Open WebUI

Key highlights in this release include:

• 📄 Support for MinerU as a document parser backend
• 🔒 JWT token expiration now defaults to 4 weeks
• ⚡ Improved page loading performance
• 📁 File hash values included in knowledge endpoint responses
• 🎨 Enhanced chat dialog scrollbar visibility

⚠️ System prompts are no longer duplicated in chat requests, which may affect some existing workflows.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• 🎨 Comprehensive redesign of workspace interface
• ⚡ Significant improvements in page initialization and chat performance
• 📁 New folder attachment feature for chats
• 📱 Android share target support for Progressive Web App
• 📊 Support for Vega and Vega-Lite chart visualizations
• 🔗 Custom HTTP headers for OpenAI connections
• 🤖 Enhancements to Ollama model management
• 📊 New layout options for chat overview flow diagram
• 🔢 Support for Ollama embedding dimensions parameter
• 📄 Improvements to PDF exports and document extraction

⚠️ System prompts are no longer duplicated in chat requests, which may affect some existing workflows.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• 🗝️ Added permission toggle for public sharing of notes
• ⚠️ Added warning for conflicting group permissions in user edit modal
• 🧬 Improved MCP tool result handling
• 🧩 Overhauled user edit modal for better usability
• 🛠️ Fixed issues with External Tool servers and OAuth 2.1 integrations
• 🐛 Resolved UI bugs in model and filter selection menus
• 🛠️ Improved embed UI functionality for tool embedding

⚠️ Channel permissions now require write access for message posting, editing, and deletion. Existing user groups default to read-only access, requiring manual admin migration for full participation.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• 🔌 Added support for MCP (streamable HTTP) servers alongside OpenAPI servers
• 🔐 Implemented OAuth 2.1 dynamic client registration for MCP server authentication
• 🛠️ External & Built-In Tools now support rich UI element embedding
• 📝 Note editor now supports drag-and-drop reordering of list items
• 🔍 Enhanced search modal with quick action buttons
• 👥 Improved channel access control with write permissions for posting and editing
• 💬 Channel models now support image processing
• 🌐 Added Attach Webpage button to message input menu
• 🔍 Added Ollama Cloud and Perplexity Websearch API integrations
• ☁️ Improved OneDrive integration with separate client IDs for personal and business
• 🎨 Modernized interface design with updated visual styling
• ⚡ Optimized page loading and query performance
• 🔄 Various improvements to enhance performance, stability, and security
• 🌐 Enhanced translations for multiple languages

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• ✨ Redesigned chat input with unified attachments and streamlined options
• 🤖 AI models can be mentioned in channels for automatic threaded responses
• 📝 Rich text editor in channels with command and mention suggestions
• 📎 Direct paste support for images and files in messages
• ⚙️ Configurable default features, filters, and model-level settings
• 🔗 Ability to reference other chats as context in conversations
• 🎨 Enhanced folders with backgrounds, emoji icons, and better interactions
• ☁️ OneDrive integration with personal/work account selection
• 📤 Export individual chats as PDFs from sidebar
• 🔐 Feishu SSO and improved OAuth token management for security
• 🌐 Enhanced web search result display with titles and favicons
• 🖼️ Azure OpenAI image generation support
• 🗂️ Improved knowledge base permissions and access control
• 🔑 Microsoft Entra ID authentication type support was added for Azure OpenAI connections
• 🐛 Various bug fixes, improved performance, and better error handling

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• 🛂 Granular Chat Interaction Permissions
• 🧠 Custom Reasoning Tags Configuration
• 📱 Pull-to-Refresh Support
• 📁 Configurable File Upload Processing Mode
• 🔐 Azure Document Intelligence DefaultAzureCredential Support
• 🔐 Authentication Bootstrapping Enhancements
• ⚡ Query Generation Caching
• 🔧 Configurable Tool Call Retry Limit
• 📦 Slim Docker Image Variant
• 🗂️ Shift-to-Delete Functionality for Workspace Prompts
• ♿ Accessibility Enhancements
• 📄 Optimized PDF Export for Smaller File Size
• 📦 Slimmed Default Install with Optional Full Dependencies
• 🔄 General Backend Refactoring
• 🌐 Localization & Internationalization Improvements
• 🐛 Various bug fixes and performance improvements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• OpenAI API '/v1' Endpoint Compatibility for better integration with tools expecting OpenAI's API structure
• Toggle for Guided Response Regeneration Menu in Interface settings
• General UI/UX Enhancements for improved visual consistency
• Localization & Internationalization Improvements including support for Kabyle language
• Fixed issues with OpenAI error message propagation, Pinecone insertion, s3vector functionality, and landing page option setting
• Resolved critical chat completion 'model_id' error after upgrading
• Improved audit log user information logging and OpenTelemetry configuration consistency
• Fixed reply input content display and refined translations for multiple languages

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Users Not Loading in Groups issue resolved
• Dedicated Folder View with Chat List for easier navigation
• Streamlined Folder Creation Modal for intuitive workspace organization
• Direct File Uploads to Folder Knowledge
• Chat Preview in Search for faster discovery
• Image Upload and Inline Insertion in Notes
• Enhanced Note Selection Editing and Q&A
• Copy Notes as Rich Text for seamless sharing
• Fade-In Streaming Text Experience for more engaging reading
• Settings for Follow-Up Prompts to customize workflow
• Prompt Variable Documentation Quick Link for easier advanced prompt-building
• Active and Total User Metrics for Telemetry
• Traceability with Log Trace and Span IDs for better troubleshooting
• User Group Add/Remove Endpoints for easier collaboration management
• Note Settings and Controls Streamlined
• Faster Admin User Page Loads
• Chat ID Header Forwarding for better request correlation
• Enhanced Reasoning Tag Processing for better AI transparency
• OAuth Token Endpoint Authentication Method for enhanced security options
• Redis Sentinel High Availability Support for continuous service availability
• Localization & Internationalization Improvements for global users

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Folders as Projects for organizing workflows with folder-level system prompts and custom knowledge
• Instant Folder-Based Chat Creation for quick context-aware conversations
• Prompt Variables with Automatic Input Modal for easier value entry
• Variable Input Typing in Prompts for more precise prompt-building
• Base Model List Caching to speed up model selection
• Reference Notes as Knowledge or in Chats for better integration of documentation
• Collaborative Notes with Multi-User Editing for real-time cooperation
• Task List Support in Notes for project planning and to-do tracking
• AI-Generated Note Titles for effortless organization
• Full Undo/Redo Support in Notes
• Rich Text Prompt Insertion for more intuitive editing
• Configurable Database URL for flexible deployment
• Frontend-Handled File Upload in Temporary Chats for enhanced privacy
• Mobile Experience Polished for better usability on phones and tablets
• OpenDocument Text (.odt) Support for wider document compatibility
• Enhanced Markdown Document Splitting for improved knowledge retrieval
• Configurable OAuth Timeout for better login reliability
• Accessibility & High-Contrast Theme Enhancements for improved readability
• Granular Update Check Control for environments with restricted internet access

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Global Image Compression Option to optimize all image uploads and outputs for faster load times
• Custom Speech-to-Text Content-Type for better audio transcription compatibility
• User Message Timestamps on Hover in Chat Bubble UI for better context
• Leaderboard Sorting Options for clearer analysis of top performers
• Evaluation Details Modal for deeper insights into feedbacks and rankings
• Support for Multiple Pages in External Document Loaders
• New Accessibility Enhancements including better tab navigation and ARIA support
• Performance and Stability Upgrades across frontend and backend
• Updated and Expanded Localizations for multiple languages
• More descriptive Ollama error messages for better troubleshooting
• Fixed issues with webloader bypass, citation duplicates, and OAuth callbacks
• Dedicated Permission for System Prompts for enhanced security control

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Automatic "Follow Up" Suggestions that intelligently generate actionable suggestions with each message
• OpenAI-Compatible Embeddings Endpoint for seamless integration with external tools
• Model Pinning for Quick Access to your favorite models in the sidebar
• Reliable Stop for Ongoing Chats in Multi-Replica Setups
• 'Think' Parameter support for Ollama Models for advanced reasoning control
• Picture Description Modes for Docling to customize image extraction
• Settings Modal Deep Linking for direct navigation to specific settings
• Audio HTML Component Token for embedding audio directly in chats
• Support for Secret Key File for more secure key management
• Better Handling & Storage of Interpreter-Generated Images
• Pinecone & Vector Search Optimizations for faster document search
• CUDA 12.6 Docker Image Support for older NVIDIA GPUs
• Experimental Table-Level PGVector Data Encryption for enhanced security
• Accessibility Upgrades and High-Contrast Mode Expansions
• Global Localization & Translation Improvements for multiple languages
• General Backend Stability & Security Enhancements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Azure OpenAI Embedding Support for enterprise-scale AI integration
• Smarter Custom Parameter Handling with automatic JSON parsing
• Improved user interface translations for Simplified and Traditional Chinese, Korean, and Finnish
• Enhanced stability and error handling for chat loading and memory operations
• Fixed issues with prompt access controls and parameter handling

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Ollama Model Status Indicator in Model Selector
• Unload Ollama Model Directly from Model Selector
• User-Configurable Speech-to-Text Language Setting
• Granular Audio Playback Speed Control
• GZip, Brotli, ZStd Compression Middleware for faster page loads
• Configurable Weight for BM25 in Hybrid Search
• Bypass File Creation with CTRL + SHIFT + V
• Bypass Web Loader in Web Search
• Workspace Models Visibility Controls
• Copy Model Link feature
• Load Function Directly from URL
• Custom Name/Description for External Tool Servers
• Custom OpenAPI JSON URL Support for Tool Servers
• Pinned Chats with reduced payload size
• Import/Export Default Prompt Suggestions
• Sortable Banners from Admin Settings
• Advanced Chat Parameters with clearer Ollama support labels
• Improved scroll bar visibility
• Redesigned modals for archived and user chat listings
• Enhanced Add/Edit Memory Modal UX
• Major translation and localization enhancements
• Various bug fixes and improvements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Experimental Azure OpenAI Support for enterprise-grade AI integration
• Watermark AI Responses for clear content provenance
• Enhanced Search Experience with a dedicated modal
• "Toggle" Filter Type for Chat Input
• Granular Model Capabilities Editor
• Flexible Local and External Connection Support
• Allowed File Extensions for RAG
• Enhanced Audio Transcription Logic
• External Document Loader Support
• Preview Button for Code Artifacts
• Screen Reader Support for Response Messages
• Customizable Pending User Overlay
• Option to Disable LDAP Certificate Validation
• Workspace Search by Username or Email
• High Contrast & Dark Mode Enhancements
• Refined Security for Pipelines & Model Uploads
• Major Localization Upgrades
• General Backend Stability & Security improvements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Edit attached images/files in messages
• Clear alerts for private task models
• Improved confirmation dialog focus
• Enhanced temporary chat admin controls
• External Reranker for sharper Knowledge Base search
• Unstylized PDF export option (smaller, faster)
• Milvus settings: index & metric configuration
• Faster web search performance
• Improved accessibility (ARIA labels, modal focus traps)
• Various bug fixes and performance enhancements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• Custom Azure TTS API URL support for enterprise deployments
• Enhanced OAuth group handling for improved compatibility
• Fixed OIDC OAuth login issues
• Resolved access issues for non-admin users
• Improved image extraction and generation functionality
• Support for WebM audio transcription
• Various bug fixes and performance improvements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

Key highlights in this release include:

• AI-Enhanced Notes with audio transcription
• Meeting audio recording and import
• Import Markdown notes
• Notes permissions by user group
• OneDrive & SharePoint integration
• Paginated user list in admin panel
• Granular chat share & export permissions
• User role change confirmation dialog
• Audit log for failed login attempts
• Dedicated 'Generate Title' button for chats
• Notification sound always-on option
• Optimized faster web search & multi-threaded queries
• New Firecrawl & Yacy web search integrations
• Pinecone vector database integration
• Automatic requirements installation for tools & functions
• Automatic sign-out on token expiry
• Automatic YouTube embed detection
• Expanded language & locale support

Various bug fixes and security improvements have also been implemented.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

Key highlights in this release include:

• Granular voice feature permissions for user groups
• Toggle for Voice Activity Detection in Whisper speech-to-text
• New "Copy Formatted" option for AI responses
• Backend stability and performance improvements
• Enhanced translations across multiple languages
• Fixed LDAP login reliability issues
• Resolved image generation problems in temporary chats
• Toggle for auto-artifact detection and persistent config
• Widescreen shared chat view and improved copy behavior
• On-demand knowledge reindexing and YAML OpenAPI support
• Azure Speech-to-Text and Sougou search integration
• Multi-model chat and web loader engine controls
• PWA external manifest, Elixir highlighting, and PKCE for OIDC
• UI/UX improvements and translation updates
• Bug fixes and performance enhancements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

Key highlights in this release include:

• Improved global language support with expanded translations
• Enhanced accuracy for tool descriptions from OpenAPI servers
• Fixed web search result attribution and content retrieval
• Restored audio file upload responses
• Various backend improvements for better performance and stability
• Global external tool server config for admins
• User toggle to access external tools
• Mistral OCR support for scanned docs
• Unified tools dropdown UI
• Improved default RAG prompt
• Refactored tool logic for better performance
• Updated translations
• Better image output in tool messages
• Various bug fixes and performance improvements

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

Added

• 🧩 Connect external tools via OpenAPI servers.
• 🛠️ Expose internal MCP tools as OpenAPI servers using MCPO.
• 📨 Control messages asynchronously with new chat API endpoints.
• 📝 Generate PDFs client-side for improved quality.
• 💼 Admins can enforce temporary chats for compliance.
• 🌍 Fine-grained permissions for public resource sharing.
• 📦 Set custom pip options for tool/function installations.
• 🔢 Double-click message count to edit index quickly.
• 🧠 Add custom prefixes to embeddings for better RAG.
• 🙈 Optionally hide base models from the UI.
• 📚 Use Docling for enhanced content extraction from files.
• 🗃️ Added Redis Sentinel support for high availability.
• 📚 Support JSON schema format definition in Ollama models.
• 🔍 Clear button added to chat sidebar search.
• 🗂️ Auto-focus and Enter submit for new folder renaming.
• 🧱 Render styled Markdown alert banners from blockquotes.
• 🔁 Hybrid search components now run in parallel for speed.
• 📋 Cleaner UI display for tool calls in chat messages.
• 🧪 Playwright timeout is now configurable.
• 📈 Integrated OpenTelemetry for observability (opt-in, self-hosted).
• 🛠 General UI enhancements and UX polish implemented.
• 🧱 Backend refactored for improved stability and performance.
• 🌍 Added/updated languages: Estonian, Galician, Spanish, Chinese, Turkish, etc.

Fixed

• 🧑‍💻 Corrected text input height bug in Firefox.
• 🧾 Fixed Tika adding excessive blank lines in processed PDFs.
• 🧪 Resolved CSV loader encoding issues by auto-detecting charsets.
• ✅ Made certificate path optional for LDAP authentication setup.
• 📥 Fixed file deletion issue in bypass embedding mode.
• 🧩 Corrected RAG hybrid/reranker citation, sorting, and deduplication.
• 🧷 Fixed bug preventing single model export/import.
• 📫 Resolved unnecessary login prompts for already authenticated users.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

Added

• ⚡ Toggle Code Execution On/Off: You can now enable or disable code execution, providing more control over security, ensuring a safer and more customizable experience.
• 📊 Logit Bias Parameter Support: Fine-tune conversation dynamics by adjusting the Logit Bias parameter directly in chat settings, giving you more control over model responses.
• ⌨️ Customizable Enter Behavior: You can now configure Enter to send messages only when combined with Ctrl (Ctrl+Enter) via Settings > Interface, preventing accidental message sends.
• 📝 Collapsible Code Blocks: Easily collapse long code blocks to declutter your chat, making it easier to focus on important details.
• 🏷️ Tag Selector in Model Selector: Quickly find and categorize models with the new tag filtering system in the Model Selector, streamlining model discovery.
• 📈 Experimental Elasticsearch Vector DB Support: Now supports Elasticsearch as a vector database, offering more flexibility for data retrieval in Retrieval-Augmented Generation (RAG) workflows.
• ⚙️ General Reliability Enhancements: Various stability improvements across the WebUI, ensuring a smoother, more consistent experience.
• 🌍 Updated Translations: Refined multilingual support for better localization and accuracy across various languages.

Fixed

• 📜 Pinyin Keyboard Enter Key Now Works Properly: Resolved an issue where the Enter key for Pinyin keyboards was not functioning as expected, ensuring seamless input for Chinese users.
• 🖼️ Web Manifest Loading Issue Fixed: Addressed inconsistencies with 'site.webmanifest', guaranteeing proper loading and representation of the app across different browsers and devices.
• 📦 Non-Root Container Issue Resolved: Fixed a critical issue where the UI failed to load correctly in non-root containers, ensuring reliable deployment in various environments.
• 🔄 "Stream" Hook Activation: Fixed an issue where the "Stream" hook only worked when globally enabled, ensuring reliable real-time filtering.
• 📧 LDAP Email Case Sensitivity: Resolved an issue where LDAP login failed due to email case sensitivity mismatches, improving authentication reliability.
• 💬 WebSocket Chat Event Registration: Fixed a bug preventing chat event listeners from being registered upon sign-in, ensuring real-time updates work properly.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

Highlights:

• 🌐 Open WebUI Now Works Over LAN in Insecure Context: Resolved an issue preventing Open WebUI from functioning when accessed over a local network in an insecure context, ensuring seamless connectivity.
• 🔄 UI Now Reflects Deleted Connections Instantly: Fixed an issue where deleting a connection did not update the UI in real time, ensuring accurate system state visibility.
• 🛠️ Models Now Display Correctly with ENABLE_FORWARD_USER_INFO_HEADERS: Addressed a bug where models were not visible when ENABLE_FORWARD_USER_INFO_HEADERS was set, restoring proper model listing.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

Highlights:

• 📄 Full Context Mode for Local Document Search (RAG): Toggle full context mode from Admin Settings > Documents to inject entire document content into context, improving accuracy for models with large context windows—ideal for deep context understanding.
• 🌍 Smarter Web Search with Agentic Workflows: Web searches now intelligently gather and refine multiple relevant terms, similar to RAG handling, delivering significantly better search results for more accurate information retrieval.
• 🔎 Experimental Playwright Support for Web Loader: Web content retrieval is taken to the next level with Playwright-powered scraping for enhanced accuracy in extracted web data.
• ☁️ Experimental Azure Storage Provider: Early-stage support for Azure Storage allows more cloud storage flexibility directly within Open WebUI.
• 📊 Improved Jupyter Code Execution with Plots: Interactive coding now properly displays inline plots, making data visualization more seamless inside chat interactions.
• ⏳ Adjustable Execution Timeout for Jupyter Interpreter: Customize execution timeout (default: 60s) for Jupyter-based code execution, allowing longer or more constrained execution based on your needs.
• ▶️ "Running..." Indicator for Jupyter Code Execution: A visual indicator now appears while code execution is in progress, providing real-time status updates on ongoing computations.
• ⚙️ General Backend & Frontend Stability Enhancements: Extensive refactoring improves reliability, performance, and overall user experience for a more seamless Open WebUI.
• 🌍 Translation Updates: Various international translation refinements ensure better localization and a more natural user interface experience.
• 🐞 Various bug fixes and improvements.

Full release notes can be found at https://github.com/open-webui/open-webui/releases

⚠️ If you encounter errors when chatting with your existing ollama models after this update, please clear your browser cache to resolve. This is a known issue with ollama and open-webui that may occur after updating.

This update includes several improvements and fixes:

• Added support for multiple tool calls in native function mode for better automation
• Fixed text completion functionality in the Playground
• Improved input responsiveness for better typing experience with long messages
• Enhanced direct API connections for all user roles

Full release notes can be found at https://github.com/open-webui/open-webui/releases

This update includes several new features, improvements and bug fixes:

• Added Code Interpreter for real-time code execution for smoother, dynamic results.
• Updated the chat interface for a simpler, more intuitive experience.
• Introduced an experimental feature for quicker, smarter tool responses.
• Added a new search option and always-on web search for up-to-date info.
• Improved local date/time displays and overall performance.
• Enhanced security for external connections and fixed login and upload issues.
• System prompts now work correctly when used through the API
• Fixed an issue with the 'thinking' tag display
• Improved stability of the Code Interpreter when using custom functions

Full release notes can be found at https://github.com/open-webui/open-webui/releases