# Chunking Visualised

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

Chunking is the step in a retrieval system that splits documents into pieces small enough to embed and retrieve. Where the cuts fall decides what context the model can see for a given question.

> Play a short animation of one sentence split into readable text chunks. The same words separate in 3D, showing why each cut changes the context a retrieval system can see.

Press Play to see one sentence become three chunks. Two cut lines appear, then the original text pieces lift away from the page. Every word, space and punctuation mark stays in its source order. The cut points are handpicked for this small demonstration.

Chunking divides source material into pieces that can be indexed and retrieved separately. A useful chunk keeps enough context to stand on its own. Here, the later pieces no longer name Northbank. This makes a simple limitation visible: preserving every character does not guarantee that each separate piece makes sense.

Real document pipelines can use sentence, paragraph, fixed-size or semantic boundaries. Larger chunks, overlap or added source context can help preserve relationships across a cut. The appropriate choice depends on the material and the questions readers ask. This animation illustrates the mechanism; it does not run an embedding model or choose an optimal production chunk size.

## Sources

- [Microsoft: chunk large documents for vector search](https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-chunk-documents)

## Related terms

- [Context window](https://understandingdata.com/ai-coding-dictionary/context-window/)
- [Context](https://understandingdata.com/ai-coding-dictionary/context/)
- [Chunking](https://understandingdata.com/context-engineering-dictionary/chunking/)
- [Retrieval-augmented generation (RAG)](https://understandingdata.com/context-engineering-dictionary/retrieval-augmented-generation/)
- [Embeddings](https://understandingdata.com/context-engineering-dictionary/embeddings/)

## More visualisations

- [Hybrid Retrieval Visualised](https://understandingdata.com/ai-engineering-visualised/hybrid-retrieval/)
- [GraphRAG Visualised](https://understandingdata.com/ai-engineering-visualised/graphrag/)
- [Embedding space](https://understandingdata.com/ai-engineering-visualised/embedding-space/)
- [HNSW Visualised](https://understandingdata.com/ai-engineering-visualised/hnsw/)

---

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