Class UnifiedMetric (1.144.0) 

UnifiedMetric(
    *,
    bleuSpec: typing.Optional[google.genai.types.BleuSpec] = None,
    rougeSpec: typing.Optional[google.genai.types.RougeSpec] = None,
    pointwiseMetricSpec: typing.Optional[google.genai.types.PointwiseMetricSpec] = None,
    llmBasedMetricSpec: typing.Optional[google.genai.types.LLMBasedMetricSpec] = None,
    customCodeExecutionSpec: typing.Optional[
        vertexai._genai.types.common.CustomCodeExecutionSpec
    ] = None,
    predefinedMetricSpec: typing.Optional[
        google.genai.types.PredefinedMetricSpec
    ] = None,
    computationBasedMetricSpec: typing.Optional[
        google.genai.types.ComputationBasedMetricSpec
    ] = None
)

The unified metric used for evaluation.

Methods

UnifiedMetric

UnifiedMetric(
    *,
    bleuSpec: typing.Optional[google.genai.types.BleuSpec] = None,
    rougeSpec: typing.Optional[google.genai.types.RougeSpec] = None,
    pointwiseMetricSpec: typing.Optional[google.genai.types.PointwiseMetricSpec] = None,
    llmBasedMetricSpec: typing.Optional[google.genai.types.LLMBasedMetricSpec] = None,
    customCodeExecutionSpec: typing.Optional[
        vertexai._genai.types.common.CustomCodeExecutionSpec
    ] = None,
    predefinedMetricSpec: typing.Optional[
        google.genai.types.PredefinedMetricSpec
    ] = None,
    computationBasedMetricSpec: typing.Optional[
        google.genai.types.ComputationBasedMetricSpec
    ] = None
)

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.