GraphRAG
knowledge graph
RAG that uses a graph of entities and their relationships, not just text chunks. Helps with questions that connect many documents.
01In short
RAG that uses a graph of entities and their relationships, not just text chunks. Helps with questions that connect many documents.
02Video
slot · videoGraphRAG in 90 secondsadd: GUIDES['graphrag'].video
03Guide
slot · guide
A step-by-step guide for “GraphRAG” goes here. Suggested outline:
- What it is — in one paragraph
- Why it matters in production
- How to do it — 3 to 7 steps
- Pitfalls we see in the field
04Checklist
slot · checklist
Four to eight things a team can tick before go-live.
05FAQ
slot · FAQ
The three questions clients actually ask about “GraphRAG”.
06Related terms
Data & retrievalRAGBefore answering, the system searches your documents and hands the relevant passages to the model. Answers get grounded in your data without retraining.Data & retrievalChunkingSplitting documents into pieces before embedding them. Too big and the answer drowns; too small and the context is lost.Data & retrievalGroundingTying a model’s answer to specific sources it was given, ideally with citations. The main defence against hallucination in business use.
Where we help · Build