Class TextEmbeddingModel (1.50.0)

TextEmbeddingModel(model_id: str, endpoint_name: typing.Optional[str] = None)

Creates a LanguageModel.

This constructor should not be called directly. Use LanguageModel.from_pretrained(model_name=...) instead.

Parameters

Name Description
model_id str

Identifier of a Vertex LLM. Example: "text-bison@001"

endpoint_name typing.Optional[str]

Vertex Endpoint resource name for the model

Methods

deploy_tuned_model

deploy_tuned_model(
    tuned_model_name: str,
    machine_type: typing.Optional[str] = None,
    accelerator: typing.Optional[str] = None,
    accelerator_count: typing.Optional[int] = None,
) -> vertexai.language_models._language_models._LanguageModel

Loads the specified tuned language model.

Parameters
Name Description
machine_type typing.Optional[str]

Machine type. E.g., "a2-highgpu-1g". See also: https://cloud.google.com/vertex-ai/docs/training/configure-compute.

accelerator typing.Optional[str]

Kind of accelerator. E.g., "NVIDIA_TESLA_A100". See also: https://cloud.google.com/vertex-ai/docs/training/configure-compute.

accelerator_count typing.Optional[int]

Count of accelerators.

from_pretrained

from_pretrained(model_name: str) -> vertexai._model_garden._model_garden_models.T

Loads a _ModelGardenModel.

Parameter
Name Description
model_name str

Name of the model.

Exceptions
Type Description
ValueError If model_name is unknown.
ValueError If model does not support this class.

get_embeddings

get_embeddings(
    texts: typing.List[typing.Union[str, vertexai.language_models.TextEmbeddingInput]],
    *,
    auto_truncate: bool = True,
    output_dimensionality: typing.Optional[int] = None
) -> typing.List[vertexai.language_models.TextEmbedding]

Calculates embeddings for the given texts.

Parameter
Name Description
texts typing.List[typing.Union[str, vertexai.language_models.TextEmbeddingInput]]

A list of texts or TextEmbeddingInput objects to embed.

get_embeddings_async

get_embeddings_async(
    texts: typing.List[typing.Union[str, vertexai.language_models.TextEmbeddingInput]],
    *,
    auto_truncate: bool = True,
    output_dimensionality: typing.Optional[int] = None
) -> typing.List[vertexai.language_models.TextEmbedding]

Asynchronously calculates embeddings for the given texts.

Parameter
Name Description
texts typing.List[typing.Union[str, vertexai.language_models.TextEmbeddingInput]]

A list of texts or TextEmbeddingInput objects to embed.

get_tuned_model

get_tuned_model(*args, **kwargs)

Loads the specified tuned language model.

list_tuned_model_names

list_tuned_model_names() -> typing.Sequence[str]

Lists the names of tuned models.

tune_model

tune_model(
    *,
    training_data: typing.Optional[str] = None,
    corpus_data: typing.Optional[str] = None,
    queries_data: typing.Optional[str] = None,
    test_data: typing.Optional[str] = None,
    validation_data: typing.Optional[str] = None,
    batch_size: typing.Optional[int] = None,
    train_steps: typing.Optional[int] = None,
    tuned_model_location: typing.Optional[str] = None,
    model_display_name: typing.Optional[str] = None,
    task_type: typing.Optional[str] = None,
    machine_type: typing.Optional[str] = None,
    accelerator: typing.Optional[str] = None,
    accelerator_count: typing.Optional[int] = None
) -> vertexai.language_models._language_models._LanguageModelTuningJob

Tunes a model based on training data.

This method launches and returns an asynchronous model tuning job. Usage:

tuning_job = model.tune_model(...)
... do some other work
tuned_model = tuning_job.get_tuned_model()  # Blocks until tuning is complete
Exceptions
Type Description
ValueError If the "tuned_model_location" value is not supported
RuntimeError If the model does not support tuning