- Added `startup` field to MCP server configuration, allowing users to control server connection at application startup.
- Included instructions for reinitializing MCP servers with user credentials.
- Updated changelog for version 1.2.8 to include enhancements in MCP server management, such as connection status tracking and OAuth support.
- Added detailed documentation on connection status indicators, server initialization processes, and user interface improvements for managing MCP servers.
- Introduced new images and videos to illustrate the updated features and functionalities.
* 📘 docs: Enhance Model Specs documentation with new parameters and default values
- Updated Model Specs documentation to include new parameters: `reasoning_effort`, `reasoning_summary`, `useResponsesApi`, `web_search`, `disableStreaming`, `thinking`, and `thinkingBudget`.
- Added some default values for existing parameters
- Documented changes in changelog
* docs: change note on model params from 'numbers' to 'values' to account for new params that don't have numeric values
* 📚 docs: Add MCP Servers configuration to interface documentation
- Introduced `mcpServers` field in the interface configuration with a placeholder for the MCP server selection dropdown.
- Updated example configurations and added detailed descriptions for the `mcpServers` key and its sub-key `placeholder` in the documentation.
* 📚 docs: Add docs update summary to config_v1.2.8 changelog
---------
Co-authored-by: Danny Avila <danny@librechat.ai>
- Introduced new environment variables for SearXNG: SEARXNG_INSTANCE_URL and SEARXNG_API_KEY.
- Updated documentation to include detailed setup instructions for configuring SearXNG with LibreChat.
- Added new images and a video guide to assist users in setting up and configuring SearXNG.
- Enhanced existing web search documentation to clarify the integration of SearXNG as a search provider
- Introduced new environment variables for SearXNG: SEARXNG_INSTANCE_URL and SEARXNG_API_KEY.
- Updated documentation to include detailed setup instructions for configuring SearXNG with LibreChat.
- Added new images and a video guide to assist users in setting up and configuring SearXNG.
- Enhanced existing web search documentation to clarify the integration of SearXNG as a search provider.
* Update link to 2024 Roadmap to 2025 Roadmap
* fix: update Roadmap link to point to 2025 roadmap
---------
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
- Updated the MCP documentation to include detailed instructions for adding MCP servers using the smithery cli tool.
- Added new images to illustrate the steps for discovering and installing MCP servers through smithery.ai.
* 📚 docs: Update OCR documentation for clarity and structure
* 📚 docs: Add Model Context Protocol (MCP) documentation and update features
* 📚 docs: Add Model Context Protocol (MCP) section to features documentation
* 📚 docs: Enhance MCP documentation with OAuth authentication details and configuration examples
* 📚 docs: Update MCP documentation with improved configuration examples and OAuth authentication details
* 📚 docs: Update dotenv documentation to reflect new index header constants
* 📚 docs: Revise MCP integration documentation for Agents with clearer instructions and new images
- Updated the steps for adding MCP tools to agents for better clarity and organization.
- Introduced new images to illustrate the MCP tools interface.
- Removed outdated image and improved the overall structure of the documentation.
* 📚 docs: Enhance MCP documentation with custom user variables support
---------
Co-authored-by: Aleš Kůtek <kutekales@gmail.com>
* 📄 docs: Accurate Privacy, Terms of Service, and Cookie Policies for LibreChat Docs
* 📄 docs: Update last updated dates in Cookie and Privacy Policies to June 13, 2025
* 📚 docs: Update Config Version to v1.2.8 and add Azure Mistral OCR support
- Updated version numbers in multiple configuration files to reflect the new version 1.2.8.
- Introduced a new `azure_mistral_ocr` strategy option for OCR configuration, enabling the use of Mistral OCR models deployed on Azure AI Foundry.
- Enhanced documentation for OCR configuration to include details on Azure deployment and its requirements.
- Added changelog entries for version 1.2.8, summarizing the new features and updates.
* 📚 docs: Enhance changelog for v1.2.8 with MCP Servers updates
- Added `serverInstructions` to MCP Servers object structure, detailing its role in agent context.
- Introduced new dynamic user field placeholders for enhanced multi-user support, including `{{LIBRECHAT_USER_ID}}` and `{{LIBRECHAT_USER_*}}`.
- Updated documentation links for better navigation and clarity on MCP Servers object structure.
* 📚 docs: Update changelog and OCR documentation for v1.2.8
- Enhanced the changelog for v1.2.8 with additional details on user field placeholders in the MCP Servers object structure.
- Improved OCR documentation by linking strategies to their respective sections for better clarity and navigation.
- Noted the future implementation status of the custom OCR service in the documentation.
* update info about admin user
Signed-off-by: Noah Ispas (iamNoah1) <noahispas@gmail.com>
* fix: typo, and corrections on notes
---------
Signed-off-by: Noah Ispas (iamNoah1) <noahispas@gmail.com>
Co-authored-by: Danny Avila <danacordially@gmail.com>
- Updated the `mcp_servers.mdx` and `agents.mdx` files to include dynamic user field placeholders for headers, URLs, and environment variables.
- Added detailed descriptions and examples for user field placeholders such as `{{LIBRECHAT_USER_EMAIL}}`, `{{LIBRECHAT_USER_ROLE}}`, and others.
- Improved clarity on the usage of environment variables and their integration with user-specific data.
* feat: memories update
* docs: Add LibreChat documentation rules and configuration update guidelines
* docs: Update Node.js version requirements across documentation
- Revised Node.js prerequisites to specify v20.19.0+ (or ^22.12.0 or >= 23.0.0) in README.md, get_started.mdx, npm.mdx, docker_linux.mdx, and nginx.mdx for clarity and compatibility with openid-client v6.
* docs: Add DEBUG_OPENID_REQUESTS environment variable for enhanced OpenID debugging
- Introduced a new environment variable, DEBUG_OPENID_REQUESTS, to enable detailed logging of OpenID request headers for better troubleshooting.
- Updated documentation to include troubleshooting steps for OpenID Connect, emphasizing the use of the new logging feature.
* docs: Update changelog dates for versions v1.2.6 and v1.2.7
* docs: Enhance memory configuration documentation
- Updated the memory configuration section to clarify the default value for the personalize option.
- Changed the provider name from "openai" to "openAI" for consistency.
- Added notes regarding the provider field and valid model parameters.
- Improved examples for memory agent configuration.
* feat: Introduce web search functionality in configuration v1.2.6
- Added `webSearch` configuration to manage web search features, including search providers, scrapers, and rerankers.
- Implemented a toggle for `webSearch` in the interface configuration to control visibility in the chat interface.
- Updated agents configuration to include `web_search` capability, enabling web search for agents by default.
- Created detailed documentation for web search configuration and usage, including API key setup and component descriptions.
* feat: Add web search feature documentation and update configuration
- Introduced a new section for the web search feature in the documentation, detailing its capabilities and configuration options.
- Updated the `_meta.ts` file to include the web search entry.
- Enhanced the web search configuration instructions to emphasize the importance of using environment variable names instead of actual API keys in the YAML file.
* fix: Correct clip-path attribute to clipPath in RossIndex component
* docs: Expand web search feature documentation
- Added detailed information about the web search feature, including environment variable customization options.
- Included a table of required API keys for various search providers and services.
- Emphasized the ability to customize variable names in the `librechat.yaml` configuration file.
* docs: Update web search configuration settings
- Changed default `scraperTimeout` from 30000ms to 7500ms in the documentation.
- Updated `safeSearch` option to reflect new values: 0 (OFF), 1 (MODERATE - default), and 2 (STRICT).
- Enhanced descriptions for both settings to clarify their functionality and defaults.
- Introduced a new section on reusing access and refresh tokens from OpenID Connect providers, specifically for Azure Entra ID.
- Added detailed configuration steps and environment variables for enabling token reuse.
- Created a dedicated page for "Re-use OpenID Tokens for Login Session" with prerequisites and troubleshooting tips.
- Updated existing documentation to reference the new token reuse feature.
* chore: officially deprecate `endpointsMenu`
* feat: add `chatMenu` option to MCP server configuration for dropdown visibility control
* chore: add missing `timeout` and `initTimeout` options to MCP server configuration
* chore: add Authorization header example to MCP server configuration
* Config v1.2.5
* chore: remove plugins configuration from Azure OpenAI documentation
* feat: add vLLM configuration documentation
* feat: add changelog for LibreChat v0.7.8 and update config date to 2025/5/7
* docs: Enhance MCP server documentation with multi-user support details and example configuration
* ✨ v0.7.8-rc1
* feat: Add changelog for v0.7.7-rc1 and update v0.7.8-rc1 to remove ogImage
* docs: Update new contributors section in changelog for v0.7.8-rc1
* docs: Remove idleTimeout from MCP server configuration examples for clarity
* chore: Remove template pricing page and related metadata for simplification
* Create optimizing-rag-performance-in-librechat.md
This PR adds a detailed blog post written by Henk van Ess that covers how to optimize Retrieval-Augmented Generation (RAG) performance in LibreChat.
The guide walks through:
Improving vector database performance (PostgreSQL/pgvector)
Chunking strategies (CHUNK_SIZE / CHUNK_OVERLAP)
Embedding provider options (OpenAI, Azure, Ollama)
Retrieval settings (RAG_API_TOP_K)
Monitoring and server resource tips
It's designed to help developers fine-tune their LibreChat instances for speed and quality. All content is based on hands-on testing and is Markdown-formatted for blog use.
Looking forward to feedback — happy to revise if needed!
* Update optimizing-rag-performance-in-librechat.md
This PR adds a detailed blog post written by Henk van Ess that covers how to optimize Retrieval-Augmented Generation (RAG) performance in LibreChat.
The guide walks through:
Improving vector database performance (PostgreSQL/pgvector)
Chunking strategies (CHUNK_SIZE / CHUNK_OVERLAP)
Embedding provider options (OpenAI, Azure, Ollama)
Retrieval settings (RAG_API_TOP_K)
Monitoring and server resource tips
It's designed to help developers fine-tune their LibreChat instances for speed and quality. All content is based on hands-on testing and is Markdown-formatted for blog use.
Looking forward to feedback — happy to revise if needed!
* Optimizing-rag-performance-in-librechat.md
This PR adds a detailed blog post written by Henk van Ess that covers how to optimize Retrieval-Augmented Generation (RAG) performance in LibreChat.
The guide walks through:
Improving vector database performance (PostgreSQL/pgvector)
Chunking strategies (CHUNK_SIZE / CHUNK_OVERLAP)
Embedding provider options (OpenAI, Azure, Ollama)
Retrieval settings (RAG_API_TOP_K)
Monitoring and server resource tips
It's designed to help developers fine-tune their LibreChat instances for speed and quality. All content is based on hands-on testing and is Markdown-formatted for blog use.
Looking forward to feedback — happy to revise if needed!
* docs: Document AWS_ENDPOINT_URL for S3 configuration (#285)
This commit updates the documentation related to S3 storage configuration to include the `AWS_ENDPOINT_URL` environment variable. This variable was introduced in PR [#6431](https://github.com/danny-avila/LibreChat/pull/6431) to allow users to specify a custom endpoint URL for S3 connections, but the documentation is not update.
The changes include:
- Adding a description for `AWS_ENDPOINT_URL`, clarifying its purpose and indicating that it's optional.
* 🎨 feat: Adds Image Gen Docs, fix broken links, usage stats, missing .env vars, formatting issues, bump Next.js (#288)
* docs: enhance API key setup instructions for clarity
* docs: update section title for API key setup clarity
* docs: add comprehensive guide for OpenAI image generation and editing tools
* docs: clarify Stable Diffusion section and update link in Image Generation overview
* docs: add Flux cloud generator configuration details and environment variables
* fix: Firebase CDN configuration link
* docs: enhance fileStrategy section with CDN options and notes
* docs: enhance Image Generation section with improved structure and pricing details
* docs: add Code Interpreter section with environment variable details and enterprise plan notes
* fix: formatting
* chore: bump next
* fix: correct markdown formatting for artifact example in agents documentation
* docs: add deprecation notices for tools, plugins, presets, and enhance image generation section
* feat: implement GitHub stats API and update Usage component to fetch stars dynamically
* fix: update Docker pulls value in Usage component
* 🫙 fix: Azure Blob Storage Documentation (#289)
* fix: Update fileStrategy option to use "azure_blob" in configuration docs
* fix: Update CDN documentation for Azure Blob Storage and improve navigation
* fix: Remove Hetzner reference from deployment comparison, closes#271
* fix: Update RAG API documentation for clarity on feature availability, closes#249
* feat: Update demo images (#290)
* docs: Clarify configuration file usage and API key settings in documentation, closes#238
* fix: Add instructions to remove existing Docker images for local and remote setups
* 🌊 docs: Flux (#203)
* feat: Enhance documentation for Flux and related tools, including setup instructions and parameters
* docs: Update image generation documentation with additional notes on output handling and MCP server format
* feat: Add blog post on optimizing RAG performance in LibreChat with accompanying image
* chore: Remove unused image for RAG performance blog post
---------
Co-authored-by: Henk van Ess <31323314+voelspriet@users.noreply.github.com>
Co-authored-by: lensfa <80903255+lensfa-lzd@users.noreply.github.com>
Co-authored-by: Marco Beretta <81851188+berry-13@users.noreply.github.com>
Co-authored-by: heptapod <164861708+leondape@users.noreply.github.com>
