graphrag-microsoft-knowledge-graphs
IN premise — entries/2026/06/21/wiki-Prompt_engineering-chunk-1.md
Created 2026-06-21T09:50:10+00:00
GraphRAG, coined by Microsoft Research, extends RAG with knowledge graphs to connect disparate information and synthesize insights over large data collections
Summary
Microsoft Research proposed building a relationship map (a knowledge graph) on top of the usual document-search step used by language models, so the system can see how facts and entities connect across an entire corpus rather than just grabbing a handful of relevant paragraphs. This matters because it lets the system piece together insights that only emerge when you follow chains of connections across large, heterogeneous data, instead of answering from isolated text snippets.
Dependents
These beliefs depend on this one:
- IN retrieval-augmentation-evolved-from-flat-to-structured-knowledge — Retrieval augmentation evolved from flat document retrieval (RAG reducing hallucinations via dynamic prompting-layer retrieval) to structured knowledge traversal (GraphRAG using knowledge graphs to connect disparate information), recapitulating the broader NLP pattern of progressing from unstructured to structured representations — now at the retrieval layer rather than the model layer.