Class Evals (1.129.0)

Version latest

• 1.122.0 (latest)
• 1.121.0
• 1.120.0
• 1.119.0
• 1.118.0
• 1.117.0
• 1.95.1
• 1.94.0
• 1.93.1
• 1.92.0
• 1.91.0
• 1.90.0
• 1.89.0
• 1.88.0
• 1.87.0
• 1.86.0
• 1.85.0
• 1.84.0
• 1.83.0
• 1.82.0
• 1.81.0
• 1.80.0
• 1.79.0
• 1.78.0
• 1.77.0
• 1.76.0
• 1.75.0
• 1.74.0
• 1.73.0
• 1.72.0
• 1.71.1
• 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

Evals(api_client_: google.genai._api_client.BaseApiClient)

API documentation for Evals class.

Methods

batch_evaluate

batch_evaluate(
    *,
    dataset: typing.Union[
        vertexai._genai.types.common.EvaluationDataset,
        vertexai._genai.types.common.EvaluationDatasetDict,
    ],
    metrics: list[
        typing.Union[
            vertexai._genai.types.common.Metric, vertexai._genai.types.common.MetricDict
        ]
    ],
    dest: str,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.EvaluateDatasetConfig,
            vertexai._genai.types.common.EvaluateDatasetConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluateDatasetOperation

Evaluates a dataset based on a set of given metrics.

create_evaluation_item

create_evaluation_item(
    *,
    evaluation_item_type: vertexai._genai.types.common.EvaluationItemType,
    gcs_uri: str,
    display_name: typing.Optional[str] = None,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.CreateEvaluationItemConfig,
            vertexai._genai.types.common.CreateEvaluationItemConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationItem

Creates an EvaluationItem.

create_evaluation_run

create_evaluation_run(
    *,
    dataset: typing.Union[
        vertexai._genai.types.common.EvaluationRunDataSource,
        vertexai._genai.types.common.EvaluationDataset,
    ],
    dest: str,
    metrics: list[
        typing.Union[
            vertexai._genai.types.common.EvaluationRunMetric,
            vertexai._genai.types.common.EvaluationRunMetricDict,
        ]
    ],
    name: typing.Optional[str] = None,
    display_name: typing.Optional[str] = None,
    agent_info: typing.Optional[
        typing.Union[
            vertexai._genai.types.evals.AgentInfo,
            vertexai._genai.types.evals.AgentInfoDict,
        ]
    ] = None,
    labels: typing.Optional[dict[str, str]] = None,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.CreateEvaluationRunConfig,
            vertexai._genai.types.common.CreateEvaluationRunConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationRun

Creates an EvaluationRun.

create_evaluation_set

create_evaluation_set(
    *,
    evaluation_items: list[str],
    display_name: typing.Optional[str] = None,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.CreateEvaluationSetConfig,
            vertexai._genai.types.common.CreateEvaluationSetConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationSet

Creates an EvaluationSet.

evaluate

evaluate(
    *,
    dataset: typing.Union[
        pandas.core.frame.DataFrame,
        vertexai._genai.types.common.EvaluationDataset,
        vertexai._genai.types.common.EvaluationDatasetDict,
        list[
            typing.Union[
                vertexai._genai.types.common.EvaluationDataset,
                vertexai._genai.types.common.EvaluationDatasetDict,
            ]
        ],
    ],
    metrics: typing.Optional[
        list[
            typing.Union[
                vertexai._genai.types.common.Metric,
                vertexai._genai.types.common.MetricDict,
            ]
        ]
    ] = None,
    location: typing.Optional[str] = None,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.EvaluateMethodConfig,
            vertexai._genai.types.common.EvaluateMethodConfigDict,
        ]
    ] = None,
    **kwargs
) -> vertexai._genai.types.common.EvaluationResult

Evaluates candidate responses in the provided dataset(s) using the specified metrics.

evaluate_instances

evaluate_instances(
    *, metric_config: vertexai._genai.types.common._EvaluateInstancesRequestParameters
) -> vertexai._genai.types.common.EvaluateInstancesResponse

Evaluates an instance of a model.

generate_rubrics

generate_rubrics(
    *,
    src: typing.Union[
        str, pd.DataFrame, vertexai._genai.types.common.EvaluationDataset
    ],
    rubric_group_name: str,
    prompt_template: typing.Optional[str] = None,
    generator_model_config: typing.Optional[genai_types.AutoraterConfigOrDict] = None,
    rubric_content_type: typing.Optional[types.RubricContentType] = None,
    rubric_type_ontology: typing.Optional[list[str]] = None,
    predefined_spec_name: typing.Optional[
        typing.Union[str, types.PrebuiltMetric]
    ] = None,
    metric_spec_parameters: typing.Optional[dict[str, typing.Any]] = None,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.RubricGenerationConfig,
            vertexai._genai.types.common.RubricGenerationConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationDataset

Generates rubrics for each prompt in the source and adds them as a new column structured as a dictionary.

You can generate rubrics by providing either:

1. A predefined_spec_name to use a Vertex AI backend recipe.
2. A prompt_template along with other configuration parameters (generator_model_config, rubric_content_type, rubric_type_ontology) for custom rubric generation.

These two modes are mutually exclusive.

get_evaluation_item

get_evaluation_item(
    *,
    name: str,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.GetEvaluationItemConfig,
            vertexai._genai.types.common.GetEvaluationItemConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationItem

Retrieves an EvaluationItem from the resource name.

get_evaluation_run

get_evaluation_run(
    *,
    name: str,
    include_evaluation_items: bool = False,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.GetEvaluationRunConfig,
            vertexai._genai.types.common.GetEvaluationRunConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationRun

Retrieves an EvaluationRun from the resource name.

Exceptions
Type	Description
ValueError	If the name is empty or invalid.

get_evaluation_set

get_evaluation_set(
    *,
    name: str,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.GetEvaluationSetConfig,
            vertexai._genai.types.common.GetEvaluationSetConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationSet

Retrieves an EvaluationSet from the resource name.

run_inference

run_inference(
    *,
    src: typing.Union[
        str, pandas.core.frame.DataFrame, vertexai._genai.types.common.EvaluationDataset
    ],
    model: typing.Optional[
        typing.Union[str, typing.Callable[[typing.Any], typing.Any]]
    ] = None,
    agent: typing.Optional[
        typing.Union[str, vertexai._genai.types.common.AgentEngine]
    ] = None,
    location: typing.Optional[str] = None,
    config: typing.Optional[
        typing.Union[
            vertexai._genai.types.common.EvalRunInferenceConfig,
            vertexai._genai.types.common.EvalRunInferenceConfigDict,
        ]
    ] = None
) -> vertexai._genai.types.common.EvaluationDataset

Runs inference on a dataset for evaluation.