# Chunking

> Chunking is splitting documents into smaller passages before they are embedded and indexed, so a retrieval system can find and return the exact part that answers a question.

- Page: https://methodcrew.com/glossary/chunking
- Last updated: 2026-10-28
- Publisher: [The Method Crew](https://methodcrew.com/)
- Also known as: text splitting

## How it works

A 60-page policy manual is too big to retrieve as one unit, and a single embedding cannot represent 60 pages of meaning. So the document is cut into chunks, and each chunk is embedded and stored with metadata: source file, page, section heading, date.

Common approaches:

- Fixed size: every 300 to 800 tokens, with 10% to 20% overlap so sentences at the edges are not lost
- Structure-aware: split on headings, list items and table boundaries, keeping each section whole
- Semantic: split where the topic changes, measured by embedding similarity between sentences
- Parent and child: search small chunks for precision, then hand the model the larger section around the match

Structure-aware chunking with a size cap is our usual starting point. It keeps a clause or a procedure in one piece.

## How businesses use it

Chunking is a design step inside every [RAG system](https://methodcrew.com/glossary/retrieval-augmented-generation), and it decides more about answer quality than the choice of model. It matters most for:

- Contracts, where a clause only makes sense with its definitions (see the [contract review assistant blueprint](https://methodcrew.com/blueprints/contract-review-assistant))
- Technical manuals with numbered procedures
- Spreadsheets and tables, which need their header row repeated in every chunk
- Scanned PDFs, which need [document processing](https://methodcrew.com/services/intelligent-document-processing) to extract clean text first

## Where it goes wrong

Bad chunking produces answers that sound right and are not. A table split across 2 chunks loses its headers. A procedure cut in the middle returns step 4 without steps 1 to 3. A chunk that says "this does not apply to contractors" is useless once it has lost the heading that says what "this" is.

Start by adding the document title and section heading to each chunk's text before embedding. Anthropic's [contextual retrieval tests](https://www.anthropic.com/news/contextual-retrieval) (September 2024) found that adding a short explanation of context to each chunk cut retrieval failures by 35%. Then test retrieval on real questions and read the passages that come back, not only the final answers. If exact terms still go missing, add [hybrid search](https://methodcrew.com/glossary/hybrid-search).

## Example (hypothetical)

Hypothetical: a 300-person manufacturer's safety assistant returns lockout steps without the warnings printed above them. Re-chunking each procedure as 1 unit with its warnings attached means every answer about a procedure carries its warnings too.

## Related terms

- [Embeddings](https://methodcrew.com/glossary/embeddings): Embeddings are lists of numbers that capture the meaning of text or images, so software can measure how closely related one item is to another.
- [Retrieval-augmented generation (RAG)](https://methodcrew.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation is a method where a system first searches your own documents for relevant passages, then gives them to a language model to answer from.
- [Context window](https://methodcrew.com/glossary/context-window): A context window is the maximum amount of text, measured in tokens, that a language model can read and write in one request, counting instructions, documents and its reply.
- [Intelligent document processing (IDP)](https://methodcrew.com/glossary/intelligent-document-processing): Intelligent document processing uses OCR and AI models to read documents such as invoices, contracts and forms, extract the fields you need, check them and post them into your systems.
- [Vector database](https://methodcrew.com/glossary/vector-database): A vector database stores embeddings, the numeric fingerprints of text or images, and quickly finds the stored items whose meaning is closest to a query.

## Services where this matters

- [RAG and knowledge systems](https://methodcrew.com/services/rag-knowledge-systems): Your documents turned into an assistant that cites its sources. $15,000 to $75,000 per project.
- [Intelligent document processing](https://methodcrew.com/services/intelligent-document-processing): Invoices, contracts and forms turned into clean, checked data. $12,000 to $40,000 per project.

## Articles that use this term

- [How to build a company knowledge assistant that cites its sources](https://methodcrew.com/insights/build-rag-knowledge-assistant)

Full glossary: https://methodcrew.com/glossary