Project GraphRAG
LLM-Derived Knowledge Graphs
GraphRAG
GraphRAG (Graphs + Retrieval Augmented Generation) is a technique for richly understanding text datasets by combining text extraction, network analysis, and LLM prompting and summarization into a single end-to-end system.
-
GraphRAG auto-tuning provides rapid adaptation to new domains
September 9, 2024
-
GraphRAG: New tool for complex data discovery now on GitHub
July 2, 2024 | Darren Edge, Ha Trinh, Steven Truitt, Jonathan Larson
-
GraphRAG: Unlocking LLM discovery on narrative private data
February 13, 2024 | Jonathan Larson, Steven Truitt
-
GraphRAG: Improving global search via dynamic community selection
November 15, 2024 | Bryan Li, Ha Trinh, Darren Edge, Jonathan Larson
-
LazyGraphRAG: Setting a new standard for quality and cost
November 25, 2024 | Darren Edge, Ha Trinh, Jonathan Larson
-
Moving to GraphRAG 1.0 – Streamlining ergonomics for developers and users
December 16, 2024 | Nathan Evans, Alonso Guevara Fernández, Joshua Bradley
-
Claimify: Extracting high-quality claims from language model outputs
March 19, 2025 | Dasha Metropolitansky
Open Source
The GraphRAG library is available on GitHub! The GraphRAG solution accelerator repository, an API experience hosted on Azure, has been archived but can still be referenced below.