Neo4j GraphRAG
ActiveDescription
Official Neo4j GraphRAG Python SDK providing an integrated toolkit for knowledge graph construction, vector retrieval, and graph querying, supporting agent-driven graph retrieval-augmented generation workflows.
Key Features
- Official Neo4j GraphRAG Python SDK providing integrated toolkit for knowledge graph construction, vector retrieval, and graph querying
- Supports multiple LLM providers: OpenAI, Anthropic, Google, Cohere, Mistral, Bedrock, Ollama, and more
- SimpleKGPipeline for simplified knowledge graph construction supporting text and PDF input
- Multiple retrievers: vector, full-text, graph traversal, and Text2Cypher hybrid retrieval
- Integration with multiple vector databases: Weaviate, Pinecone, Qdrant
- Full Pipeline class for extensive customization, ideal for advanced use cases
Use Cases
💡 Building knowledge graph-based RAG applications
💡 Automated knowledge graph construction from unstructured documents (text, PDFs)
💡 Hybrid retrieval-augmented generation combining graph traversal and vector search
💡 Enterprise knowledge management and intelligent Q&A systems
Categories
Quick Start
Install via pip install neo4j-graphrag, ensure a Neo4j instance is running with the APOC library. Set NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD and LLM API keys, then use SimpleKGPipeline to build knowledge graphs or create vector indexes for retrieval.