Module language_models (1.75.0)

Classes for working with language models.

Classes

ChatMessage

ChatMessage(content: str, author: str)

A chat message.

CountTokensResponse

CountTokensResponse(
    total_tokens: int,
    total_billable_characters: int,
    _count_tokens_response: typing.Any,
)

The response from a count_tokens request. .. attribute:: total_tokens

The total number of tokens counted across all instances passed to the request.

:type: int

EvaluationClassificationMetric

EvaluationClassificationMetric(
    label_name: typing.Optional[str] = None,
    auPrc: typing.Optional[float] = None,
    auRoc: typing.Optional[float] = None,
    logLoss: typing.Optional[float] = None,
    confidenceMetrics: typing.Optional[
        typing.List[typing.Dict[str, typing.Any]]
    ] = None,
    confusionMatrix: typing.Optional[typing.Dict[str, typing.Any]] = None,
)

The evaluation metric response for classification metrics.

Parameters
Name	Description
`label_name`	`str` Optional. The name of the label associated with the metrics. This is only returned when `only_summary_metrics=False` is passed to evaluate().
`auPrc`	`float` Optional. The area under the precision recall curve.
`auRoc`	`float` Optional. The area under the receiver operating characteristic curve.
`logLoss`	`float` Optional. Logarithmic loss.
`confidenceMetrics`	`List[Dict[str, Any]]` Optional. This is only returned when `only_summary_metrics=False` is passed to evaluate().
`confusionMatrix`	`Dict[str, Any]` Optional. This is only returned when `only_summary_metrics=False` is passed to evaluate().

EvaluationMetric

EvaluationMetric(
    bleu: typing.Optional[float] = None, rougeLSum: typing.Optional[float] = None
)

The evaluation metric response.

Parameters
Name	Description
`bleu`	`float` Optional. BLEU (Bilingual evauation understudy). Scores based on sacrebleu implementation.
`rougeLSum`	`float` Optional. ROUGE-L (Longest Common Subsequence) scoring at summary level.

EvaluationQuestionAnsweringSpec

EvaluationQuestionAnsweringSpec(
    ground_truth_data: typing.Union[typing.List[str], str, pandas.core.frame.DataFrame],
    task_name: str = "question-answering",
)

Spec for question answering model evaluation tasks.

EvaluationTextClassificationSpec

EvaluationTextClassificationSpec(
    ground_truth_data: typing.Union[typing.List[str], str, pandas.core.frame.DataFrame],
    target_column_name: str,
    class_names: typing.List[str],
)

Spec for text classification model evaluation tasks.

Parameters
Name	Description
`target_column_name`	`str` Required. The label column in the dataset provided in `ground_truth_data`. Required when task_name='text-classification'.
`class_names`	`List[str]` Required. A list of all possible label names in your dataset. Required when task_name='text-classification'.

EvaluationTextGenerationSpec

EvaluationTextGenerationSpec(
    ground_truth_data: typing.Union[typing.List[str], str, pandas.core.frame.DataFrame]
)

Spec for text generation model evaluation tasks.

EvaluationTextSummarizationSpec

EvaluationTextSummarizationSpec(
    ground_truth_data: typing.Union[typing.List[str], str, pandas.core.frame.DataFrame],
    task_name: str = "summarization",
)

Spec for text summarization model evaluation tasks.

InputOutputTextPair

InputOutputTextPair(input_text: str, output_text: str)

InputOutputTextPair represents a pair of input and output texts.

TextEmbedding

TextEmbedding(
    values: typing.List[float],
    statistics: typing.Optional[
        vertexai.language_models.TextEmbeddingStatistics
    ] = None,
    _prediction_response: typing.Optional[
        google.cloud.aiplatform.models.Prediction
    ] = None,
)

Text embedding vector and statistics.

TextEmbeddingInput

TextEmbeddingInput(
    text: str,
    task_type: typing.Optional[str] = None,
    title: typing.Optional[str] = None,
)

Structural text embedding input.

TextGenerationResponse

TextGenerationResponse(text: str, _prediction_response: typing.Any, is_blocked: bool = False, errors: typing.Tuple[int] = (), safety_attributes: typing.Dict[str, float] = <factory>, grounding_metadata: typing.Optional[vertexai.language_models._language_models.GroundingMetadata] = None)

TextGenerationResponse represents a response of a language model. .. attribute:: text

The generated text

:type: str

TuningEvaluationSpec

TuningEvaluationSpec(
    evaluation_data: typing.Optional[str] = None,
    evaluation_interval: typing.Optional[int] = None,
    enable_early_stopping: typing.Optional[bool] = None,
    enable_checkpoint_selection: typing.Optional[bool] = None,
    tensorboard: typing.Optional[
        typing.Union[
            google.cloud.aiplatform.tensorboard.tensorboard_resource.Tensorboard, str
        ]
    ] = None,
)

Specification for model evaluation to perform during tuning.