Embedding
Also known as: embeddings, vector embedding
What is embedding?
An embedding is a list of numbers representing the meaning of a piece of text, produced by a model so that semantically similar texts sit close together in that numeric space.
Embeddings power semantic search, clustering, deduplication, recommendation and routing. They are cheap to compute and cheap to store, which is why they underpin most retrieval systems.
Last reviewed by the gAIcko editorial team.