Class MetricPromptBuilder (1.154.0)

MetricPromptBuilder(*, text: typing.Optional[str] = None, criteria: typing.Optional[dict[str, str]] = None, ratingScores: typing.Optional[dict[str, str]] = None, instruction: typing.Optional[str] = <factory>, metricDefinition: typing.Optional[str] = None, evaluationSteps: typing.Optional[dict[str, str]] = <factory>, fewShotExamples: typing.Optional[list[str]] = None)

Builder class for structured LLM-based metric prompt template.

Methods

MetricPromptBuilder

MetricPromptBuilder(*, text: typing.Optional[str] = None, criteria: typing.Optional[dict[str, str]] = None, ratingScores: typing.Optional[dict[str, str]] = None, instruction: typing.Optional[str] = <factory>, metricDefinition: typing.Optional[str] = None, evaluationSteps: typing.Optional[dict[str, str]] = <factory>, fewShotExamples: typing.Optional[list[str]] = 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.

__str__

__str__() -> str

Returns the fully constructed prompt template text.