pgraf¶
pgraf turns PostgreSQL into a lightning fast property graph engine with vector search capabilities, designed for use in AI agents and applications.
Features¶
- Typed Models: Strong typing with Pydantic models for nodes, edges, and content
- Vector Search: Built-in support for embeddings and semantic search
- Property Graph: Full property graph capabilities with typed nodes and labeled edges
- Asynchronous API: Modern async/await API for high-performance applications
- PostgreSQL Backend: Uses PostgreSQL's power for reliability and scalability
Installation¶
Database Setup¶
Ensure pgvector is installed.
DDL is located in schema/pgraf.sql
Requirements¶
- Python 3.12+
- PostgreSQL 14+