liveBook · Manning

Text chunk

As explained in Retrieval Augmented Generation, The Foundational Ideas

A chunk is a smaller contiguous segment of source text created for processing or retrieval.

A text chunk is a smaller contiguous segment of source text created for processing or retrieval. Chunking can turn a long policy into sentences, paragraphs, or other fine-grained knowledge strips, reducing irrelevant context before generation. section 11.2.2

Text chunks support two complementary retrieval patterns:

  • In Decompose-then-Recompose, an evaluator re-scores each chunk against the query, discards irrelevant segments, and concatenates the useful remainder into a dense context. section 11.2.2
  • In Clue-RAG, chunks are raw-data nodes connected with knowledge units and entities; they can bridge missing entity-to-entity links during graph traversal. section 12.6.2

Transaction-limit lookup

A 20-page AML policy may contain one relevant paragraph or table row. Chunking lets the system retain that precise evidence while dropping surrounding definitions and boilerplate, improving the signal-to-noise ratio presented to the generator. section 11.2.2

Figure 11.4 The Decompose-then-Recompose Algorithm: Distilling signal from noise in retrieved documents.

Follow the decomposition, filtering, and recomposition flow from a retrieved document to a refined context. section 11.2.2

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains segmentation, query rescoring, filtering, recomposition, and graph bridging, but does not specify chunk-size selection.
Examples
Uses an AML policy paragraph or transaction-limit table row and a path through entities, knowledge units, and chunks.
What it assumes
Assumes familiarity with retrieval-augmented generation, query evaluation, and graph entities while defining chunks through concrete examples.
What you can do after
Apply chunking to isolate query-relevant evidence and preserve retrieval paths through sparse knowledge graphs.
How it connects
Connects text chunks with retrieval, context windows, knowledge units, entities, and knowledge graphs.

Also explained in

Compare how 24 books explain text chunk →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.