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.
Related terms
Retrieval-Augmented Generation
A technique that looks up relevant documents and feeds them to a model so its answers are grounded in real sources.
Semantic Search
Search that matches on meaning rather than exact keywords, so related ideas surface even with different wording.
Vector Database
A database built to store embeddings and quickly find the items most similar in meaning to a query.
Chunking
Splitting documents into smaller passages before indexing them, a foundational step that makes or breaks a RAG system.