Embedding
A numerical representation of the meaning of text, words or phrases (or an image), so that items with similar meaning sit close together and can be found by meaning, not keyword.
Also called
- Vectors
Kinds
- Embedding model A model that creates embeddings from content it is given, usually to fill a vector database and later to turn each search question into an embedding.
Often confused with
- Token A unit of text that a model reads and writes in, a whole word or a piece of one, on average about three-quarters of an English word.
How it connects
- Embedding power the search in RAG
- Embedding are stored in Vector database