← Glossary / 48 of 100
n. / Models and tokens
Embeddings
Definition
Embeddings are lists of numbers that represent the meaning of a piece of text, so texts with similar meaning have similar numbers. They power semantic search and retrieval.
In more detail
An embedding model turns a document chunk or a question into a vector. Searching for the closest vectors finds relevant text even when the words differ. The same model must be used for both documents and queries, and changing the model means re-embedding everything.
Example
The question "how do I get my money back?" and a document titled "Refund policy" share no words, but their embeddings are close, so retrieval finds the document.
