Glossary Updates12 new terms added to the glossaries · October 2, 2026, 22:44 CEST
AI TechDocKnowledge

Glossary · 4 · Grounding: content, retrieval and knowledge

Chunking

Also known as: Text splitting, Document chunking

Chunking is the splitting of documents into smaller passages — chunks — before they are embedded and indexed for retrieval, so that a RAG system can retrieve just the relevant part of a document.

  • Intermediate
  • Technical writers
  • Developers

In one sentence

Chunking explained: how documents are split for AI retrieval, and why topic-based content chunks better than long PDFs.

Example

A 300-page PDF manual split every 500 tokens cuts a procedure in half; the same content authored as DITA topics can be chunked topic by topic, each with its metadata.

Why it matters on your learning path

  • Technical writers: Topic-based authoring is chunking done by humans, with meaning intact — a strong argument for structured content in AI projects.
  • Developers: Chunk along document structure (headings, topics) where possible, keep titles and metadata with each chunk and test chunk sizes with your evaluation set.

By knowledge.aitechdoc.world · Published September 26, 2026 · Last reviewed

Source: AI TechDoc Knowledge editorial definition

Definitions follow the cited standards and specifications. Where a source is a copyrighted publication, such as an ISO, IEC or EN standard, the definition is a close paraphrase, not a verbatim quotation, so as not to infringe copyright. We recommend reading the original publication. The sections “How it applies” are editorial commentary by AI TechDoc Knowledge and are not part of any standard.

Seen a mistake? Send us a note!