Rag

概要

Streamlines Retrieval-Augmented Generation (RAG) workflows by providing a Model Context Protocol (MCP) server, enabling seamless document parsing and vector database storage using ChromaDB. It supports various document types, automatic chunking for large documents, and robust error handling. Operating silently, it integrates cleanly into MCP environments, offering efficient document management and semantic similarity search capabilities.

主な機能

• Intelligently chunks large documents and reconstructs them on demand.
• 0 GitHub stars
• Uses ChromaDB v2 API for semantic similarity search.
• Automatically processes new and changed files in a watched directory.
• Provides full MCP protocol support with resources and tools.
• Supports PDF, Markdown, and text files with enhanced parsing.

ユースケース

• Building AI applications that require access to large amounts of structured data.
• Semantic document search within an MCP environment.
• Automated document ingestion and indexing for RAG applications.