# ApeRAG

A production-ready retrieval-augmented generation platform that combines graph RAG, vector search, and full-text search with AI agents, MCP support, and Kubernetes deployment for enterprise use.

ApeRAG is a RAG platform that combines Graph RAG, vector search, and full-text search with AI agents for building applications with hybrid retrieval, multimodal document processing, and enterprise-grade management features over a knowledge base.

It starts through Docker Compose, exposing a web interface and an API with documentation, and supports MCP so AI assistants can browse collections, run hybrid search, and ask natural-language questions against a knowledge base directly, authenticated by an API key passed as a header or environment variable. Document parsing can be extended with an add-on service powered by MinerU for more difficult document layouts.

Kubernetes deployment is documented as the recommended path for production use, alongside development instructions and a Docker image build process.

Website: https://github.com/apecloud/ApeRAG