Embedding models

An embedding model is a model that is designed to convert text to Vectors in a way that encodes the meaning of the piece of text.

They are useful for all sort of algorithm as computers are better at handling numbers than characters.

In general, the vectors produced have a meaning relative to the text. For example, vectors that are close to each other represent text with similar meaning, or you can add vectors to add meanings and have equations like queen = king + man - woman