Retrieval & Agents

GraphRAG

A RAG variant that builds a knowledge graph from your documents so it can answer broad questions ordinary RAG cannot.

GraphRAG, introduced by Microsoft, uses a language model to extract entities and relationships from a document set into a knowledge graph, then groups that graph into themed communities with summaries. This lets it answer global, big-picture questions across an entire corpus, like what are the main themes, which plain vector RAG struggles with because it only pulls a few similar chunks. The tradeoff is a more expensive, more complex indexing step up front.