graphrag and graphrag-visualizer
The visualizer is a complementary frontend tool that enables interactive exploration of artifacts (knowledge graphs, communities, entities) produced by the core GraphRAG system, making them ecosystem complements designed to be used together.
About graphrag
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Extracts knowledge graphs from unstructured text using LLMs, then uses those graph structures to improve retrieval and reasoning for private data. Implements a data indexing pipeline that transforms narrative documents into entity-relationship graphs, enabling more contextual and discovery-oriented query responses compared to standard vector retrieval. Supports prompt tuning workflows and integrates with major LLM providers through a configuration-driven architecture.
About graphrag-visualizer
noworneverev/graphrag-visualizer
A web-based tool for visualizing and exploring artifacts from Microsoft's GraphRAG.
Enables client-side parsing of GraphRAG's parquet outputs (entities, relationships, documents, text units, communities) into interactive 2D/3D graph visualizations and tabular data views. Supports optional integration with graphrag-api for live search queries against hosted indexes. Processes all data locally for privacy while maintaining compatibility across GraphRAG versions 0.3.x through 2.x.x.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work