Class LLMBasedMetricSpec (1.141.0) 

LLMBasedMetricSpec(
    *,
    metricPromptTemplate: typing.Optional[str] = None,
    systemInstruction: typing.Optional[str] = None,
    judgeAutoraterConfig: typing.Optional[google.genai.types.AutoraterConfig] = None,
    rubricGroupKey: typing.Optional[str] = None,
    predefinedRubricGenerationSpec: typing.Optional[
        vertexai._genai.types.common.PredefinedMetricSpec
    ] = None,
    rubricGenerationSpec: typing.Optional[
        vertexai._genai.types.common.RubricGenerationSpec
    ] = None
)

Specification for an LLM based metric.

Methods

LLMBasedMetricSpec

LLMBasedMetricSpec(
    *,
    metricPromptTemplate: typing.Optional[str] = None,
    systemInstruction: typing.Optional[str] = None,
    judgeAutoraterConfig: typing.Optional[google.genai.types.AutoraterConfig] = None,
    rubricGroupKey: typing.Optional[str] = None,
    predefinedRubricGenerationSpec: typing.Optional[
        vertexai._genai.types.common.PredefinedMetricSpec
    ] = None,
    rubricGenerationSpec: typing.Optional[
        vertexai._genai.types.common.RubricGenerationSpec
    ] = 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.