# GraphRAG

> Build an LLM-extracted entity-and-relation knowledge graph plus hierarchical community summaries, then answer global queries via map-reduce over th...

- **Category**: Agentic AI
- **Subcategory**: Retrieval & RAG
- **Canonical URL**: https://designpattern.fyi/patterns/graphrag/

---

## Description
**Intent**: Build an LLM-extracted entity-and-relation knowledge graph plus hierarchical community summaries, then answer global queries via map-reduce over those summaries.
**Context**: A team is using a retrieval-augmented system over a large corpus and starts receiving questions about the corpus as a whole rather than individual facts in it: 'what are the main themes in these reports?', 'how does this position evolve across the documents?', 'which entities are central to the discussion?' These are corpus-level sensemaking queries, not local lookup queries, and they arrive alongside the easier fact-style questions.
**Solution**: Index time: extract entities and relations from chunks; build a knowledge graph; cluster into hierarchical communities; summarise each community. Query time: classify query as local (entity-specific) or global (corpus-wide). Local queries use entity-anchored retrieval; global queries map-reduce over community summaries.


## Use Cases
- Users ask global, corpus-wide questions that local chunk retrieval cannot answer.
- The corpus has clear entities and relations worth extracting into a graph.
- Index-time cost can be paid up front to enable hierarchical community summaries.





## Trade-offs


### Advantages

- Answers corpus-level sensemaking questions naive RAG cannot.

- Communities are inspectable artefacts of the corpus.




### Considerations & Drawbacks

- High indexing cost (orders of magnitude more LLM calls).

- Entity extraction errors cascade through the graph.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/graphrag/)