← Back to Glossary
GraphRAG
Phase 03 · RAGtechnique

Combining RAG with a structured knowledge graph to extract entities, relationships, and community summaries across complex datasets.

Why it exists

Flat vector search struggles with global questions like 'What are the main themes across all 500 transcripts?'.

How it works

Extracts entities and relationships into a graph, detects hierarchical communities, generates multi-level text summaries, and searches both graph nodes and vectors.

Where you'll use this