GraphRAG-SDK and llm-graph-builder
These are complements: the graph construction tool (B) ingests unstructured data into Neo4j, while the SDK (A) queries the resulting graph database for RAG applications.
About GraphRAG-SDK
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
Combines knowledge graphs, ontology extraction, and LLM inference via LiteLLM to enable GraphRAG workflows—automatically structuring unstructured data into queryable graphs stored in FalkorDB. Supports multi-vendor LLM deployment (OpenAI, Google, Azure, Ollama) and provides both ontology auto-detection from sources and chat-based query interfaces for knowledge graph traversal and augmented generation.
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