autointent.Embedder#

class autointent.Embedder(embedder_config)#

A wrapper for managing embedding models using sentence_transformers.SentenceTransformer.

This class handles initialization, saving, loading, and clearing of embedding models, as well as calculating embeddings for input texts.

clear_ram()#

Move the embedding model to CPU and delete it from memory.

delete()#

Delete the embedding model and its associated directory.

dump(path)#

Save the embedding model and metadata to disk.

Parameters:: path (pathlib.Path) – Path to the directory where the model will be saved.
Return type:: None

classmethod load(path, override_config=None)#

Load the embedding model and metadata from disk.

Parameters:

path (pathlib.Path | str) – Path to the directory where the model is stored.
override_config (autointent.configs.EmbedderConfig | None) – one can override presaved settings

Return type:

Embedder

embed(utterances, task_type=None)#

Calculate embeddings for a list of utterances.

Parameters:

utterances (list[str]) – List of input texts to calculate embeddings for.
task_type (autointent.configs.TaskTypeEnum | None) – Type of task for which embeddings are calculated.

Returns:

A numpy array of embeddings.

Return type:

numpy.typing.NDArray[numpy.float32]

similarity(embeddings1, embeddings2)#

Calculate similarity between two sets of embeddings.

Parameters:

embeddings1 (numpy.typing.NDArray[numpy.float32]) – First set of embeddings (size n).
embeddings2 (numpy.typing.NDArray[numpy.float32]) – Second set of embeddings (size m).

Returns:

A numpy array of similarities (size n x m).

Return type:

numpy.typing.NDArray[numpy.float32]