GraphRAG
A retrieval technique that builds a knowledge graph from documents (entities, relationships, community summaries) and retrieves along its edges, enabling "connect the dots" answers across many documents where standard vector-based RAG only finds look-alike passages. Production systems typically run hybrid vector-plus-graph retrieval.
Want the full picture? This term comes from GenAI for Business, a complete free book on generative AI strategy and implementation by Prof. Shubin Yu (HEC Paris).