Chunking
Chunking is the process of dividing content or data into smaller units for processing, retrieval, or organization.
Designing AI Systems
Fixed-size chunking divides text into chunks containing a configured number of tokens with optional overlap between consecutive chunks.
- How it is used
- Supports document ingestion for semantic search and grounding over organizational knowledge.
- How deep it goes
- Implements fixed-size token windows and a pluggable strategy interface, while illustrating recursive splitting and overlap tradeoffs.
- Examples
- Uses 512-token windows with 50-token overlap, a boundary-spanning return-policy sentence, FAQ entries, and technical manuals.
- What you can do after
- Build it from scratch as a token-window strategy and configure it per index for ingestion.
Retrieval Augmented Generation, The Foundational Ideas
Chunking is the division of source documents into smaller units for processing and retrieval.
- How it is used
- Divides documents during offline RAG indexing into units that query-time retrieval can supply as grounding context.
- How deep it goes
- Works through a PDF indexing configuration and compares boundary strategies, then identifies where flat chunks fail thematic retrieval.
- Examples
- Uses a chunked PDF index and a Q2-versus-Q3 board-minutes question whose answer spans separate passages.
- What you can do after
- Evaluate/understand it by testing fixed-size and structural boundaries against retrieval quality before adopting costlier chunking or hierarchical indexing.
Read how Retrieval Augmented Generation, The Foundational Ideas explains chunking →
Architecting Accessibility
Chunking is the organization of information into smaller, meaningful units that can be processed as groups.
- How it is used
- Uses chunking to make text and interfaces easier to scan, understand, and navigate.
- How deep it goes
- Explains the cognitive rationale and demonstrates text structures and grouped form controls.
- Examples
- Uses short paragraphs, headings, lists, messaging-service markup, and grouped owner, dog, and complaint form fields.
- What you can do after
- Apply chunking by organizing content into concise sections and grouping related controls with labels.
Generative AI in Action
Fixed-length chunking divides text into chunks according to a predetermined character, word, or token length rather than linguistic boundaries.
- How it is used
- Prepares large corpora for RAG retrieval when predictable sizing, performance, and scalability matter more than linguistic boundaries.
- How deep it goes
- Defines fixed-size splitting, demonstrates lost context, and compares selection factors without detailing a complete implementation.
- Examples
- Uses the UK Constitution, fixed-size figures, and comparisons with textwrap, NLTK, spaCy, and NLP-based splitting.
- What you can do after
- Apply it via a fixed-size splitter, then evaluate retrieval context, performance, resource use, and corpus structure against alternatives.
The Art of AI Product Development
Fixed-size chunking is the division of documents into segments containing a predetermined number of tokens or other units.
- How it is used
- Prepares varied-length documents for semantic embedding and search by splitting them into segments of similar length.
- How deep it goes
- Explains the length trade-off and gives a 300-token example, but does not detail chunk-boundary strategies.
- Examples
- Uses lengthy notes and reports split into 300-token chunks before MiniLM embedding and storage in Weaviate.
- What you can do after
- Apply it by splitting documents into similarly sized segments before embedding them for semantic search.
Read how The Art of AI Product Development explains chunking →
Building Reliable AI Systems
A method for dividing source material into segments for processing or retrieval.
- How it is used
- Divides documents for embedding and retrieval in RAG systems.
- How deep it goes
- Explains size trade-offs and content-specific boundaries, with a sliding-window implementation.
- Examples
- Uses a leave-policy eligibility passage and legal, narrative, and code documentation splitting strategies.
- What you can do after
- Evaluate chunking choices for context retention and retrieval relevance, and apply content-aware or overlapping splits.
Financial AI in Practice
Chunking divides documents or other content into smaller segments for processing or retrieval.
- How it is used
- Improves retrieval in RAG pipelines by balancing specific matches against enough surrounding context for grounded answers.
- How deep it goes
- Explains the small-versus-large chunk tradeoff and parent-document retrieval without detailing a full implementation.
- Examples
- Compares 50,000-word Form 10-K filings with 250-character summaries and 80-character headlines that remain intact.
- What you can do after
- Evaluate whether to split content, retain it intact, or retrieve parent documents after searching smaller chunks.
Context Engineering
Chunking is the division of large documents into smaller, coherent text segments for downstream processing and retrieval.
- How it is used
- Positions chunking in the offline RAG indexing pipeline to determine which document evidence can be retrieved.
- How deep it goes
- Compares foundational and advanced strategies, their use cases and trade-offs, and outlines index evaluation and deployment.
- Examples
- Illustrates boundary choices with a warranty policy whose battery exception must remain attached to the general coverage rule.
- What you can do after
- Evaluate chunking strategies for contextual completeness, retrieval precision, and indexing cost.
LLM Customization and Fine-Tuning
The process of dividing documents into smaller units for indexing or retrieval.
- How it is used
- Improves RAG indexing and retrieval by dividing documents into retrievable units.
- How deep it goes
- Compares fixed, structure-aware, and semantic boundaries, then recommends measuring retrieval quality before switching strategies.
- Examples
- Uses numbered policy clauses, code functions, transcript speaker turns, and 400-word windows with 50-word overlap.
- What you can do after
- Apply a corpus-appropriate chunking strategy and change it when measured failures point to chunk boundaries.
Read how LLM Customization and Fine-Tuning explains chunking →
Design for Developers
A technique for dividing content or a task into smaller, manageable units or sequential steps.
- How it is used
- Uses smaller steps to make long mobile forms manageable and reduce user overload.
- How deep it goes
- Explains sequential screens, progress cues, and focused error correction, but does not specify implementation code.
- Examples
- Uses payment, shipping address, and shipping options as separate checkout steps.
- What you can do after
- Apply chunking by splitting a long mobile form into focused screens with clear movement between steps.
Also covered in
- AI Agents and Applications
- Build an AI Agent (From Scratch)
- Build Applications with Local AI Models on a Mac
What to know first
- similarity searchSimilarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- retrieval-augmented generationRetrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- embeddingAn embedding is a numerical vector representation of an item in a feature space, encoding selected properties or relationships for computational tasks such as comparison or retrieval.
- vector databaseA vector database is a data-management system that stores and indexes numerical vector representations and supports retrieval through similarity or distance searches.
Related concepts
- information retrievaluses · Information retrieval is the process of finding and selecting information relevant to a query or information need from a collection.
- text chunkkind of · A text chunk is a bounded segment of a larger text treated as a unit for processing, storage, or retrieval.
- structure-aware chunkingincludes · Structure-aware chunking is the division of a document into segments using structural boundaries, such as headings or sections, to preserve its organization.
- user flowaddresses · A user flow is an ordered sequence of user actions and interface states through which a person interacts with a system, often to accomplish a goal.
- cognitive loadaddresses · Cognitive load is the mental effort required to process information, retain it in working memory, or perform a task.
Questions about chunking
What is chunking?
Chunking is the process of dividing content or data into smaller units for processing, retrieval, or organization.
Which Manning books explain chunking?
Designing AI Systems, Retrieval Augmented Generation, The Foundational Ideas, Architecting Accessibility, Generative AI in Action, The Art of AI Product Development, Building Reliable AI Systems, Financial AI in Practice, Context Engineering and 2 more.
What should I know before learning chunking?
Manning books that teach chunking usually introduce similarity search, retrieval-augmented generation, embedding and vector database first.
What kinds of chunking are there?
Kinds of chunking include structure-aware chunking and character-based splitting.
What is chunking a kind of?
Chunking is a kind of text chunk. A text chunk is a bounded segment of a larger text treated as a unit for processing, storage, or retrieval.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.









