From 592a6213b9981883755dcf8b16c9f952b4d350c8 Mon Sep 17 00:00:00 2001 From: Timothy Jaeryang Baek Date: Fri, 9 Jan 2026 21:00:30 +0400 Subject: [PATCH] doc: changelog --- CHANGELOG.md | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 78f3e60909..0ddf463f29 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,24 +5,23 @@ All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [0.7] - 2026-01-09 +## [0.7.0] - 2026-01-09 ### Added -- πŸ€– When configured for agentic mode, AI models independently research topics by searching the web multiple times, fetching and analyzing web pages, managing their own memory, and generating images without waiting for user prompts, transforming conversations from simple Q&A into dynamic research sessions where the AI proactively investigates and synthesizes information across multiple sources. [#19397](https://github.com/open-webui/open-webui/issues/19397), [Commit](https://github.com/open-webui/open-webui/commit/5c1d52231a3997a17381c48639bd7e339262cf7c) -- 🧠 Models in agentic mode autonomously search through your notes, past conversations, channels, and messages to find relevant context, calculate timestamps for temporal queries, and access your complete communication history without explicit commands, turning AI into a self-sufficient research assistant that knows when and where to look for information. [Commit](https://github.com/open-webui/open-webui/commit/646835d76744ad9b2e67ede0407a61d62e969aab) -- πŸ“š Models in agentic mode proactively list accessible knowledge bases, search files by name, retrieve full document contents, and perform semantic vector searches across your entire knowledge repository to find relevant information autonomously, eliminating the need to manually specify which documents to reference. [Commit](https://github.com/open-webui/open-webui/commit/c8622adcb01f3091b17ca50f8c8e2f20c7b9cd2a) -- πŸ’­ Models with interleaved thinking support can now reason and reflect between tool calls, analyzing search results before deciding what to search for next, leading to dramatically more focused and effective multi-step research as the AI refines its strategy based on what it learns. -- πŸ” When AI models autonomously search the web in agentic mode, users see every search result as clickable citations in real-time, making the AI's research process completely transparent and allowing full verification of sources even when the model initiates searches independently. [Commit](https://github.com/open-webui/open-webui/commit/2789f6a24d8405c30cd48ae460071f6a4f2c35f9) -- πŸ“– When AI models autonomously query knowledge bases in agentic mode, every retrieved file and content chunk appears as grouped, clickable citations showing exactly which documents informed the response, with sources automatically organized by origin for easy verification. [#20380](https://github.com/open-webui/open-webui/pull/20380), [Commit](https://github.com/open-webui/open-webui/commit/ab400e3eae569a5e09fe391d4b4bab104423bb0b) -- 🎚️ Users can now selectively disable built-in agentic tools for individual models through the model editor's capabilities settings, allowing precise control over which models can autonomously access timestamps, memory, chat history, notes, web search, and knowledge bases. [Commit](https://github.com/open-webui/open-webui/commit/60e916d6c0c5f7db9e6d670e12be2d1d4abc2dd6) -- πŸ‘οΈ Users now see exactly which agentic tools are being invoked as AI models work, with pending tool calls displayed during response generation so it's always clear the system is actively researching rather than frozen or stuck. [Commit](https://github.com/open-webui/open-webui/commit/1d08376860e775049abd1dd5f568ac0c6466c944) +- πŸ€– **Native Function Calling with Built-in Tools.** Models with native function calling support can now use a suite of built-in tools when function calling mode is set to "Native" in Chat Controlsβ€”including web search, web page fetching, memory management, and image generationβ€”enabling multi-step research workflows where the model autonomously decides which tools to invoke. [#19397](https://github.com/open-webui/open-webui/issues/19397), [Commit](https://github.com/open-webui/open-webui/commit/5c1d52231a3997a17381c48639bd7e339262cf7c) +- 🧠 Built-in tools for native function calling now include access to notes, past conversations, channels, and messages, allowing models to search your communication history and retrieve relevant context when needed. [Commit](https://github.com/open-webui/open-webui/commit/646835d76744ad9b2e67ede0407a61d62e969aab) +- πŸ“š Built-in tools for native function calling now include knowledge base accessβ€”models can list available knowledge bases, search files by name, retrieve document contents, and perform semantic vector searches without requiring you to manually attach files. [Commit](https://github.com/open-webui/open-webui/commit/c8622adcb01f3091b17ca50f8c8e2f20c7b9cd2a) +- πŸ’­ Users with models that support interleaved thinking now get more refined results from native function calling workflows with built-in tools, as the model can analyze each tool's output before deciding what to do next instead of executing all tools blindly. +- πŸ” When models invoke web search via native function calling, search results appear as clickable citations in real-time for full source verification. [Commit](https://github.com/open-webui/open-webui/commit/2789f6a24d8405c30cd48ae460071f6a4f2c35f9) +- 🎚️ Users can selectively disable specific built-in tools (timestamps, memory, chat history, notes, web search, knowledge bases) per model via the model editor's capabilities settings. [Commit](https://github.com/open-webui/open-webui/commit/60e916d6c0c5f7db9e6d670e12be2d1d4abc2dd6) +- πŸ‘οΈ Pending tool calls are now displayed during response generation, showing which tools are being invoked so users know the system is working. [Commit](https://github.com/open-webui/open-webui/commit/1d08376860e775049abd1dd5f568ac0c6466c944) +- πŸ“ Administrators can now limit the number of files that can be uploaded to folders using the "FOLDER_MAX_FILE_COUNT" setting, preventing resource exhaustion from bulk uploads. [#19810](https://github.com/open-webui/open-webui/issues/19810), [Commit](https://github.com/open-webui/open-webui/commit/a1036e544d573e3d35e05c1c2472ba762c32431b), [Commit](https://github.com/open-webui/open-webui/commit/d3ee3fd23e762c9d83fe1da5636d03259e186e57) - ⚑ Users experience transformative speed improvements across the entire application through completely reengineered database connection handling, delivering noticeably faster page loads, butter-smooth interactions, and rock-solid stability during intensive operations like user management and bulk data processing. [Commit](https://github.com/open-webui/open-webui/commit/2041ab483e21b3a757baa25c47dc2fa29018674f), [Commit](https://github.com/open-webui/open-webui/commit/145c7516f227ce56fd52373cee86217fadf16181), [Commit](https://github.com/open-webui/open-webui/commit/475dd91ed798f2efcdf27799d5c5cae3f0e6e847), [Commit](https://github.com/open-webui/open-webui/commit/5d1459df166cce8445eb1556cc26abbd65a3f9f4), [Commit](https://github.com/open-webui/open-webui/commit/2453b75ff0fb2dc75b929d96f417d84e332922d9), [Commit](https://github.com/open-webui/open-webui/commit/5649a668fad15393a52c27a2f188841af8b66989) - πŸš€ Users experience significantly faster initial page load times through dynamic loading of document processing libraries, reducing the initial bundle size. [#20200](https://github.com/open-webui/open-webui/pull/20200), [#20202](https://github.com/open-webui/open-webui/pull/20202), [#20203](https://github.com/open-webui/open-webui/pull/20203), [#20204](https://github.com/open-webui/open-webui/pull/20204) - πŸ’¨ Administrators experience dramatically faster user list loading through optimized database queries that eliminate N+1 query patterns, reducing query count from 1+N to just 2 total queries regardless of user count. [#20427](https://github.com/open-webui/open-webui/pull/20427) - πŸ“‹ Notes now load faster through optimized database queries that batch user lookups instead of fetching each note's author individually. [Commit](https://github.com/open-webui/open-webui/commit/084f0ef6a5491e186bf6b71c6386973ba18ef2fa) - πŸ’¬ Channel messages, pinned messages, and thread replies now load faster through batched user lookups instead of individual queries per message. [#20458](https://github.com/open-webui/open-webui/pull/20458), [#20459](https://github.com/open-webui/open-webui/pull/20459), [#20460](https://github.com/open-webui/open-webui/pull/20460) -- πŸ“Š Users can now sync their chat statistics to create public profile pages on the Open WebUI Community website or download them as JSON files, with incremental synchronization by default and an administrator option to disable the feature. [Commit](https://github.com/open-webui/open-webui/commit/4be99174be505b187812e0b48b9f9f7bf6897c52), [Commit](https://github.com/open-webui/open-webui/commit/df106099a159f8cf7910a89c50338ec045a78e61), [Commit](https://github.com/open-webui/open-webui/commit/9c61e95ecba071f5a99d93d1b1c5d17b80159329), [Commit](https://github.com/open-webui/open-webui/commit/85bbed3ec539dc958d306117f97d6be977b7253b), [Commit](https://github.com/open-webui/open-webui/commit/459cfde1f80e76618fb7fb75318d8daf2ccf1590), [Commit](https://github.com/open-webui/open-webui/commit/37b15604de0eaa5bfde378f12ac2d94c7aab60b9), [Commit](https://github.com/open-webui/open-webui/commit/71ca25c8ac4ad97b5a52016a5b2f385b333bd480) - πŸ”— Users can now click citation content links to jump directly to the relevant portion of source documents with automatic text highlighting, making it easier to verify AI responses against their original sources. [#20116](https://github.com/open-webui/open-webui/pull/20116), [Commit](https://github.com/open-webui/open-webui/commit/40c45ffe1f9b45538d32c8ecba8cac62c6eca503) - πŸ“Œ Users can now pin or hide models directly from the Workspace Models page and Admin Settings Models page, making it easier to manage which models appear in the sidebar without switching to the chat interface. [#20176](https://github.com/open-webui/open-webui/pull/20176) - πŸ”Ž Administrators can now quickly find settings using the new search bar in the Admin Settings sidebar, which supports fuzzy filtering by category names and related keywords like "whisper" for Audio or "rag" for Documents. [#20434](https://github.com/open-webui/open-webui/pull/20434) @@ -31,6 +30,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - πŸ”§ Users can now view read-only tools in the workspace tools list, with clear "Read Only" badges indicating when editing is restricted. [#20243](https://github.com/open-webui/open-webui/issues/20243), [#20370](https://github.com/open-webui/open-webui/pull/20370) - πŸ“‚ Searching for files is now significantly faster, especially for users with large file collections. [Commit](https://github.com/open-webui/open-webui/commit/a9a979fb3db1743553ca0705f571c0b9c252841f) - πŸ† The Evaluations leaderboard now calculates Elo ratings on the backend instead of in the browser, improving performance and enabling topic-based model ranking through semantic search. [#15392](https://github.com/open-webui/open-webui/pull/15392), [#20476](https://github.com/open-webui/open-webui/issues/20476), [Commit](https://github.com/open-webui/open-webui/commit/10838b3654bf6fdef02d57311f7f1c01df4cd033) +- πŸ“Š The Evaluations leaderboard now includes a per-model activity chart displaying daily wins and losses as a diverging bar chart, with 30-day, 1-year, and all-time views using weekly aggregation for longer timeframes. - 🎞️ Users can now upload animated GIF and WebP formats as model profile images, with animation preserved by skipping resize processing for these file types. [Commit](https://github.com/open-webui/open-webui/commit/00af37bb4ed1ea0957c7c84a6a8def3a7998b8ca) - πŸ“Έ Users uploading profile images for users, models, and arena models now benefit from WebP compression at 80% quality instead of JPEG, resulting in significantly smaller file sizes and faster uploads while maintaining visual quality. [Commit](https://github.com/open-webui/open-webui/commit/b1d30673b69571e081abb881d34944cf33cdc67e) - ⭐ Action Function developers can now update message favorite status using the new "chat:message:favorite" event, enabling the development of pin/unpin message actions without race conditions from frontend auto-save. [#20375](https://github.com/open-webui/open-webui/pull/20375) @@ -41,7 +41,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - 🧩 Administrators can now set a minimum chunk size target using the "CHUNK_MIN_SIZE_TARGET" setting to merge small markdown header chunks with neighbors, which improves retrieval quality by eliminating tiny meaningless fragments, significantly speeds up document processing and embedding, reduces storage costs, and lowers embedding API costs or local compute requirements. [#19595](https://github.com/open-webui/open-webui/issues/19595), [#20314](https://github.com/open-webui/open-webui/pull/20314), [Commit](https://github.com/open-webui/open-webui/commit/c32435958073cf002d87e78544baa88bc4e15d7f) - πŸ’¨ Administrators can now enable KV prefix caching optimization by setting "RAG_SYSTEM_CONTEXT" to true, which injects RAG context into the system message instead of user messages, enabling models to reuse cached tokens for follow-up questions instead of reprocessing the entire context on each turn, significantly improving response times and reducing costs for cloud-based models. [#20301](https://github.com/open-webui/open-webui/discussions/20301), [#20317](https://github.com/open-webui/open-webui/pull/20317) - πŸ–ΌοΈ Administrators and Action developers can now control image generation denoising steps per-request using a steps parameter, allowing Actions and API calls to override the global IMAGE_STEPS configuration for both ComfyUI and Automatic1111 engines. [#20337](https://github.com/open-webui/open-webui/pull/20337) -- πŸ“ Administrators can now limit the number of files that can be uploaded to folders using the "FOLDER_MAX_FILE_COUNT" setting, preventing resource exhaustion from bulk uploads. [#19810](https://github.com/open-webui/open-webui/issues/19810), [Commit](https://github.com/open-webui/open-webui/commit/a1036e544d573e3d35e05c1c2472ba762c32431b), [Commit](https://github.com/open-webui/open-webui/commit/d3ee3fd23e762c9d83fe1da5636d03259e186e57) - πŸ—„οΈ Administrators running multi-pod deployments can now designate a master pod to handle database migrations using the "ENABLE_DB_MIGRATIONS" environment variable. [Commit](https://github.com/open-webui/open-webui/commit/9824f0e33359a917ac07b60bf1f972074d5c8203) - πŸŽ™οΈ Administrators can now configure Whisper's compute type using the "WHISPER_COMPUTE_TYPE" environment variable to fix compatibility issues with CUDA/GPU deployments. [Commit](https://github.com/open-webui/open-webui/commit/26af1f92e21ddfd08348570bf54a6f345ac69648) - πŸ” Administrators can now control sigmoid normalization for CrossEncoder reranking models using the "SENTENCE_TRANSFORMERS_CROSS_ENCODER_SIGMOID_ACTIVATION_FUNCTION" environment variable, enabled by default for proper relevance threshold behavior with MS MARCO models. [#20228](https://github.com/open-webui/open-webui/pull/20228) @@ -53,7 +52,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - πŸͺ Channel managers can now create webhooks to allow external services to post messages to channels without authentication. [Commit](https://github.com/open-webui/open-webui/commit/cd296fcf0d79cecd1a6a3ee4e492c6b5246ca7ae) - πŸ“„ In the model editor users can now disable the "File Context" capability to skip automatic file content extraction and injection, forwarding raw messages with file attachment metadata instead for use with custom tools or future built-in file access tools. [Commit](https://github.com/open-webui/open-webui/commit/daccf0713e3ecd6d24f003a87b5f8b3c61852958), [Docs:Commit](https://github.com/open-webui/docs/commit/18ec6eaefc071a278ec57d4d1b8d66d686af0870) - πŸ”Š In the model editor users can now configure a specific TTS voice for each model, overriding user preferences and global defaults to give different AI personas distinct voices. [#3097](https://github.com/open-webui/open-webui/issues/3097), [Commit](https://github.com/open-webui/open-webui/commit/bb6188abf04302f79d80b0d6cc42c232624b5757) -- πŸ• User timezones are now automatically detected and stored on login, enabling accurate timestamp handling for time-sensitive features. [Commit](https://github.com/open-webui/open-webui/commit/401c1949a04dfd1bcc3c8b9a4f77b73beb78b818) - πŸ‘₯ Administrators now have three granular group sharing permission options instead of a simple on/off toggle, allowing them to choose between "No one", "Members", or "Anyone" for who can share content to each group. [Commit](https://github.com/open-webui/open-webui/commit/ca514cd3eda2524b8da472ef17c0ccb216bac2e8) - πŸ“¦ Administrators can now export knowledge bases as zip files containing text files for backup and archival purposes. [#20120](https://github.com/open-webui/open-webui/issues/20120), [Commit](https://github.com/open-webui/open-webui/commit/c1147578c073a8c7fa7e7f836149e1cdfec8f18d) - πŸš€ Administrators can now create an admin account automatically at startup via "WEBUI_ADMIN_EMAIL", "WEBUI_ADMIN_PASSWORD", and "WEBUI_ADMIN_NAME" environment variables, enabling headless and automated deployments without exposing the signup page. [#17654](https://github.com/open-webui/open-webui/issues/17654), [Commit](https://github.com/open-webui/open-webui/commit/1138929f4d083931305f1f925899971b190562ae) @@ -62,6 +60,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - πŸ”₯ Administrators can now configure Firecrawl timeout values using the "FIRECRAWL_TIMEOUT" environment variable to control web scraping wait times. [#19973](https://github.com/open-webui/open-webui/pull/19973), [Commit](https://github.com/open-webui/open-webui/commit/89ad1c68d1aadf849960b5e202aa4651096b05f5) - πŸ’Ύ Administrators can now use openGauss as the vector database backend for knowledge base document storage and retrieval. [#20179](https://github.com/open-webui/open-webui/pull/20179) - πŸ”„ Various improvements were implemented across the application to enhance performance, stability, and security. +- πŸ“Š Users can now sync their anonymous usage statistics to the Open WebUI Community platform to power community leaderboards, drive model evaluations, and contribute to open-source AI research that benefits everyone, all while keeping conversations completely private (only metadata like model names, message counts, and ratings are shared). By sharing your stats, you're helping the community identify which models perform best, contributing to transparent AI benchmarking, and supporting the collective effort to make AI better for all. You can also download your stats as JSON for personal analysis. - 🌐 Translations for German, Portuguese (Brazil), Spanish, Simplified Chinese, Traditional Chinese, and Polish were enhanced and expanded. ### Fixed