post-graph-rag

post-graph-rag is a developer tool that integrates AI-powered graph-based retrieval-augmented generation with PostgreSQL databases. It extracts entities and relations using large language models, stores them as property graphs alongside vector embeddings, and answers queries by combining vector similarity, graph traversal, and full-text search without requiring separate vector or graph stores. It improves knowledge update precision by superseding outdated facts and supports complex temporal and relational queries in one consistent database environment.