# GraphRAG Visualised

**AI Engineering Visualised** · Retrieval · Graphs and evidence · Interactive explainer · Updated 2026-09-09

GraphRAG is a retrieval-augmented generation approach that indexes documents as a graph of entities and relationships, so a question can travel along connections to find evidence that plain vector search would miss.

> See a Bristol launch question travel through a 3D graph into source passages and a cited answer. Adjust graph hops and passage budget, then press Play.

GraphRAG Visualised follows one question: why is the Bristol launch at risk? Press Play to see it move through a 3D graph, collect source passages and form a cited example answer. Graph hops and Passage budget are the two settings. Play resumes a paused sequence or starts it again after completion; changing either setting prepares a fresh run.

The example follows a fictional UK operations team. A Bristol launch needs a sensor delivery, engineers are shared with Leeds, and a component substitution requires assurance approval. The graph connects these entities to the documents that describe their relationships.

Local retrieval starts at the entity named in the question. Graph hops determines how far it explores the connected neighbourhood. The animation names the new entities as they join the search. Their linked passages become retrieval candidates, ranked here using toy cosine similarity.

Passage budget determines how many of those candidates enter context. More graph exploration can find more candidate evidence, but a small budget can still exclude an important passage. Try one hop with four passages, then increase the budget and watch the answer change. The graph and answer use the same selected evidence.

Source passages appear as the run progresses. A graph path points towards possible evidence; it does not prove a claim. Each authored answer point declares its required passages. The example includes it only if those sources are present in context and identifies the evidence missing from withheld points.

This is a simplified local GraphRAG example. The documents, entity matches, graph relationships, vectors and candidate answers are authored fixtures. No language model is called. Real GraphRAG systems also support community-report approaches for broader questions and need evaluation of extraction quality, retrieval relevance and whether the cited text actually supports the answer.

## The maths

### Toy passage ranking

```latex
\operatorname{sim}(q,p)=\frac{q\cdot p}{\lVert q\rVert\lVert p\rVert}
```

The local retrieval example ranks candidate passages with cosine similarity. These three-dimensional vectors are authored examples, not embeddings produced by a language model.

### The provenance check

```latex
\operatorname{covered}(c)=\mathbf{1}\left[S_c\subseteq S_{\mathrm{available}}\right]
```

Each authored claim c declares its required passages S. It passes the demonstration check only when every required passage is present in the selected context. A graph path alone cannot pass this check.

## Sources

- [Microsoft GraphRAG: query engine overview](https://microsoft.github.io/graphrag/query/overview/)
- [Microsoft GraphRAG: local search](https://microsoft.github.io/graphrag/query/local_search/)
- [Microsoft GraphRAG: global search](https://microsoft.github.io/graphrag/query/global_search/)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://arxiv.org/abs/2404.16130)

## Related terms

- [Context window](https://understandingdata.com/ai-coding-dictionary/context-window/)
- [GraphRAG](https://understandingdata.com/context-engineering-dictionary/graphrag/)
- [Retrieval-augmented generation (RAG)](https://understandingdata.com/context-engineering-dictionary/retrieval-augmented-generation/)
- [Contextual retrieval](https://understandingdata.com/context-engineering-dictionary/contextual-retrieval/)

## More visualisations

- [HNSW Visualised](https://understandingdata.com/ai-engineering-visualised/hnsw/)
- [Hybrid Retrieval Visualised](https://understandingdata.com/ai-engineering-visualised/hybrid-retrieval/)
- [Chunking Visualised](https://understandingdata.com/ai-engineering-visualised/chunking/)

---

Source: https://understandingdata.com/ai-engineering-visualised/graphrag/
From AI Engineering Visualised by James Phoenix, Understanding Data. Published 2026-09-09.