Module language_models (1.35.0)

Version 1.35.0

• 1.71.1 (latest)
• 1.71.0
• 1.70.0
• 1.69.0
• 1.68.0
• 1.67.1
• 1.66.0
• 1.65.0
• 1.63.0
• 1.62.0
• 1.60.0
• 1.59.0
• 1.58.0
• 1.57.0
• 1.56.0
• 1.55.0
• 1.54.1
• 1.53.0
• 1.52.0
• 1.51.0
• 1.50.0
• 1.49.0
• 1.48.0
• 1.47.0
• 1.46.0
• 1.45.0
• 1.44.0
• 1.43.0
• 1.39.0
• 1.38.1
• 1.37.0
• 1.36.4
• 1.35.0
• 1.34.0
• 1.33.1
• 1.32.0
• 1.31.1
• 1.30.1
• 1.29.0
• 1.28.1
• 1.27.1
• 1.26.1
• 1.25.0
• 1.24.1
• 1.23.0
• 1.22.1
• 1.21.0
• 1.20.0
• 1.19.1
• 1.18.3
• 1.17.1
• 1.16.1
• 1.15.1
• 1.14.0
• 1.13.1
• 1.12.1
• 1.11.0
• 1.10.0
• 1.9.0
• 1.8.1
• 1.7.1
• 1.6.2
• 1.5.0
• 1.4.3
• 1.3.0
• 1.2.0
• 1.1.1
• 1.0.1
• 0.9.0
• 0.8.0
• 0.7.1
• 0.6.0
• 0.5.1
• 0.4.0
• 0.3.1

Classes for working with language models.

Classes

ChatMessage

ChatMessage(content: str, author: str)

A chat message.

Author of the message.

ChatSession

ChatSession(
    model: vertexai.language_models.ChatModel,
    context: typing.Optional[str] = None,
    examples: typing.Optional[
        typing.List[vertexai.language_models.InputOutputTextPair]
    ] = None,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    message_history: typing.Optional[
        typing.List[vertexai.language_models.ChatMessage]
    ] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None,
)

ChatSession represents a chat session with a language model.

Within a chat session, the model keeps context and remembers the previous conversation.

CodeChatSession

CodeChatSession(
    model: vertexai.language_models.CodeChatModel,
    context: typing.Optional[str] = None,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    message_history: typing.Optional[
        typing.List[vertexai.language_models.ChatMessage]
    ] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None,
)

CodeChatSession represents a chat session with code chat language model.

Within a code chat session, the model keeps context and remembers the previous converstion.

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.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.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.DataFrame]
)

Spec for text generation model evaluation tasks.

EvaluationTextSummarizationSpec

EvaluationTextSummarizationSpec(
    ground_truth_data: typing.Union[typing.List[str], str, pandas.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.

The name of the downstream task the embeddings will be used for. Valid values: RETRIEVAL_QUERY Specifies the given text is a query in a search/retrieval setting. RETRIEVAL_DOCUMENT Specifies the given text is a document from the corpus being searched. SEMANTIC_SIMILARITY Specifies the given text will be used for STS. CLASSIFICATION Specifies that the given text will be classified. CLUSTERING Specifies that the embeddings will be used for clustering.

TextGenerationResponse

TextGenerationResponse(text: str, _prediction_response: typing.Any, is_blocked: bool = False, safety_attributes: typing.Dict[str, float] = <factory>)

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

The generated text

Scores for safety attributes. Learn more about the safety attributes here: https://cloud.google.com/vertex-ai/docs/generative-ai/learn/responsible-ai#safety_attribute_descriptions

TuningEvaluationSpec

TuningEvaluationSpec(
    evaluation_data: str,
    evaluation_interval: typing.Optional[int] = None,
    enable_early_stopping: 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.

The evaluation will run at every evaluation_interval tuning steps. Default: 20.

Vertex Tensorboard where to write the evaluation metrics. The Tensorboard must be in the same location as the tuning job.