This RagDocs MCP server provides Retrieval-Augmented Generation capabilities using Qdrant vector database and Ollama/OpenAI embeddings. Built with TypeScript, it offers semantic search and management of documentation through vector similarity. The server implements automatic text chunking, embedding generation, and supports both local and cloud-based Qdrant setups. Key features include adding documents with metadata, semantic search, listing/organizing documents, and deletion. By abstracting vector storage and embedding complexities, it enables easy integration of RAG functionality into AI workflows. This implementation is particularly useful for applications requiring context-aware document retrieval, knowledge management systems, and AI-powered documentation tools.
아직 리뷰가 없습니다. 첫 번째 리뷰를 작성해 보세요!
대화에 참여하려면 로그인하세요
Add a document to the RAG system. Parameters: url (required): Document URL/identifier, content (required): Document content, metadata (optional): Document metadata including title and contentType.
Search through stored documents using semantic similarity. Parameters: query (required): Natural language search query, options (optional): limit, scoreThreshold, filters.
List all stored documents with pagination and grouping options. Parameters: page, pageSize, groupByDomain, sortBy, sortOrder.
Delete a document from the RAG system. Parameters: url (required): URL of the document to delete.
