Frequently Asked Questions about the UBOS MCP Server for RAG

Q: What is the MCP Server for RAG? A: The MCP Server for RAG is an implementation of a Model Context Protocol (MCP) server that provides tools for retrieving and processing documentation through vector search. This allows AI assistants to augment their responses with relevant documentation context.

Q: What are the key features of the MCP Server for RAG? A: Key features include vector-based documentation search and retrieval, support for multiple documentation sources, semantic search capabilities, automated documentation processing, and real-time context augmentation for LLMs.

Q: How does the search_documentation tool work? A: The search_documentation tool allows you to search through stored documentation using natural language queries. It returns matching excerpts with context, ranked by relevance, making it easy to find the information you need.

Q: What is the purpose of the list_sources tool? A: The list_sources tool lists all documentation sources currently stored in the system. This helps you understand what documentation is available for searching or to verify if specific sources have been indexed.

Q: How can I add new documentation sources to the system? A: You can use the extract_urls tool to extract and analyze all URLs from a given web page. You can then add these URLs to the processing queue for indexing.

Q: How do I remove documentation from the system? A: Use the remove_documentation tool to remove specific documentation sources from the system by their URLs. Note that the removal is permanent and will affect future search results.

Q: What are the list_queue and run_queue tools used for? A: The list_queue tool lists all URLs currently waiting in the documentation processing queue. The run_queue tool processes and indexes all URLs currently in the queue.

Q: How can I clear the documentation processing queue? A: Use the clear_queue tool to remove all pending URLs from the documentation processing queue. This is useful for resetting the queue or canceling pending processing.

Q: What is UBOS, and how does it relate to the MCP Server for RAG? A: UBOS is a full-stack AI Agent Development Platform. The MCP Server for RAG can be integrated with UBOS to provide AI Agents with access to relevant documentation, enhancing their capabilities.

Q: What are the configuration requirements for the MCP Server for RAG? A: You need to provide values for the following environment variables: * OPENAI_API_KEY: Your OpenAI API key for embeddings generation * QDRANT_URL: URL of your Qdrant vector database instance * QDRANT_API_KEY: API key for authenticating with Qdrant

Q: What license is the MCP Server for RAG released under? A: This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.