How neo4j-contrib/ms-graphrag-neo4j works
MsGraphRAG-Neo4j is a Python library for building and enriching a Neo4j knowledge graph to support query-focused summarization and retrieval. The principal workflow accepts text and entity types, uses an LLM to extract entities and relationships, stores them in Neo4j, summarizes graph data, then detects and summarizes communities. The graph separates those domain stages from their shared orchestration and prompt/parsing layer. The README documents the overall workflow; sampled source confirms key calls and query definitions, but does not show a user-facing search or retrieval API.
Main entry points: ms_graphrag.py MsGraphRAG API · cypher_queries.py Graph queries · prompts.py LLM prompt templates · utils.py Output parsing
Components 13
Graph workflow
- MsGraphRAG API
src/ms_graphrag_neo4j/ms_graphrag.py - Entity extraction
src/ms_graphrag_neo4j/ms_graphrag.py - Node and relation summaries
src/ms_graphrag_neo4j/ms_graphrag.py - Community detection
src/ms_graphrag_neo4j/ms_graphrag.py - Community summaries
src/ms_graphrag_neo4j/ms_graphrag.py
Graph processing
- LLM prompt templates
src/ms_graphrag_neo4j/prompts.py - Output parsing
src/ms_graphrag_neo4j/utils.py - Graph queries
src/ms_graphrag_neo4j/cypher_queries.py
LLM and database
- OpenAI API
- Neo4j graph
- Neo4j GDS
- Neo4j APOC
Other components
- Library user
Connections 18
- Library user → MsGraphRAG API: calls
README.md - MsGraphRAG API → Entity extraction: runs
README.md - Entity extraction → OpenAI API: requests extraction
README.md - Entity extraction → Output parsing: parses output
src/ms_graphrag_neo4j/ms_graphrag.py - Entity extraction → Neo4j graph: imports graph data
src/ms_graphrag_neo4j/ms_graphrag.py - Entity extraction → LLM prompt templates: uses prompts
src/ms_graphrag_neo4j/ms_graphrag.py - MsGraphRAG API → Node and relation summaries: runs
README.md - Node and relation summaries → Neo4j graph: reads and writes
README.md - Node and relation summaries → OpenAI API: requests summaries
README.md - Node and relation summaries → Graph queries: uses queries
src/ms_graphrag_neo4j/ms_graphrag.py - MsGraphRAG API → Community detection: runs
README.md - Community detection → Neo4j graph: runs graph queries
README.md - Graph queries → Neo4j GDS: calls Leiden
src/ms_graphrag_neo4j/cypher_queries.py - MsGraphRAG API → Community summaries: runs
README.md - Community summaries → Neo4j graph: reads and writes
README.md - Community summaries → OpenAI API: requests summaries
README.md - Community summaries → LLM prompt templates: uses prompts
src/ms_graphrag_neo4j/ms_graphrag.py - Graph queries → Neo4j APOC: calls subgraph procedure
src/ms_graphrag_neo4j/cypher_queries.py