Retrieval
Searching a larger set of records for useful parts. Finding a passage does not prove it answers the question.
The model answers from whatever it absorbed in training, like an exam from memory.
The app first finds the relevant pages in your documents and puts them in front of the model, like an open-book exam with page references.
Open book is better, but the student can still misread the page, and the search can hand it the wrong page. The page reference is what lets you check.
The fuller definition
Retrieval selects potentially relevant information from a collection for a query or task.
Go deeper
Delivery may be possible in April.
Subject to inspection.
Delivery may be possible in April. Subject to inspection.
source_id: A01
page: 2
version: original
This fictional example keeps a condition beside the proposition it qualifies. Extraction and chunking should preserve enough context to inspect what the source actually says.
A concrete example
A system finds email passages mentioning an inspection condition before building a chronology.
The distinction that matters
Retrieved material is a candidate for use, not proof that the search was exhaustive or the source is correct.
Related terms
RAG — Retrieval-augmented generation
Letting the model look things up in your documents before answering, and show where the answer came from. Like an open-book exam.
Documents & retrievalSemantic search
Searching by meaning rather than by exact words, so 'delay' can find 'postponed'.
Documents & retrievalKeyword search
Searching for the exact words you typed.
Where it is taught
How document-grounded AI answers workSource and further reading
Sentence Transformers · Semantic searchThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.