What is Graph RAG and when does it beat plain RAG?
hardAnswer
- GraphRAG (Microsoft 2024): pre-extract entities and relations from the corpus into a knowledge graph, cluster the graph into hierarchical communities, and summarize each community with an LLM.
- At query time, retrieve relevant community summaries + underlying chunks.
- Beats plain RAG on questions requiring aggregation across many documents ('What are the main themes?') and multi-hop reasoning.
- Cost: heavy indexing pipeline (many LLM calls).
- Best for expert domains and long documents where relationships matter.
Check yourself — multiple choice
- Same as plain RAG
- Pre-extract entities/relations → hierarchical communities + summaries → retrieve summaries + chunks → wins on aggregation and multi-hop
- No indexing
- Only for images
GraphRAG: knowledge-graph + community summaries → strong on aggregation / multi-hop.
#rag#retrieval
Practise LLMs & GenAI
214 interview questions in this topic.