# GraphRAG

> RAG that makes a map of facts from your files. Then it searches that map too.

**Field:** Artificial Intelligence  
**Category:** Retrieval & Search  
**Also known as:** Graph RAG, Graph Retrieval-Augmented Generation, Knowledge Graph RAG

## Think of it like

It is like a map of who knows who in a town. Big questions get easy.

## Definition

GraphRAG is RAG that searches a knowledge graph as well as text chunks. First, a model reads every document and pulls out the people, places and links. These form a graph. The graph is split into groups of linked things, and each group gets a summary. Questions about the whole collection can then use those summaries. Plain RAG struggles with "what are the main themes here?"

## Example

Microsoft Research put its GraphRAG on GitHub in July 2024. A team uses it to ask "what are the big risks across these 500 reports?"

## Why it matters

Some questions span a whole collection, not one passage. A graph with summaries can answer them.

## Common mistake

Using it for simple fact lookups. Building the graph costs many model calls, and plain RAG already does that well.

## Three principles

- **Build a graph.** Things and links from the text.
- **Summarize groups.** Each cluster gets an overview.
- **Big questions.** Themes across many documents.

## Related terms

- [Knowledge Graph](https://learn.benibix.com/term/ai/knowledge-graph)
- [Retrieval-Augmented Generation (RAG)](https://learn.benibix.com/term/ai/retrieval-augmented-generation)
- [Agentic RAG](https://learn.benibix.com/term/ai/agentic-rag)
- [Named Entity Recognition (NER)](https://learn.benibix.com/term/ai/named-entity-recognition)
- [Chunking (RAG)](https://learn.benibix.com/term/ai/chunking)

![Two dashed groups of linked circles. In the first, Emma works at Acme, Acme is in London, and Jack is a friend of Emma, with a summary line on top about who works where. In the second, Acme makes Bike X, which is part of E-bikes, with a summary line about what Acme sells.](https://learn.benibix.com/diagrams/ai3-graph-rag.svg)

---

Source: https://learn.benibix.com/term/ai/graphrag
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
