Semantic chunking
Splitting documents along meaning boundaries — sections, topics, complete ideas — rather than at fixed character counts, to produce…
GEO AIPassage retrieval
Chunk retrieval
Retrieving individual segments of a document rather than whole pages, which is how most AI search and RAG systems select what to feed a model.
In full
Because context windows are finite and precision matters, retrieval systems index documents as chunks and return the best-matching ones. A chunk that depends on context stated elsewhere on the page — a pronoun, an implicit subject, a figure whose units appear in a distant heading — can be retrieved and then misinterpreted. Writing sections that stand alone, restating key entities and units, is the practical response, and it also improves featured snippet and passage ranking outcomes.
Example
A pricing table without a currency symbol in the same block is retrieved and summarised with the wrong currency.
Related terms
Retrieval-augmented generation
An architecture where a system retrieves relevant documents or passages first and then has a language model generate an answer conditioned…
Grounding
Constraining a language model's output to information retrieved from a specified source — a search index, a document set or a database —…
Passage ranking
Google's ability to rank a page based on the relevance of a specific passage within it, even when the page overall is about something…
Embedding
A numerical vector representing the meaning of text, an image or another item, positioned so that semantically similar items lie close…