Embedding Models

Embedding models are a type of model that convert text into a vector space. They are useful for a variety of tasks, such as clustering, semantic search, and more.

We support several embedding models, usable in the same way as the other models. The only difference is that the output is a tensor, not a string. These will be returned as a list of floats with a length equal to the embedding dimension.

See the Available Models page for a list of available embedding models.