autointent.Embedder

class autointent.Embedder(model_name, device='cpu', batch_size=32, max_length=None, use_cache=False)

A wrapper for managing embedding models using Sentence Transformers.

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

Parameters:

• model_name (str | pathlib.Path)

• device (str)

• batch_size (int)

• max_length (int | None)

• use_cache (bool)

embedder_subdir: str = 'sentence_transformers'

metadata_dict_name: str = 'metadata.json'

model_name

device = 'cpu'

batch_size = 32

max_length = None

use_cache = False

logger

__hash__()

Compute a hash value for the Embedder.

Returns:

The hash value of the Embedder.

Return type:

int

clear_ram()

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

Return type:

None

delete()

Delete the embedding model and its associated directory.

Return type:

None

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

load(path)

Load the embedding model and metadata from disk.

Parameters:

path (pathlib.Path | str) – Path to the directory where the model is stored.

Return type:

None

embed(utterances)

Calculate embeddings for a list of utterances.

Parameters:

utterances (list[str]) – List of input texts to calculate embeddings for.

Returns:

A numpy array of embeddings.

Return type:

numpy.typing.NDArray[numpy.float32]