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: Unlocking LLM discovery on narrative private data
February 13, 2024 | Jonathan Larson, Steven Truitt
-
GraphRAG: New tool for complex data discovery now on GitHub
July 2, 2024 | Darren Edge, Ha Trinh, Steven Truitt, Jonathan Larson
-
GraphRAG auto-tuning provides rapid adaptation to new domains
September 9, 2024
-
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
-
BenchmarkQED: Automated benchmarking of RAG systems
June 5, 2025 | Darren Edge, Ha Trinh, Andres Morales Esquivel, Jonathan Larson
-
VeriTrail: Detecting hallucination and tracing provenance in multi-step AI workflows
August 5, 2025 | Dasha Metropolitansky
Microsoft Discovery
GraphRAG and LazyGraphRAG technology is now available through Microsoft Discovery (opens in new tab), an agentic platform for scientific research built in Azure.