\n_this version includes 1.7.7, which no changelog was published for - whoops!_\r\n\r\n## What's Changed\r\n* Enable slash commands in dev API chat/stream-chat by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3514\r\n* Enable use of @agent in slash commands by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3508\r\n* Protected slash command check by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3524\r\n* Prompt variables by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3359\r\n* Update QDRANT_SETUP.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3530\r\n* Overhaul AWS Bedrock provider for `AIProviders` by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3537\r\n* add AgentFlow execution via API chat invocation by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3545\r\n* Persist images attached in API requests to the UI for rendering by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3546\r\n\r\n_1.7.7 changes_\r\n* CHORE: debounce telems to prevent spamming by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3505\r\n* Bump LanceDB by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3015\r\n* Update README.zh-CN.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/3527\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.6...v1.7.8","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's New</h2><a id=\"user-content-whats-new\" class=\"anchor\" aria-label=\"Permalink: What's New\" href=\"#whats-new\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Support for Workspace <a href=\"https://docs.anythingllm.com/features/system-prompt-variables\" rel=\"nofollow\">system prompt variables!</a>\n</li>\n<li>NVIDIA NIM support - <a href=\"https://docs.anythingllm.com/nvidia-nims/introduction\" rel=\"nofollow\">AnythingLLM Desktop only</a>\n</li>\n</ul>\n<p><em>this version includes 1.7.7, which no changelog was published for - whoops!</em></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Enable slash commands in dev API chat/stream-chat by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3514\">https://github.com/Mintplex-Labs/anything-llm/pull/3514</a>\n</li>\n<li>Enable use of @agent in slash commands by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3508\">https://github.com/Mintplex-Labs/anything-llm/pull/3508</a>\n</li>\n<li>Protected slash command check by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3524\">https://github.com/Mintplex-Labs/anything-llm/pull/3524</a>\n</li>\n<li>Prompt variables by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3359\">https://github.com/Mintplex-Labs/anything-llm/pull/3359</a>\n</li>\n<li>Update QDRANT_SETUP.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3530\">https://github.com/Mintplex-Labs/anything-llm/pull/3530</a>\n</li>\n<li>Overhaul AWS Bedrock provider for <code>AIProviders</code> by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3537\">https://github.com/Mintplex-Labs/anything-llm/pull/3537</a>\n</li>\n<li>add AgentFlow execution via API chat invocation by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3545\">https://github.com/Mintplex-Labs/anything-llm/pull/3545</a>\n</li>\n<li>Persist images attached in API requests to the UI for rendering by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3546\">https://github.com/Mintplex-Labs/anything-llm/pull/3546</a>\n</li>\n</ul>\n<p><em>1.7.7 changes</em></p>\n<ul>\n<li>CHORE: debounce telems to prevent spamming by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3505\">https://github.com/Mintplex-Labs/anything-llm/pull/3505</a>\n</li>\n<li>Bump LanceDB by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3015\">https://github.com/Mintplex-Labs/anything-llm/pull/3015</a>\n</li>\n<li>Update README.zh-CN.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3527\">https://github.com/Mintplex-Labs/anything-llm/pull/3527</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.6...v1.7.8\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.6...v1.7.8</a></p>\n","assets":[]},{"id":207011904,"tag":"v1.7.6","author":"timothycarambat","name":"AnythingLLM v1.7.6","draft":false,"prerelease":false,"createdAt":"2025-03-19T18:41:07Z","publishedAt":"2025-03-19T22:52:50Z","markdown":"## What's Changed\r\n* fix thought container from getting cut off at max height by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3449\r\n* Fix agent calling UI max height by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3457\r\n* Added danish translation by @MOEI-123412 in https://github.com/Mintplex-Labs/anything-llm/pull/3461\r\n* Pinning UI improvements by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3490\r\n* Add remove folder developer API endpoint by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3489\r\n* fix chroma db + add similarity offset by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3458\r\n* Fix embedding endpoint for OpenAI compatible API by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3467\r\n* Add ability to reordering workspaces by @MrMarans in https://github.com/Mintplex-Labs/anything-llm/pull/3446\r\n* Use concurrently to run all dev service at once by @dotku in https://github.com/Mintplex-Labs/anything-llm/pull/3424\r\n\r\n## New Contributors\r\n* @MOEI-123412 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3461\r\n* @dotku made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3424\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.5...v1.7.6","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>fix thought container from getting cut off at max height by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3449\">https://github.com/Mintplex-Labs/anything-llm/pull/3449</a>\n</li>\n<li>Fix agent calling UI max height by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3457\">https://github.com/Mintplex-Labs/anything-llm/pull/3457</a>\n</li>\n<li>Added danish translation by @MOEI-123412 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3461\">https://github.com/Mintplex-Labs/anything-llm/pull/3461</a>\n</li>\n<li>Pinning UI improvements by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3490\">https://github.com/Mintplex-Labs/anything-llm/pull/3490</a>\n</li>\n<li>Add remove folder developer API endpoint by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3489\">https://github.com/Mintplex-Labs/anything-llm/pull/3489</a>\n</li>\n<li>fix chroma db + add similarity offset by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3458\">https://github.com/Mintplex-Labs/anything-llm/pull/3458</a>\n</li>\n<li>Fix embedding endpoint for OpenAI compatible API by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3467\">https://github.com/Mintplex-Labs/anything-llm/pull/3467</a>\n</li>\n<li>Add ability to reordering workspaces by @MrMarans in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3446\">https://github.com/Mintplex-Labs/anything-llm/pull/3446</a>\n</li>\n<li>Use concurrently to run all dev service at once by @dotku in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3424\">https://github.com/Mintplex-Labs/anything-llm/pull/3424</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@MOEI-123412 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3461\">https://github.com/Mintplex-Labs/anything-llm/pull/3461</a>\n</li>\n<li>@dotku made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3424\">https://github.com/Mintplex-Labs/anything-llm/pull/3424</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.5...v1.7.6\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.5...v1.7.6</a></p>\n","assets":[]},{"id":203716721,"tag":"v1.7.5","author":"timothycarambat","name":"AnythingLLM v1.7.5","draft":false,"prerelease":false,"createdAt":"2025-03-04T17:08:21Z","publishedAt":"2025-03-04T22:14:53Z","markdown":"## Notable Changes\r\n\r\n- Anthropic provider now uses their `/models` endpoint (finally)\r\n- Bug fixes on collector to prevent thread crashing\r\n- Multi-language OCR support on collector\r\n- More localization and language support\r\n\r\n## What's Changed\r\n* Add additional embed API endpoints by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3264\r\n* feat: Add endpoint to retrieve documents by folder name by @thestackdev in https://github.com/Mintplex-Labs/anything-llm/pull/3258\r\n* Improve PromptInput component by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3266\r\n* 2749 ollama client auth token by @ssbodapati in https://github.com/Mintplex-Labs/anything-llm/pull/3005\r\n* Normalize chat sorting defaults in developer API by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3270\r\n* Markdown support in custom messages by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3267\r\n* Update null-check function for aibitat runners by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3283\r\n* Fix garbled non English chars on document upload by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3301\r\n* [FEAT] Add claude-3-7 by @kaashmonee in https://github.com/Mintplex-Labs/anything-llm/pull/3337\r\n* feature: support configurable left and right message layout by @MrGaoGang in https://github.com/Mintplex-Labs/anything-llm/pull/3244\r\n* Arabic Translation by @Saidoua in https://github.com/Mintplex-Labs/anything-llm/pull/3357\r\n* fix: bug where in single user mode deletion of an api key deletes all  by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3358\r\n* feat: Add endpoint to upload documents to a specified folder by @thestackdev in https://github.com/Mintplex-Labs/anything-llm/pull/3276\r\n* Add bio field to user by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3346\r\n* speech to text typo correction by @yashschandra in https://github.com/Mintplex-Labs/anything-llm/pull/3330\r\n* New thinking/agent animation + UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3302\r\n* Windows development environment variables support by @kbourro in https://github.com/Mintplex-Labs/anything-llm/pull/3354\r\n* Add new model provider PPIO by @cnJasonZ in https://github.com/Mintplex-Labs/anything-llm/pull/3211\r\n* changed language support for following windows: chat, data-upload and… by @MrMarans in https://github.com/Mintplex-Labs/anything-llm/pull/3010\r\n* feat: Add multilingual support for ocr module by @doodle777 in https://github.com/Mintplex-Labs/anything-llm/pull/3325\r\n* Prevent collector crash when blocked by CDN by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3373\r\n* Add support for Anthropics /model endpoint (finally) by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3376\r\n\r\n## New Contributors\r\n* @thestackdev made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3258\r\n* @ssbodapati made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3005\r\n* @kaashmonee made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3337\r\n* @MrGaoGang made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3244\r\n* @Saidoua made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3357\r\n* @yashschandra made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3330\r\n* @kbourro made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3354\r\n* @cnJasonZ made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3211\r\n* @MrMarans made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3010\r\n* @doodle777 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3325\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.4...v1.7.5","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable Changes</h2><a id=\"user-content-notable-changes\" class=\"anchor\" aria-label=\"Permalink: Notable Changes\" href=\"#notable-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Anthropic provider now uses their <code>/models</code> endpoint (finally)</li>\n<li>Bug fixes on collector to prevent thread crashing</li>\n<li>Multi-language OCR support on collector</li>\n<li>More localization and language support</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">What's Changed</h2><a id=\"user-content-whats-changed\" class=\"anchor\" aria-label=\"Permalink: What's Changed\" href=\"#whats-changed\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Add additional embed API endpoints by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3264\">https://github.com/Mintplex-Labs/anything-llm/pull/3264</a>\n</li>\n<li>feat: Add endpoint to retrieve documents by folder name by @thestackdev in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3258\">https://github.com/Mintplex-Labs/anything-llm/pull/3258</a>\n</li>\n<li>Improve PromptInput component by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3266\">https://github.com/Mintplex-Labs/anything-llm/pull/3266</a>\n</li>\n<li>2749 ollama client auth token by @ssbodapati in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3005\">https://github.com/Mintplex-Labs/anything-llm/pull/3005</a>\n</li>\n<li>Normalize chat sorting defaults in developer API by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3270\">https://github.com/Mintplex-Labs/anything-llm/pull/3270</a>\n</li>\n<li>Markdown support in custom messages by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3267\">https://github.com/Mintplex-Labs/anything-llm/pull/3267</a>\n</li>\n<li>Update null-check function for aibitat runners by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3283\">https://github.com/Mintplex-Labs/anything-llm/pull/3283</a>\n</li>\n<li>Fix garbled non English chars on document upload by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3301\">https://github.com/Mintplex-Labs/anything-llm/pull/3301</a>\n</li>\n<li>[FEAT] Add claude-3-7 by @kaashmonee in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3337\">https://github.com/Mintplex-Labs/anything-llm/pull/3337</a>\n</li>\n<li>feature: support configurable left and right message layout by @MrGaoGang in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3244\">https://github.com/Mintplex-Labs/anything-llm/pull/3244</a>\n</li>\n<li>Arabic Translation by @Saidoua in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3357\">https://github.com/Mintplex-Labs/anything-llm/pull/3357</a>\n</li>\n<li>fix: bug where in single user mode deletion of an api key deletes all  by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3358\">https://github.com/Mintplex-Labs/anything-llm/pull/3358</a>\n</li>\n<li>feat: Add endpoint to upload documents to a specified folder by @thestackdev in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3276\">https://github.com/Mintplex-Labs/anything-llm/pull/3276</a>\n</li>\n<li>Add bio field to user by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3346\">https://github.com/Mintplex-Labs/anything-llm/pull/3346</a>\n</li>\n<li>speech to text typo correction by @yashschandra in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3330\">https://github.com/Mintplex-Labs/anything-llm/pull/3330</a>\n</li>\n<li>New thinking/agent animation + UI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3302\">https://github.com/Mintplex-Labs/anything-llm/pull/3302</a>\n</li>\n<li>Windows development environment variables support by @kbourro in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3354\">https://github.com/Mintplex-Labs/anything-llm/pull/3354</a>\n</li>\n<li>Add new model provider PPIO by @cnJasonZ in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3211\">https://github.com/Mintplex-Labs/anything-llm/pull/3211</a>\n</li>\n<li>changed language support for following windows: chat, data-upload and… by @MrMarans in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3010\">https://github.com/Mintplex-Labs/anything-llm/pull/3010</a>\n</li>\n<li>feat: Add multilingual support for ocr module by @doodle777 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3325\">https://github.com/Mintplex-Labs/anything-llm/pull/3325</a>\n</li>\n<li>Prevent collector crash when blocked by CDN by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3373\">https://github.com/Mintplex-Labs/anything-llm/pull/3373</a>\n</li>\n<li>Add support for Anthropics /model endpoint (finally) by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3376\">https://github.com/Mintplex-Labs/anything-llm/pull/3376</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@thestackdev made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3258\">https://github.com/Mintplex-Labs/anything-llm/pull/3258</a>\n</li>\n<li>@ssbodapati made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3005\">https://github.com/Mintplex-Labs/anything-llm/pull/3005</a>\n</li>\n<li>@kaashmonee made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3337\">https://github.com/Mintplex-Labs/anything-llm/pull/3337</a>\n</li>\n<li>@MrGaoGang made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3244\">https://github.com/Mintplex-Labs/anything-llm/pull/3244</a>\n</li>\n<li>@Saidoua made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3357\">https://github.com/Mintplex-Labs/anything-llm/pull/3357</a>\n</li>\n<li>@yashschandra made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3330\">https://github.com/Mintplex-Labs/anything-llm/pull/3330</a>\n</li>\n<li>@kbourro made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3354\">https://github.com/Mintplex-Labs/anything-llm/pull/3354</a>\n</li>\n<li>@cnJasonZ made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3211\">https://github.com/Mintplex-Labs/anything-llm/pull/3211</a>\n</li>\n<li>@MrMarans made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3010\">https://github.com/Mintplex-Labs/anything-llm/pull/3010</a>\n</li>\n<li>@doodle777 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3325\">https://github.com/Mintplex-Labs/anything-llm/pull/3325</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.4...v1.7.5\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.7.4...v1.7.5</a></p>\n","assets":[]},{"id":200811614,"tag":"v1.7.4","author":"timothycarambat","name":"AnythingLLM v1.7.4 & the No-code Agent skill builder!","draft":false,"prerelease":false,"createdAt":"2025-02-17T22:44:23Z","publishedAt":"2025-02-18T01:15:43Z","markdown":"## The no-code agent skill builder is live ⚡ \r\n![AnythingLLM](https://github.com/user-attachments/assets/14b09cc2-4932-47c1-a81d-5b96ab64504a)\r\n\r\n## Big changes\r\n\r\n### 🏗️ The built-in no-code agent flow builder is alive!\r\n\r\nNow, without a line of code you can seamlessly draft and run agentic skills that _just make sense_. No confusing setup - just AI skills on steroids, fully local and about 1000x easier to understand than MCP.\r\n\r\n[Read the docs on making your first skill ->](https://docs.anythingllm.com/agent-flows/tutorial-hackernews)\r\n\r\n### OCR scanning of PDF and images is live!\r\n\r\nNow, when Anythingllm is given an image or _nondigitized_ PDF we will automatically OCR the text content into a document. This is done via a local [Tesseract](https://github.com/tesseract-ocr/tesseract?tab=readme-ov-file#installing-tesseract) model running in process!\r\n\r\n_this is OCR, not \"vision\" so if the content has no text - nothing will be found!_\r\n\r\n\r\nLastly, we skipped a few Docker versions to make Docker <=> Desktop the same release version. It was confusing have two different semantic versions. They will now be lock-step going forward.\r\n\r\n## All the other fixes 🔧 \r\n* Enable `include_reasoning` in request by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3067\r\n* parse streams from `reasoning_content` from DeepSeek API by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3068\r\n* Add tokenizer improvements via Singleton class and estimation by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3072\r\n* autodetect parseable text file contents by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3079\r\n* inherit font size from UI for thoughts by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3099\r\n* Enable consistent styling on chart items by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3126\r\n* Add reasoning flag for azure models with \"default\" fallback by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3128\r\n* Enable `num_ctx` to match defined chunk length in ollama embedder by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3129\r\n* Patch PPLX streaming for timeouts by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3130\r\n* Add improved logging and introspection to web-browsing by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3140\r\n* [FEAT] Add Turkish Language Support (tr.js) #3108 by @TunahanDilercan in https://github.com/Mintplex-Labs/anything-llm/pull/3141\r\n* [CHORE] Onboarding language translations by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3176\r\n* fix UserMenu rendered twice on Main page by @sdeleeuw in https://github.com/Mintplex-Labs/anything-llm/pull/3110\r\n* Add handling to reasoning models for Generic OpenAI connector by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3183\r\n* Agent flow builder by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3077\r\n* chore: rename Github to GitHub by @setchy in https://github.com/Mintplex-Labs/anything-llm/pull/3199\r\n* chore: rename `Gitlab` to `GitLab` by @setchy in https://github.com/Mintplex-Labs/anything-llm/pull/3200\r\n* Add `querySelectorAll` capability to web-scraping block by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3186\r\n* Turkish translations by @cobanov in https://github.com/Mintplex-Labs/anything-llm/pull/3207\r\n* OCR PDFs as fallback during upload by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3204\r\n* Add OCR of image support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3219\r\n* feat(dataconnectors): support confluence personal access token by @lcgash in https://github.com/Mintplex-Labs/anything-llm/pull/3206\r\n* fix agent builder move block bug by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3220\r\n* Drop Node `canvas` for manual `sharp` conversion by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3221\r\n* for projects in gitlab subgroup (#3075) by @t2tx in https://github.com/Mintplex-Labs/anything-llm/pull/3247\r\n* Fix: fix text and format issues in Chinese documentation. by @alongLFB in https://github.com/Mintplex-Labs/anything-llm/pull/3249\r\n* fix: sanitizeNamespace by @hakeemsyd in https://github.com/Mintplex-Labs/anything-llm/pull/3246\r\n* fix: Patch agent flow to honor agent handler established provider by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3251\r\n\r\n## New Contributors\r\n* @TunahanDilercan made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3141\r\n* @sdeleeuw made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3110\r\n* @setchy made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3199\r\n* @cobanov made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3207\r\n* @lcgash made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3206\r\n* @t2tx made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3247\r\n* @alongLFB made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3249\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.4.0...v1.7.4","html":"<div class=\"markdown-heading\"><h2 class=\"heading-element\">The no-code agent skill builder is live ⚡</h2><a id=\"user-content-the-no-code-agent-skill-builder-is-live-\" class=\"anchor\" aria-label=\"Permalink: The no-code agent skill builder is live ⚡\" href=\"#the-no-code-agent-skill-builder-is-live-\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/14b09cc2-4932-47c1-a81d-5b96ab64504a\"><img src=\"https://github.com/user-attachments/assets/14b09cc2-4932-47c1-a81d-5b96ab64504a\" alt=\"AnythingLLM\" style=\"max-width: 100%;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Big changes</h2><a id=\"user-content-big-changes\" class=\"anchor\" aria-label=\"Permalink: Big changes\" href=\"#big-changes\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">🏗️ The built-in no-code agent flow builder is alive!</h3><a id=\"user-content-️-the-built-in-no-code-agent-flow-builder-is-alive\" class=\"anchor\" aria-label=\"Permalink: 🏗️ The built-in no-code agent flow builder is alive!\" href=\"#️-the-built-in-no-code-agent-flow-builder-is-alive\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, without a line of code you can seamlessly draft and run agentic skills that <em>just make sense</em>. No confusing setup - just AI skills on steroids, fully local and about 1000x easier to understand than MCP.</p>\n<p><a href=\"https://docs.anythingllm.com/agent-flows/tutorial-hackernews\" rel=\"nofollow\">Read the docs on making your first skill -&gt;</a></p>\n<div class=\"markdown-heading\"><h3 class=\"heading-element\">OCR scanning of PDF and images is live!</h3><a id=\"user-content-ocr-scanning-of-pdf-and-images-is-live\" class=\"anchor\" aria-label=\"Permalink: OCR scanning of PDF and images is live!\" href=\"#ocr-scanning-of-pdf-and-images-is-live\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<p>Now, when Anythingllm is given an image or <em>nondigitized</em> PDF we will automatically OCR the text content into a document. This is done via a local <a href=\"https://github.com/tesseract-ocr/tesseract?tab=readme-ov-file#installing-tesseract\">Tesseract</a> model running in process!</p>\n<p><em>this is OCR, not \"vision\" so if the content has no text - nothing will be found!</em></p>\n<p>Lastly, we skipped a few Docker versions to make Docker &lt;=&gt; Desktop the same release version. It was confusing have two different semantic versions. They will now be lock-step going forward.</p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">All the other fixes 🔧</h2><a id=\"user-content-all-the-other-fixes-\" class=\"anchor\" aria-label=\"Permalink: All the other fixes 🔧\" href=\"#all-the-other-fixes-\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Enable <code>include_reasoning</code> in request by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3067\">https://github.com/Mintplex-Labs/anything-llm/pull/3067</a>\n</li>\n<li>parse streams from <code>reasoning_content</code> from DeepSeek API by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3068\">https://github.com/Mintplex-Labs/anything-llm/pull/3068</a>\n</li>\n<li>Add tokenizer improvements via Singleton class and estimation by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3072\">https://github.com/Mintplex-Labs/anything-llm/pull/3072</a>\n</li>\n<li>autodetect parseable text file contents by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3079\">https://github.com/Mintplex-Labs/anything-llm/pull/3079</a>\n</li>\n<li>inherit font size from UI for thoughts by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3099\">https://github.com/Mintplex-Labs/anything-llm/pull/3099</a>\n</li>\n<li>Enable consistent styling on chart items by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3126\">https://github.com/Mintplex-Labs/anything-llm/pull/3126</a>\n</li>\n<li>Add reasoning flag for azure models with \"default\" fallback by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3128\">https://github.com/Mintplex-Labs/anything-llm/pull/3128</a>\n</li>\n<li>Enable <code>num_ctx</code> to match defined chunk length in ollama embedder by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3129\">https://github.com/Mintplex-Labs/anything-llm/pull/3129</a>\n</li>\n<li>Patch PPLX streaming for timeouts by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3130\">https://github.com/Mintplex-Labs/anything-llm/pull/3130</a>\n</li>\n<li>Add improved logging and introspection to web-browsing by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3140\">https://github.com/Mintplex-Labs/anything-llm/pull/3140</a>\n</li>\n<li>[FEAT] Add Turkish Language Support (tr.js) #3108 by @TunahanDilercan in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3141\">https://github.com/Mintplex-Labs/anything-llm/pull/3141</a>\n</li>\n<li>[CHORE] Onboarding language translations by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3176\">https://github.com/Mintplex-Labs/anything-llm/pull/3176</a>\n</li>\n<li>fix UserMenu rendered twice on Main page by @sdeleeuw in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3110\">https://github.com/Mintplex-Labs/anything-llm/pull/3110</a>\n</li>\n<li>Add handling to reasoning models for Generic OpenAI connector by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3183\">https://github.com/Mintplex-Labs/anything-llm/pull/3183</a>\n</li>\n<li>Agent flow builder by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3077\">https://github.com/Mintplex-Labs/anything-llm/pull/3077</a>\n</li>\n<li>chore: rename Github to GitHub by @setchy in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3199\">https://github.com/Mintplex-Labs/anything-llm/pull/3199</a>\n</li>\n<li>chore: rename <code>Gitlab</code> to <code>GitLab</code> by @setchy in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3200\">https://github.com/Mintplex-Labs/anything-llm/pull/3200</a>\n</li>\n<li>Add <code>querySelectorAll</code> capability to web-scraping block by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3186\">https://github.com/Mintplex-Labs/anything-llm/pull/3186</a>\n</li>\n<li>Turkish translations by @cobanov in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3207\">https://github.com/Mintplex-Labs/anything-llm/pull/3207</a>\n</li>\n<li>OCR PDFs as fallback during upload by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3204\">https://github.com/Mintplex-Labs/anything-llm/pull/3204</a>\n</li>\n<li>Add OCR of image support by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3219\">https://github.com/Mintplex-Labs/anything-llm/pull/3219</a>\n</li>\n<li>feat(dataconnectors): support confluence personal access token by @lcgash in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3206\">https://github.com/Mintplex-Labs/anything-llm/pull/3206</a>\n</li>\n<li>fix agent builder move block bug by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3220\">https://github.com/Mintplex-Labs/anything-llm/pull/3220</a>\n</li>\n<li>Drop Node <code>canvas</code> for manual <code>sharp</code> conversion by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3221\">https://github.com/Mintplex-Labs/anything-llm/pull/3221</a>\n</li>\n<li>for projects in gitlab subgroup (#3075) by @t2tx in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3247\">https://github.com/Mintplex-Labs/anything-llm/pull/3247</a>\n</li>\n<li>Fix: fix text and format issues in Chinese documentation. by @alongLFB in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3249\">https://github.com/Mintplex-Labs/anything-llm/pull/3249</a>\n</li>\n<li>fix: sanitizeNamespace by @hakeemsyd in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3246\">https://github.com/Mintplex-Labs/anything-llm/pull/3246</a>\n</li>\n<li>fix: Patch agent flow to honor agent handler established provider by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3251\">https://github.com/Mintplex-Labs/anything-llm/pull/3251</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@TunahanDilercan made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3141\">https://github.com/Mintplex-Labs/anything-llm/pull/3141</a>\n</li>\n<li>@sdeleeuw made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3110\">https://github.com/Mintplex-Labs/anything-llm/pull/3110</a>\n</li>\n<li>@setchy made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3199\">https://github.com/Mintplex-Labs/anything-llm/pull/3199</a>\n</li>\n<li>@cobanov made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3207\">https://github.com/Mintplex-Labs/anything-llm/pull/3207</a>\n</li>\n<li>@lcgash made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3206\">https://github.com/Mintplex-Labs/anything-llm/pull/3206</a>\n</li>\n<li>@t2tx made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3247\">https://github.com/Mintplex-Labs/anything-llm/pull/3247</a>\n</li>\n<li>@alongLFB made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3249\">https://github.com/Mintplex-Labs/anything-llm/pull/3249</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.4.0...v1.7.4\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.4.0...v1.7.4</a></p>\n","assets":[]},{"id":197475018,"tag":"v1.4.0","author":"timothycarambat","name":"AnythingLLM 1.4.0","draft":false,"prerelease":false,"createdAt":"2025-01-29T20:03:20Z","publishedAt":"2025-01-29T23:40:58Z","markdown":"# 🧠 AnythingLLM is `<think>`ing....\r\n\r\n> [!Note]\r\n> **Desktop build of this release (1.7.3) are attached as binaries below**\r\n\r\n## Notable changes 🌟 \r\n- Better Agent calling UI\r\n<img width=\"1612\" alt=\"agent-ui\" src=\"https://github.com/user-attachments/assets/ac33824f-9e8e-4292-ac3c-9e48630cdcb0\" />\r\n\r\n- UI support for `<think>`ing models in chat response\r\n<img width=\"1612\" alt=\"think\" src=\"https://github.com/user-attachments/assets/0af37a48-0bf2-4da6-8980-5bba80afe555\" />\r\n\r\n## Misc Fixes and improvements 🔧 \r\n\r\n* Add Support for NVIDIA NIM by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2766\r\n* update chat model filters for openai by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2803\r\n* Fixed a typo in README by @logscore in https://github.com/Mintplex-Labs/anything-llm/pull/2805\r\n* Fix scraping failed bug in link/bulk link scrapers by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2807\r\n* Fix timestamp bug in embed widget by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2806\r\n* Redirect to default thread on thread deletion by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2808\r\n* Add support for hiding sidebar by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2809\r\n* Add vector search API endpoint by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2815\r\n* patch ZH typo by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2816\r\n* add Gitlab to watchable documents by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2817\r\n* Fix(2753): Replace React Router Navigate with window.location for SSO state refresh by @andydev404 in https://github.com/Mintplex-Labs/anything-llm/pull/2818\r\n* Docker Scout CI error by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2820\r\n* APIPie LLM provider improvements by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2695\r\n* Add thread name to workspaces get endpoint by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2822\r\n* Add new workspace user management endpoint by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2842\r\n* Add attachments to GenericOpenAI prompt by @wolfganghuse in https://github.com/Mintplex-Labs/anything-llm/pull/2831\r\n* Purge cached docs and remove docs from all workspaces on vectorDB/embedder changes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2819\r\n* LLM performance metric tracking by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2825\r\n* Append writable fields to dev API new workspace endpoint by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2843\r\n* Enable `default` roles to be able to use `attachments` but not upload documents by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2860\r\n* Add support for gemini authenticated models endpoint by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2868\r\n* Remove fine-tuning flow by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2872\r\n* fix wrong metadata assignment in MilvusProvider by @wolfganghuse in https://github.com/Mintplex-Labs/anything-llm/pull/2870\r\n* update ollama performance mode by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2874\r\n* Fix light mode table colors by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2873\r\n* Fix styles of ChangeWarningModal by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2876\r\n* Show scrollbar on rendered tables in chat by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2884\r\n* Fix typo in frontend for SearXNG agent setup by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2917\r\n* Normalize paths on files uploaded to prevent arbitrary file writes by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2905\r\n* Patch unauthorized access to other user's pfps by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2904\r\n* Audio file validations by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2902\r\n* Patch custom models endpoint by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2903\r\n* Add support for Google Generative AI (Gemini) embedder by @007900 in https://github.com/Mintplex-Labs/anything-llm/pull/2895\r\n* Return timestamps in OpenAI compat endpoints in proper format by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2921\r\n* Update README.md by @KPCOFGS in https://github.com/Mintplex-Labs/anything-llm/pull/2924\r\n* make `similarityResponse` object arguments and not positional by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2930\r\n* Reranker option for RAG by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2929\r\n* Update example ENV files by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2931\r\n* feat: add support for voyage-3-large and voyage-code-3 embedding models by @root-reindeer-flotilla in https://github.com/Mintplex-Labs/anything-llm/pull/2955\r\n* Add caching to Gemini /models by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2969\r\n* Support historical message image inputs/attachments for n+1 queries by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2919\r\n* Swap to GH `arm64` runner by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2980\r\n* Fix similarity score bug in lance/chroma dbs by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2986\r\n* Farsi (Persian) translations by @okaeiz in https://github.com/Mintplex-Labs/anything-llm/pull/2989\r\n* AI agent ui animation by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/2999\r\n* Display `thinking` in the prompt response - model agnostic by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3001\r\n* Fix stop generation button UI by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3011\r\n* Bump perplexity models by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3014\r\n* Dynamic fetching of TogetherAI models by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3017\r\n* Add Version to AzureOpenAI by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3023\r\n* Allow editing of LLM settings from workspace settings by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/2865\r\n* feat: update novita AI logo and default model by @jasonhp in https://github.com/Mintplex-Labs/anything-llm/pull/3037\r\n* [Chore] Add better data-handling for unknown providers by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3026\r\n* breakout latex plugin for delims by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3040\r\n* Remove native LLM option by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/3024\r\n* Add ability to disable default agent skills by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/3041\r\n\r\n## New Contributors\r\n* @logscore made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2805\r\n* @andydev404 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2818\r\n* @wolfganghuse made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2831\r\n* @007900 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2895\r\n* @root-reindeer-flotilla made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2955\r\n* @okaeiz made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/2989\r\n* @jasonhp made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/3037\r\n\r\n**Full Changelog**: https://github.com/Mintplex-Labs/anything-llm/compare/v1.3.0...v1.4.0","html":"<div class=\"markdown-heading\"><h1 class=\"heading-element\">🧠 AnythingLLM is <code>&lt;think&gt;</code>ing....</h1><a id=\"user-content--anythingllm-is-thinking\" class=\"anchor\" aria-label=\"Permalink: 🧠 AnythingLLM is &lt;think&gt;ing....\" href=\"#-anythingllm-is-thinking\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<blockquote>\n<p>[!Note]\n<strong>Desktop build of this release (1.7.3) are attached as binaries below</strong></p>\n</blockquote>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Notable changes 🌟</h2><a id=\"user-content-notable-changes-\" class=\"anchor\" aria-label=\"Permalink: Notable changes 🌟\" href=\"#notable-changes-\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Better Agent calling UI</li>\n</ul>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/ac33824f-9e8e-4292-ac3c-9e48630cdcb0\"><img width=\"1612\" alt=\"agent-ui\" src=\"https://github.com/user-attachments/assets/ac33824f-9e8e-4292-ac3c-9e48630cdcb0\" style=\"max-width: 100%;\"></a></p>\n<ul>\n<li>UI support for <code>&lt;think&gt;</code>ing models in chat response</li>\n</ul>\n<p><a target=\"_blank\" rel=\"noopener noreferrer\" href=\"https://github.com/user-attachments/assets/0af37a48-0bf2-4da6-8980-5bba80afe555\"><img width=\"1612\" alt=\"think\" src=\"https://github.com/user-attachments/assets/0af37a48-0bf2-4da6-8980-5bba80afe555\" style=\"max-width: 100%;\"></a></p>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">Misc Fixes and improvements 🔧</h2><a id=\"user-content-misc-fixes-and-improvements-\" class=\"anchor\" aria-label=\"Permalink: Misc Fixes and improvements 🔧\" href=\"#misc-fixes-and-improvements-\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>Add Support for NVIDIA NIM by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2766\">https://github.com/Mintplex-Labs/anything-llm/pull/2766</a>\n</li>\n<li>update chat model filters for openai by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2803\">https://github.com/Mintplex-Labs/anything-llm/pull/2803</a>\n</li>\n<li>Fixed a typo in README by @logscore in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2805\">https://github.com/Mintplex-Labs/anything-llm/pull/2805</a>\n</li>\n<li>Fix scraping failed bug in link/bulk link scrapers by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2807\">https://github.com/Mintplex-Labs/anything-llm/pull/2807</a>\n</li>\n<li>Fix timestamp bug in embed widget by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2806\">https://github.com/Mintplex-Labs/anything-llm/pull/2806</a>\n</li>\n<li>Redirect to default thread on thread deletion by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2808\">https://github.com/Mintplex-Labs/anything-llm/pull/2808</a>\n</li>\n<li>Add support for hiding sidebar by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2809\">https://github.com/Mintplex-Labs/anything-llm/pull/2809</a>\n</li>\n<li>Add vector search API endpoint by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2815\">https://github.com/Mintplex-Labs/anything-llm/pull/2815</a>\n</li>\n<li>patch ZH typo by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2816\">https://github.com/Mintplex-Labs/anything-llm/pull/2816</a>\n</li>\n<li>add Gitlab to watchable documents by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2817\">https://github.com/Mintplex-Labs/anything-llm/pull/2817</a>\n</li>\n<li>Fix(2753): Replace React Router Navigate with window.location for SSO state refresh by @andydev404 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2818\">https://github.com/Mintplex-Labs/anything-llm/pull/2818</a>\n</li>\n<li>Docker Scout CI error by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2820\">https://github.com/Mintplex-Labs/anything-llm/pull/2820</a>\n</li>\n<li>APIPie LLM provider improvements by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2695\">https://github.com/Mintplex-Labs/anything-llm/pull/2695</a>\n</li>\n<li>Add thread name to workspaces get endpoint by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2822\">https://github.com/Mintplex-Labs/anything-llm/pull/2822</a>\n</li>\n<li>Add new workspace user management endpoint by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2842\">https://github.com/Mintplex-Labs/anything-llm/pull/2842</a>\n</li>\n<li>Add attachments to GenericOpenAI prompt by @wolfganghuse in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2831\">https://github.com/Mintplex-Labs/anything-llm/pull/2831</a>\n</li>\n<li>Purge cached docs and remove docs from all workspaces on vectorDB/embedder changes by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2819\">https://github.com/Mintplex-Labs/anything-llm/pull/2819</a>\n</li>\n<li>LLM performance metric tracking by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2825\">https://github.com/Mintplex-Labs/anything-llm/pull/2825</a>\n</li>\n<li>Append writable fields to dev API new workspace endpoint by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2843\">https://github.com/Mintplex-Labs/anything-llm/pull/2843</a>\n</li>\n<li>Enable <code>default</code> roles to be able to use <code>attachments</code> but not upload documents by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2860\">https://github.com/Mintplex-Labs/anything-llm/pull/2860</a>\n</li>\n<li>Add support for gemini authenticated models endpoint by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2868\">https://github.com/Mintplex-Labs/anything-llm/pull/2868</a>\n</li>\n<li>Remove fine-tuning flow by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2872\">https://github.com/Mintplex-Labs/anything-llm/pull/2872</a>\n</li>\n<li>fix wrong metadata assignment in MilvusProvider by @wolfganghuse in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2870\">https://github.com/Mintplex-Labs/anything-llm/pull/2870</a>\n</li>\n<li>update ollama performance mode by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2874\">https://github.com/Mintplex-Labs/anything-llm/pull/2874</a>\n</li>\n<li>Fix light mode table colors by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2873\">https://github.com/Mintplex-Labs/anything-llm/pull/2873</a>\n</li>\n<li>Fix styles of ChangeWarningModal by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2876\">https://github.com/Mintplex-Labs/anything-llm/pull/2876</a>\n</li>\n<li>Show scrollbar on rendered tables in chat by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2884\">https://github.com/Mintplex-Labs/anything-llm/pull/2884</a>\n</li>\n<li>Fix typo in frontend for SearXNG agent setup by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2917\">https://github.com/Mintplex-Labs/anything-llm/pull/2917</a>\n</li>\n<li>Normalize paths on files uploaded to prevent arbitrary file writes by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2905\">https://github.com/Mintplex-Labs/anything-llm/pull/2905</a>\n</li>\n<li>Patch unauthorized access to other user's pfps by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2904\">https://github.com/Mintplex-Labs/anything-llm/pull/2904</a>\n</li>\n<li>Audio file validations by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2902\">https://github.com/Mintplex-Labs/anything-llm/pull/2902</a>\n</li>\n<li>Patch custom models endpoint by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2903\">https://github.com/Mintplex-Labs/anything-llm/pull/2903</a>\n</li>\n<li>Add support for Google Generative AI (Gemini) embedder by @007900 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2895\">https://github.com/Mintplex-Labs/anything-llm/pull/2895</a>\n</li>\n<li>Return timestamps in OpenAI compat endpoints in proper format by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2921\">https://github.com/Mintplex-Labs/anything-llm/pull/2921</a>\n</li>\n<li>Update README.md by @KPCOFGS in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2924\">https://github.com/Mintplex-Labs/anything-llm/pull/2924</a>\n</li>\n<li>make <code>similarityResponse</code> object arguments and not positional by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2930\">https://github.com/Mintplex-Labs/anything-llm/pull/2930</a>\n</li>\n<li>Reranker option for RAG by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2929\">https://github.com/Mintplex-Labs/anything-llm/pull/2929</a>\n</li>\n<li>Update example ENV files by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2931\">https://github.com/Mintplex-Labs/anything-llm/pull/2931</a>\n</li>\n<li>feat: add support for voyage-3-large and voyage-code-3 embedding models by @root-reindeer-flotilla in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2955\">https://github.com/Mintplex-Labs/anything-llm/pull/2955</a>\n</li>\n<li>Add caching to Gemini /models by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2969\">https://github.com/Mintplex-Labs/anything-llm/pull/2969</a>\n</li>\n<li>Support historical message image inputs/attachments for n+1 queries by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2919\">https://github.com/Mintplex-Labs/anything-llm/pull/2919</a>\n</li>\n<li>Swap to GH <code>arm64</code> runner by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2980\">https://github.com/Mintplex-Labs/anything-llm/pull/2980</a>\n</li>\n<li>Fix similarity score bug in lance/chroma dbs by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2986\">https://github.com/Mintplex-Labs/anything-llm/pull/2986</a>\n</li>\n<li>Farsi (Persian) translations by @okaeiz in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2989\">https://github.com/Mintplex-Labs/anything-llm/pull/2989</a>\n</li>\n<li>AI agent ui animation by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2999\">https://github.com/Mintplex-Labs/anything-llm/pull/2999</a>\n</li>\n<li>Display <code>thinking</code> in the prompt response - model agnostic by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3001\">https://github.com/Mintplex-Labs/anything-llm/pull/3001</a>\n</li>\n<li>Fix stop generation button UI by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3011\">https://github.com/Mintplex-Labs/anything-llm/pull/3011</a>\n</li>\n<li>Bump perplexity models by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3014\">https://github.com/Mintplex-Labs/anything-llm/pull/3014</a>\n</li>\n<li>Dynamic fetching of TogetherAI models by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3017\">https://github.com/Mintplex-Labs/anything-llm/pull/3017</a>\n</li>\n<li>Add Version to AzureOpenAI by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3023\">https://github.com/Mintplex-Labs/anything-llm/pull/3023</a>\n</li>\n<li>Allow editing of LLM settings from workspace settings by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2865\">https://github.com/Mintplex-Labs/anything-llm/pull/2865</a>\n</li>\n<li>feat: update novita AI logo and default model by @jasonhp in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3037\">https://github.com/Mintplex-Labs/anything-llm/pull/3037</a>\n</li>\n<li>[Chore] Add better data-handling for unknown providers by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3026\">https://github.com/Mintplex-Labs/anything-llm/pull/3026</a>\n</li>\n<li>breakout latex plugin for delims by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3040\">https://github.com/Mintplex-Labs/anything-llm/pull/3040</a>\n</li>\n<li>Remove native LLM option by @shatfield4 in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3024\">https://github.com/Mintplex-Labs/anything-llm/pull/3024</a>\n</li>\n<li>Add ability to disable default agent skills by @timothycarambat in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3041\">https://github.com/Mintplex-Labs/anything-llm/pull/3041</a>\n</li>\n</ul>\n<div class=\"markdown-heading\"><h2 class=\"heading-element\">New Contributors</h2><a id=\"user-content-new-contributors\" class=\"anchor\" aria-label=\"Permalink: New Contributors\" href=\"#new-contributors\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a></div>\n<ul>\n<li>@logscore made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2805\">https://github.com/Mintplex-Labs/anything-llm/pull/2805</a>\n</li>\n<li>@andydev404 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2818\">https://github.com/Mintplex-Labs/anything-llm/pull/2818</a>\n</li>\n<li>@wolfganghuse made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2831\">https://github.com/Mintplex-Labs/anything-llm/pull/2831</a>\n</li>\n<li>@007900 made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2895\">https://github.com/Mintplex-Labs/anything-llm/pull/2895</a>\n</li>\n<li>@root-reindeer-flotilla made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2955\">https://github.com/Mintplex-Labs/anything-llm/pull/2955</a>\n</li>\n<li>@okaeiz made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/2989\">https://github.com/Mintplex-Labs/anything-llm/pull/2989</a>\n</li>\n<li>@jasonhp made their first contribution in <a href=\"https://github.com/Mintplex-Labs/anything-llm/pull/3037\">https://github.com/Mintplex-Labs/anything-llm/pull/3037</a>\n</li>\n</ul>\n<p><strong>Full Changelog</strong>: <a href=\"https://github.com/Mintplex-Labs/anything-llm/compare/v1.3.0...v1.4.0\">https://github.com/Mintplex-Labs/anything-llm/compare/v1.3.0...v1.4.0</a></p>\n","assets":[{"contentType":"application/x-msdownload","size":403977021,"createdAt":"2025-02-06T05:35:02Z","updatedAt":"2025-02-06T05:35:22Z","downloadCount":1252,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/AnythingLLMDesktop-Arm64.exe"},{"contentType":"application/x-apple-diskimage","size":329834540,"createdAt":"2025-02-06T05:35:22Z","updatedAt":"2025-02-06T05:35:38Z","downloadCount":2640,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/AnythingLLMDesktop-Silicon.dmg"},{"contentType":"application/octet-stream","size":287978309,"createdAt":"2025-02-06T05:35:38Z","updatedAt":"2025-02-06T05:35:53Z","downloadCount":1611,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/AnythingLLMDesktop.AppImage"},{"contentType":"application/x-apple-diskimage","size":329672149,"createdAt":"2025-02-06T05:35:53Z","updatedAt":"2025-02-06T05:36:11Z","downloadCount":1026,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/AnythingLLMDesktop.dmg"},{"contentType":"application/x-msdownload","size":296284295,"createdAt":"2025-02-06T05:36:12Z","updatedAt":"2025-02-06T05:36:27Z","downloadCount":19420,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/AnythingLLMDesktop.exe"},{"contentType":"text/x-sh","size":1455,"createdAt":"2025-02-06T05:36:27Z","updatedAt":"2025-02-06T05:36:27Z","downloadCount":634,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/installer.sh"},{"contentType":"text/plain","size":8,"createdAt":"2025-02-06T05:36:27Z","updatedAt":"2025-02-06T05:36:27Z","downloadCount":439,"downloadUrl":"https://github.com/Mintplex-Labs/anything-llm/releases/download/v1.4.0/version.txt"}]}]}