Multi-Document RAG

Enables document processing with OCR, vector embeddings, and semantic search capabilities for efficient retrieval-augmented generation across multiple file formats including PDF, DOCX, PPTX, Excel, CSV, and images.

MCP-RAG is a server implementation that enables large file processing and retrieval-augmented generation capabilities for AI assistants. Developed by Anurag Bombarde, it provides tools for extracting content from various document formats (PDF, DOCX, PPTX, Excel, CSV, and images) with OCR support, creating vector embeddings using OpenAI or SentenceTransformer models, and performing semantic searches across document collections. The implementation features robust handling of large files through chunking strategies, multi-vector store support with ChromaDB and Milvus integration, and comprehensive document processing with enhanced OCR capabilities for scanned documents and images.