neo4j-graphrag-python and llm-graph-builder
These are complements: llm-graph-builder constructs knowledge graphs from unstructured data using LLMs, while graphrag-python provides RAG retrieval and generation capabilities over existing graphs, so they work together in a pipeline where one builds the graph and the other queries it.
About neo4j-graphrag-python
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
Supports automated knowledge graph construction from unstructured text and PDFs via LLM-powered entity/relation extraction, alongside multiple retrieval strategies (vector search, graph traversal, hybrid, and Text2Cypher). Integrates with major LLM providers (OpenAI, Anthropic, Google, Cohere, Ollama, MistralAI) and optional external vector stores (Weaviate, Pinecone, Qdrant), with experimental NLP components using spaCy for semantic resolution.
About llm-graph-builder
neo4j-labs/llm-graph-builder
Neo4j graph construction from unstructured data using LLMs
Supports multiple input sources (PDFs, videos, web pages, S3/GCS buckets) and 10+ LLM providers through LangChain, with configurable embedding models and vector search capabilities. Built on a FastAPI backend and React frontend, featuring conversational graph querying, token usage tracking per user, and real-time visualization in Neo4j Bloom. Deployable locally via Docker Compose, separately for development, or to Google Cloud Run with support for both cloud and local LLMs like Ollama.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work