OpenWebUI - Package Updates

[Package Updates]

[2.10.15]

• Update ollama to 0.5.12
• Full Changelog
• Perplexity R1 1776: A version of the DeepSeek-R1 model that has been post trained to remove its refusal to respond to some sensitive topics.
• The OpenAI-compatible API will now return tool_calls if the model called a tool
• Performance on certain Intel Xeon processors should now be restored
• Fixed permission denied issues after installing Ollama on Linux

[Package Updates]

[2.10.16]

• Update open-webui to 0.5.18
• Full Changelog
• ** 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.
• ** Instant Document Upload with Bypass Embedding & Retrieval**: Admins can now enable "Bypass Embedding & Retrieval" in Admin Settings > Documents, significantly speeding up document uploads and ensuring full document context is retained without chunking.

[Package Updates]

[2.10.17]

• Update ollama to 0.5.13
• Full Changelog
• Phi-4-Mini: Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
• Granite-3.2-Vision: A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
• Command R7B Arabic: A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.
• The default context length can now be set with a new OLLAMA_CONTEXT_LENGTH environment variable. For example, to set the default context length to 8K, use: OLLAMA_CONTEXT_LENGTH=8192 ollama serve
• Ollama is now compiled for NVIDIA Blackwell

[Package Updates]

[2.10.18]

• Update open-webui to 0.5.19
• Full Changelog
• ** 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.
• ** "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.

[Package Updates]

[2.10.19]

• Update open-webui to 0.5.20
• Full Changelog
• ** 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.
• ** 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.

[Package Updates]

[2.11.0]

• Update ollama to 0.6.0
• Full Changelog
• Gemma 3: Google Gemma 3 model is now available in 1B, 4B, 12B, and 27B parameter sizes.
• Fixed error that would occur when running snowflake-arctic-embed and snowflake-arctic-embed2 models
• @​iBreaker made their first contribution in https://github.com/ollama/ollama/pull/9565
• @​zhu-xiaowei made their first contribution in https://github.com/ollama/ollama/pull/9540
• @​dwt made their first contribution in https://github.com/ollama/ollama/pull/9569
• @​vincentkoc made their first contribution in https://github.com/ollama/ollama/pull/9626

[Package Updates]

[2.11.1]

• Update ollama to 0.6.1

[Package Updates]

[2.11.2]

• Update ollama to 0.6.2

[Package Updates]

[2.12.0]

• Update base image to 5.0.0

[Package Updates]

[2.12.1]

• Update ollama to 0.6.3

[Package Updates]

[2.13.0]

• Update open-webui to 0.6.0
• Full Changelog
• External Tool Server Support via OpenAPI: Connect Open WebUI to any OpenAPI-compatible REST server instantlyoffering immediate integration with thousands of developer tools, SDKs, and SaaS systems for powerful extensibility. Learn more: https://github.com/open-webui/openapi-servers
• MCP Server Support via MCPO: You can now convert and expose your internal MCP tools as interoperable OpenAPI HTTP servers within Open WebUI for seamless, plug-n-play AI toolchain creation. Learn more: https://github.com/open-webui/mcpo
• /messages Chat API Endpoint Support: For power users building external AI systems, new endpoints allow precise control of messages asynchronouslyfeed long-running external responses into Open WebUI chats without coupling with the frontend.
• Client-Side PDF Generation: PDF exports are now generated fully client-side for drastically improved output qualityperfect for saving conversations or documents.
• Enforced Temporary Chats Mode: Admins can now enforce temporary chat sessions by default to align with stringent data retention and compliance requirements.
• Public Resource Sharing Permission Controls: Fine-grained user group permissions now allow enabling/disabling public sharing for models, knowledge, prompts, and toolsideal for privacy, team control, and internal deployments.

[Package Updates]

[2.13.1]

• Update ollama to 0.6.4

[Package Updates]

[2.13.2]

• Update open-webui to 0.6.1
• Full Changelog
• Global Tool Servers Configuration: Admins can now centrally configure global external tool servers from Admin Settings > Tools, allowing seamless sharing of tool integrations across all users without manual setup per user.
• Direct Tool Usage Permission for Users: Introduced a new user-level permission toggle that grants non-admin users access to direct external tools, empowering broader team collaboration while maintaining control.
• Mistral OCR Content Extraction Support: Added native support for Mistral OCR as a high-accuracy document loader, drastically improving text extraction from scanned documents in RAG workflows.
• Tools Indicator UI Redesign: Enhanced message input now smartly displays both built-in and external tools via a unified dropdown, making it simpler and more intuitive to activate tools during conversations.
• RAG Prompt Improved and More Coherent: Default RAG system prompt has been revised to be more clear and citation-focusedadmins can leave the template field empty to use this new gold-standard prompt.
• Performance & Developer Improvements: Major internal restructuring of several tool-related components, simplifying styling and merging external/internal handling logic, resulting in better maintainability and performance.
• Improved Translations: Updated translations for Tibetan, Polish, Chinese (Simplified & Traditional), Arabic, Russian, Ukrainian, Dutch, Finnish, and French to improve clarity and consistency across the interface.
• External Tool Server API Key Bug Resolved: Fixed a critical issue where authentication headers were not being sent when calling tools from external OpenAPI tool servers, ensuring full security and smooth tool operations.
• Conditional Export Button Visibility: UI now gracefully hides export buttons when there's nothing to export in models, prompts, tools, or functions, improving visual clarity and reducing confusion.
• Hybrid Search Failure Recovery: Resolved edge case in parallel hybrid search where empty or unindexed collections caused backend crashesthese are now cleanly skipped to ensure system stability.

[Package Updates]

[2.13.3]

• Update open-webui to 0.6.2
• Full Changelog
• Improved Global Language Support: Expanded and refined translations across multiple languages to enhance clarity and consistency for international users.
• Accurate Tool Descriptions from OpenAPI Servers: External tools now use full endpoint descriptions instead of summaries when generating tool specificationshelping AI models understand tool purpose more precisely and choose the right tool more accurately in tool workflows.
• Precise Web Results Source Attribution: Fixed a key issue where all web search results showed the same source IDnow each result gets its correct and distinct source, ensuring accurate citations and traceability.
• Clean Web Search Retrieval: Web search now retains only results from URLs where real content was successfully fetchedimproving accuracy and removing empty or broken links from citations.
• Audio File Upload Response Restored: Resolved an issue where uploading audio files did not return valid responses, restoring smooth file handling for transcription and audio-based workflows.
• General Backend Refactoring: Multiple behind-the-scenes improvements streamline backend performance, reduce complexity, and ensure a more stable, maintainable system overallmaking everything smoother without changing your workflow.

[Package Updates]

[2.13.4]

• Update ollama to 0.6.5

[Package Updates]

[2.13.5]

• Update open-webui to 0.6.4
• Full Changelog
• RAG_TEMPLATE Display Issue Resolved: Fixed a formatting problem where the custom RAG_TEMPLATE wasn't correctly rendered in the interfaceensuring that custom retrieval prompts now appear exactly as intended for more reliable prompt engineering.
• Auto-Artifact Detection Toggle: Automatically detects artifacts in resultsbut now you can disable this behavior under advanced settings for full control.
• Widescreen Mode for Shared Chats: Shared link conversations now support widescreen layoutsperfect for presentations or easier review across wider displays.
• Reindex Knowledge Files on Demand: Admins can now trigger reindexing of all knowledge files after changing embeddingsensuring immediate alignment with new models for optimal RAG performance.
• OpenAPI YAML Format Support: External tools can now use YAML-format OpenAPI specsmaking integration simpler for developers familiar with YAML-based configurations.
• Message Content Copy Behavior: Copy action now excludes 'details' tagsstreamlining clipboard content when sharing or pasting summaries elsewhere.
• Sougou Web Search Integration: New search engine option addedenhancing global relevance and diversity of search sources for multilingual users.
• Frontend Web Loader Engine Configuration: Admins can now set preferred web loader engine for RAG workflows directly from the frontendoffering more control across setups.
• Multi-Model Chat Permission Control: Admins can manage access to multi-model chats per user groupallowing tighter governance in team environments.
• Persistent Configuration Can Be Disabled: New environment variable lets advanced users and hosts turn off persistent configsideal for volatile or stateless deployments.

[Package Updates]

[2.13.6]

• Update open-webui to 0.6.5
• Full Changelog
• Granular Voice Feature Permissions Per User Group: Admins can now separately manage access to Speech-to-Text (record voice), Text-to-Speech (read aloud), and Tool Calls for each user groupgiving teams tighter control over voice features and enhanced governance across roles.
• Toggle Voice Activity Detection (VAD) for Whisper STT: New environment variable lets you enable/disable VAD filtering with built-in Whisper speech-to-text, giving you flexibility to optimize for different audio quality and response accuracy levels.
• Copy Formatted Response Mode: You can now enable Copy Formatted in Settings > Interface to copy AI responses exactly as styled (with rich formatting, links, and structure preserved), making it faster and cleaner to paste into documents, emails, or reports.
• Backend Stability and Performance Enhancements: General backend refactoring improves system resilience, consistency, and overall reliabilityoffering smoother performance across workflows whether chatting, generating media, or using external tools.
• Translation Refinements Across Multiple Languages: Updated translations deliver smoother language localization, clearer labels, and improved international usability throughout the UIensuring a better experience for non-English speakers.
• LDAP Login Reliability Restored: Resolved a critical issue where some LDAP setups failed due to attribute parsingensuring consistent, secure, and seamless user authentication across enterprise deployments.
• Image Generation in Temporary Chats Now Works Properly: Fixed a bug where image outputs werent generated during temporary chatsvisual content can now be used reliably in all chat modes without interruptions.

[Package Updates]

[2.13.7]

• Update ollama to 0.6.6
• Full Changelog
• New, faster model downloading: OLLAMA_EXPERIMENT=client2 ollama serve will run Ollama using a new downloader with improved performance and reliability when running ollama pull. Please share feedback here!
• Fixed memory leak issues when running Gemma 3, Mistral Small 3.1 and other models on Ollama
• Improved performance of ollama create when importing models from Safetensors
• Ollama will now allow tool function parameters with either a single type or an array of types by @rozgo
• Fixed certain out of memory issues from not reserving enough memory at startup
• Fix nondeterministic model unload order by @IreGaddr
• Include the items and $defs fields to properly handle array types in the API by @sheffler
• OpenAI-Beta headers are now included in the CORS safelist by @drifkin
• Fixed issue where model tensor data would be corrupted when importing models from Safetensors