Retrieval & ranking
Chunking
Splitting a document into small passages an AI can retrieve and quote one at a time.
Chunking is how retrieval systems split a document into smaller passages so they can be indexed, retrieved and quoted individually. Engines rarely work with whole pages; they work with chunks, and the chunk — not the page — is what gets embedded, matched to a query and lifted into an answer.
This has a direct content implication: a page is only as citable as its individual chunks. If your key point is spread across several paragraphs that only make sense together, no single chunk carries it cleanly and the engine has nothing tidy to quote. Writing in self-contained units aligns your content with how chunking actually carves it up.
You cannot control the exact chunk boundaries, but you can write so that natural passages stand alone — which is the same discipline as extractability and quotable sentences.
Related terms
Chunk Retrieval
Fetching the top few most relevant text passages from a vector index for a query.
Extractability
Whether a passage can be lifted into an AI answer and still stand on its own.
Passage Embedding
A numeric vector that captures a passage's meaning so similar passages sit near each other.
Retrieval-Augmented Generation
Fetch relevant documents first, then have an LLM write an answer grounded in them.
Quotable Sentence
A self-contained statement an AI can lift verbatim into an answer and attribute.
Want to know where you stand in AI answers?
We’ll show you which engines cite you, and which don’t.
Get a free AI citation audit