LlamaCppEx.Embedding (LlamaCppEx v0.7.0)

Generate embeddings from text using an embedding model.

Summary

t()

Computes an embedding for a single text.

Computes embeddings for multiple texts.

@type t() :: [float()]

@spec embed(LlamaCppEx.Model.t(), String.t(), keyword()) ::
  {:ok, t()} | {:error, String.t()}

Computes an embedding for a single text.

:n_ctx - Context size. Defaults to 2048.
:pooling_type - Pooling type. Defaults to :unspecified (model's default). Values: :unspecified, :none, :mean, :cls, :last.
:normalize - Normalization mode. 2 = L2 (default), 0 = max-abs, -1 = none.

@spec embed_batch(LlamaCppEx.Model.t(), [String.t()], keyword()) ::
  {:ok, [t()]} | {:error, String.t()}

Computes embeddings for multiple texts.

Uses a fresh context for each text. Accepts the same options as embed/3.