mcp-rag-server
MCP RAG Server is a Python-based server that leverages the Model Context Protocol for Retrieval-Augmented Generation, enabling efficient vector searches across document types like Markdown, PowerPoint, and PDF. It integrates with PostgreSQL for managing vectorized data, offering robust indexing and query capabilities.
What document formats are supported?
The server supports markdown, text, PowerPoint, Word, and PDF formats.
How do I perform a vector search?
Use the 'search' method with parameters like query, limit, with_context, context_size, and full_document.
How can I set up the PostgreSQL database?
You can set it up using Docker with pgvector or install pgvector on an existing PostgreSQL instance.
What is the purpose of the .env file?
The .env file is used to configure environment variables such as PostgreSQL connection details and document directories.
How do I perform incremental indexing?
Use the CLI command 'python -m src.cli index --incremental' to process only new or changed files.