Recon-GraphRAG
What it is
A domain-agnostic Python SDK for building knowledge graphs in Neo4j or Memgraph using the Microsoft GraphRAG philosophy. It supports hierarchical community detection, schema-driven extraction, and three search paradigms (Local, Global, DRIFT) with pluggable LLM providers.
The problem it solves
Existing GraphRAG implementations are often tied to specific graph databases or lack the flexibility to support multiple search paradigms and pluggable LLM providers.
What you could use it for
- Building enterprise knowledge graphs from unstructured documents
- Implementing retrieval-augmented generation with traceable citations
- Performing hierarchical community analysis on graph data
- Creating custom GraphRAG pipelines with Neo4j or Memgraph backends
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.