About
RAG Docs is a comprehensive Retrieval-Augmented Generation (RAG) system designed to enhance information retrieval and question-answering across diverse document types and codebases. It features intelligent hierarchical chunking for Markdown documents, preserving context and structure, alongside robust storage and vector search capabilities powered by Qdrant. Seamlessly integrating with Google AI Studio for state-of-the-art embeddings and generative models, RAG Docs offers both a FastAPI-based REST API with OpenAI compatibility and a Model Context Protocol (MCP) server, enabling flexible deployment and integration into various applications, including Claude Desktop. Advanced features like smart query routing, tag-based organization, and semantic code indexing make it a versatile solution for creating intelligent knowledge bases.