Overview
The official Neo4j GraphRAG package for Python enables developers to build graph retrieval augmented generation (GraphRAG) applications using the power of Neo4j and Python. It provides a robust, feature-rich solution with long-term support directly from Neo4j.
Features
- Knowledge Graph Creation: Build and manage knowledge graphs from unstructured data
- Advanced Retrieval Methods: Graph traversals, text-to-Cypher query generation, vector searches, and full-text searches
- Hybrid Search: Combine vector similarity with graph relationships
- LLM Integration: Works with popular LLM providers (OpenAI, Anthropic, etc.)
- Production Ready: Official support and maintenance from Neo4j
- Explainable Results: Graph-based retrieval provides transparent reasoning chains
Key Capabilities
- Entity extraction and relationship mapping
- Multi-hop question answering through graph traversals
- Cypher query generation from natural language
- Integration with vector embeddings for semantic search
- Structured and unstructured data combination
Use Cases
- Question answering over complex, interconnected data
- Multi-hop reasoning tasks
- Knowledge base construction
- Explainable AI applications
- Enterprise knowledge management
Pricing
Free and open-source. Neo4j database licensing applies separately.
