OpenWebUI - Package Updates
-
[0.4.0]
- Update OpenWebUI to 0.1.111
- Full changelog
- Model Whitelisting: Admins now have the ability to whitelist models for users with the 'user' role.
- Update All Models: Added a convenient button to update all models at once.
- Toggle PDF OCR: Users can now toggle PDF OCR option for improved parsing performance.
- DALL-E Integration: Introduced DALL-E integration for image generation alongside automatic1111.
- RAG API Refactoring: Refactored RAG logic and exposed its API, with additional documentation to follow.
-
[0.5.0]
- Update OpenWebUI to 0.1.113
- Full changelog
- Localization: You can now change the UI language in Settings > General. We support Ukrainian, German, Farsi (Persian), Traditional and Simplified Chinese and French translations. You can help us to translate the UI into your language! More info in our CONTRIBUTION.md.
- System-wide Theme: Introducing a new system-wide theme for enhanced visual experience.
-
[0.6.0]
- Update OpenWebUI to 0.1.114
- Full changelog
- Webhook Integration: Now you can subscribe to new user sign-up events via webhook. Simply navigate to the admin panel > admin settings > webhook URL.
- Enhanced Model Filtering: Alongside Ollama, OpenAI proxy model whitelisting, we've added model filtering functionality for LiteLLM proxy.
- Expanded Language Support: Spanish, Catalan, and Vietnamese languages are now available, with improvements made to others.
- Input Field Spelling: Resolved issue with spelling mistakes in input fields.
- Light Mode Styling: Fixed styling issue with light mode in document adding.
- Language Sorting: Languages are now sorted alphabetically by their code for improved organization.
-
[0.7.0]
- Update OpenWebUI to 0.1.115
- Full changelog
- Custom Model Selector: Easily find and select custom models with the new search filter feature.
- Cancel Model Download: Added the ability to cancel model downloads.
- Image Generation ComfyUI: Image generation now supports ComfyUI.
- Updated Light Theme: Updated the light theme for a fresh look.
- Additional Language Support: Now supporting Bulgarian, Italian, Portuguese, Japanese, and Dutch.
-
[0.9.0]
- Update OpenWebUI to 0.1.118
- Update Ollama to 0.1.31
- Full changelog
- Ollama and CUDA Images: Added support for ':ollama' and ':cuda' tagged images.
- Enhanced Response Rating: Now you can annotate your ratings for better feedback.
- User Initials Profile Photo: User initials are now the default profile photo.
- Update RAG Embedding Model: Customize RAG embedding model directly in document settings.
- Additional Language Support: Added Turkish language support.
-
[0.10.0]
- Update OpenWebUI to 0.1.119
- Update Ollama to 0.1.32
- Full changelog
- Enhanced RAG Embedding Support: Ollama, and OpenAI models can now be used for RAG embedding model.
- Seamless Integration: Copy 'ollama run ' directly from Ollama page to easily select and pull models.
- Tagging Feature: Add tags to chats directly via the sidebar chat menu.
- Mobile Accessibility: Swipe left and right on mobile to effortlessly open and close the sidebar.
- Improved Navigation: Admin panel now supports pagination for user list.
- Additional Language Support: Added Polish language support.
-
[0.11.0]
- Update OpenWebUI to 0.1.120
- Full changelog
- Archive Chat Feature: Easily archive chats with a new sidebar button, and access archived chats via the profile button > archived chats.
- Configurable Text-to-Speech Endpoint: Customize your Text-to-Speech experience with configurable OpenAI endpoints.
- Improved Error Handling: Enhanced error message handling for connection failures.
- nhanced Shortcut: When editing messages, use ctrl/cmd+enter to save and submit, and esc to close.
- Language Support: Added support for Georgian and enhanced translations for Portuguese and Vietnamese.
- Model Selector: Resolved issue where default model selection was not saving.
- Share Link Copy Button: Fixed bug where the copy button wasn't copying links in Safari.
- Light Theme Styling: Addressed styling issue with the light theme.
-
[0.11.1]
- Update OpenWebUI to 0.1.121
- Full changelog
- Translation Issues: Addressed various translation discrepancies.
- LiteLLM Security Fix: Updated LiteLLM version to resolve a security vulnerability.
- HTML Tag Display: Rectified the issue where the '< br >' tag wasn't displaying correctly.
- WebSocket Connection: Resolved the failure of WebSocket connection under HTTPS security for ComfyUI server.
- FileReader Optimization: Implemented FileReader initialization per image in multi-file drag & drop to ensure reusability.
- Tag Display: Corrected tag display inconsistencies.
- Archived Chat Styling: Fixed styling issues in archived chat.
- Safari Copy Button Bug: Addressed the bug where the copy button failed to copy links in Safari.
-
[0.11.2]
- Update OpenWebUI to 0.1.122
- Full changelog
- Enhanced RAG Pipeline: Now with hybrid searching via 'BM25', reranking powered by 'CrossEncoder', and configurable relevance score thresholds.
- External Database Support: Seamlessly connect to custom SQLite or Postgres databases using the 'DATABASE_URL' environment variable.
- Remote ChromaDB Support: Introducing the capability to connect to remote ChromaDB servers.
- Improved Admin Panel: Admins can now conveniently check users' chat lists and last active status directly from the admin panel.
- Splash Screen: Introducing a loading splash screen for a smoother user experience.
- Language Support Expansion: Added support for Bangla (bn-BD), along with enhancements to Chinese, Spanish, and Ukrainian translations.
- Improved LaTeX Rendering Performance: Enjoy faster rendering times for LaTeX equations.
- More Environment Variables: Explore additional environment variables in our documentation (https://docs.openwebui.com), including the 'ENABLE_LITELLM' option to manage memory usage.
- Ollama Compatibility: Resolved errors occurring when Ollama server version isn't an integer, such as SHA builds or RCs.
- Various OpenAI API Issues: Addressed several issues related to the OpenAI API.
- Stop Sequence Issue: Fixed the problem where the stop sequence with a backslash '' was not functioning.
- Font Fallback: Corrected font fallback issue.
- Prompt Input Behavior on Mobile: Enter key prompt submission disabled on mobile devices for improved user experience.
-
@girish Thank you! This is one of those functionally insignificant but aesthetically extremely significant updates. I really appreciate you figuring this one out. Great work!
-
[0.11.4]
- Update OpenWebUI to 0.1.123
- Full changelog
- New Landing Page Design: Refreshed design for a more modern look and optimized use of screen space.
- Youtube RAG Pipeline: Introduces dedicated RAG pipeline for Youtube videos, enabling interaction with video transcriptions directly.
- Enhanced Admin Panel: Streamlined user management with options to add users directly or in bulk via CSV import.
- '@' Model Integration: Easily switch to specific models during conversations; old collaborative chat feature phased out.
- Language Enhancements: Swedish translation added, plus improvements to German, Spanish, and the addition of Doge translation.
-
[0.11.5]
- Update OpenWebUI to 0.1.124
- Full changelog
- Improved Chat Sidebar: Now conveniently displays time ranges and organizes chats by today, yesterday, and more.
- Citations in RAG Feature: Easily track the context fed to the LLM with added citations in the RAG feature.
- Auth Disable Option: Introducing the ability to disable authentication. Set 'WEBUI_AUTH' to False to disable authentication. Note: Only applicable for fresh installations without existing users.
- Enhanced YouTube RAG Pipeline: Now supports non-English videos for an enriched experience.
- Specify OpenAI TTS Models: Customize your TTS experience by specifying OpenAI TTS models.
- Additional Environment Variables: Discover more environment variables in our comprehensive documentation at Open WebUI Documentation (https://docs.openwebui.com).
- Language Support: Arabic, Finnish, and Hindi added; Improved support for German, Vietnamese, and Chinese.
- Model Selector Styling: Addressed styling issues for improved user experience.
- Warning Messages: Resolved backend warning messages.
- Title Generation: Limited output to 50 tokens.
-
[0.11.6]
- Update OpenWebUI to 0.1.125
- Full changelog
- Updated UI: Chat interface revamped with chat bubbles. Easily switch back to the old style via settings > interface > chat bubble UI.
- Enhanced Sidebar UI: Model files, documents, prompts, and playground merged into Workspace for streamlined access.
- Improved Many Model Interaction: All responses now displayed simultaneously for a smoother experience.
- Python Code Execution: Execute Python code locally in the browser with libraries like 'requests', 'beautifulsoup4', 'numpy', 'pandas', 'seaborn', 'matplotlib', 'scikit-learn', 'scipy', 'regex'.
- Experimental Memory Feature: Manually input personal information you want LLMs to remember via settings > personalization > memory.
- Persistent Settings: Settings now saved as config.json for convenience.
- Health Check Endpoint: Added for Docker deployment.
- TL Support: Toggle chat direction via settings > interface > chat direction.
- PowerPoint Support: RAG pipeline now supports PowerPoint documents.
- Language Updates: Ukrainian, Turkish, Arabic, Chinese, Serbian, Vietnamese updated; Punjabi added.
- Shared Chat Update: Shared chat now includes creator user information.
-
[2.1.0]
- Update OpenWebUI to 0.2.2
- Full changelog
- Pipelines Support: Open WebUI now includes a plugin framework for enhanced customization and functionality (https://github.com/open-webui/pipelines). Easily add custom logic and integrate Python libraries, from AI agents to home automation APIs.
- Function Calling via Pipelines: Integrate function calling seamlessly through Pipelines.
- ser Rate Limiting via Pipelines: Implement user-specific rate limits to manage API usage efficiently.
- Usage Monitoring with Langfuse: Track and analyze usage statistics with Langfuse integration through Pipelines.
- Conversation Turn Limits: Set limits on conversation turns to manage interactions better through Pipelines.
- Toxic Message Filtering: Automatically filter out toxic messages to maintain a safe environment using Pipelines.
