A team at Microsoft originally proposed the GraphRAG framework in their paper [[edgeLocalGlobalGraph2025|From Local to Global: A Graph RAG Approach to Query-Focused Summarization]]. In their implementation, the corpus is translated into a graph by extracting entities, their relationships (i.e., when one is subject and one is object in a sentence) and claims about entities (e.g., entity A owns entity B). The entities become nodes, the relationships edges, and the number of relationships or claims is used as edge weights. Communities are detected using traditional graph community detection (Leiden). An LLM is used to summarize the communities. The process is repeated, generating summaries of summaries in a hierarchical fashion, until a single summary is produced for the entire corpus. The summaries can be used directly to understand themes in the corpus, or matched to queries to support question answering at higher levels of abstraction. The team also released GraphRAG as an [open source library](https://microsoft.github.io/graphrag/get_started/). Multiple derivative approaches have been published including - [ai-knowledge-graph](https://github.com/robert-mcdermott/ai-knowledge-graph) (Robert McDermott; see [writeup](https://robert-mcdermott.medium.com/from-unstructured-text-to-interactive-knowledge-graphs-using-llms-dd02a1f71cd6)) - [llm-graph-builder](https://github.com/neo4j-labs/llm-graph-builder) (Neo4j labs; see [writeup](https://medium.com/neo4j/llm-knowledge-graph-builder-first-release-of-2025-532828c4ba76)) > [!Tip]- Additional Resources > - [How GraphRAG works](https://medium.com/towards-artificial-intelligence/how-microsofts-graphrag-works-step-by-step-b15cada5c209) (Mariana Avelino) > - [What is GraphRAG](https://neo4j.com/blog/genai/what-is-graphrag/) | Neo4j > - [GraphRAG Pattern Catalog](https://graphrag.com/concepts/intro-to-graphrag/) | Neo4j > - [GraphRAG manifesto](https://neo4j.com/blog/genai/graphrag-manifesto/) | Neo4j > - [DeepLearning.ai GraphRAG course](https://www.deeplearning.ai/short-courses/knowledge-graphs-rag/) (2 hour course) > - [Paco Nathan](https://sessionize.com/pacoid/): see three talks