Embedding model
Also: embedding models
A model whose only job is to turn text into embeddings for searching.
An embedding turns a piece of text into a position on a map. Texts that mean similar things land close together, even with different words. Searching by meaning means looking for the nearest neighbours on the map.
The fuller definition
An embedding model converts inputs into numerical representations suitable for tasks such as similarity search or clustering.
Go deeper
Related phrasing can be nearby in an embedding space. Real embeddings have many dimensions, and the model determines similarity. Nearby does not mean legally relevant or factually correct.
A concrete example
One model encodes document passages and queries so their vectors can be compared consistently.
The distinction that matters
Different embedding models generally use different spaces; do not mix vectors without a compatible method.
Related terms
Embedding
A list of numbers used to compare items such as texts. Texts with similar meanings may have similar lists.
Documents & retrievalVector database
A store built for embeddings, so you can quickly find texts with a similar meaning.
Documents & retrievalSemantic search
Searching by meaning rather than by exact words, so 'delay' can find 'postponed'.
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.