Class EvaluateInstancesResponse (1.144.0) 

EvaluateInstancesResponse(
    *,
    rubricBasedMetricResult: typing.Optional[
        vertexai._genai.types.common.RubricBasedMetricResult
    ] = None,
    metricResults: typing.Optional[
        list[vertexai._genai.types.common.MetricResult]
    ] = None,
    bleuResults: typing.Optional[vertexai._genai.types.common.BleuResults] = None,
    cometResult: typing.Optional[vertexai._genai.types.common.CometResult] = None,
    exactMatchResults: typing.Optional[
        vertexai._genai.types.common.ExactMatchResults
    ] = None,
    metricxResult: typing.Optional[vertexai._genai.types.common.MetricxResult] = None,
    pairwiseMetricResult: typing.Optional[
        google.genai.types.PairwiseMetricResult
    ] = None,
    pointwiseMetricResult: typing.Optional[
        google.genai.types.PointwiseMetricResult
    ] = None,
    rougeResults: typing.Optional[vertexai._genai.types.common.RougeResults] = None,
    toolCallValidResults: typing.Optional[
        vertexai._genai.types.common.ToolCallValidResults
    ] = None,
    toolNameMatchResults: typing.Optional[
        vertexai._genai.types.common.ToolNameMatchResults
    ] = None,
    toolParameterKeyMatchResults: typing.Optional[
        vertexai._genai.types.common.ToolParameterKeyMatchResults
    ] = None,
    toolParameterKvMatchResults: typing.Optional[
        vertexai._genai.types.common.ToolParameterKVMatchResults
    ] = None
)

Result of evaluating an LLM metric.

Methods

EvaluateInstancesResponse

EvaluateInstancesResponse(
    *,
    rubricBasedMetricResult: typing.Optional[
        vertexai._genai.types.common.RubricBasedMetricResult
    ] = None,
    metricResults: typing.Optional[
        list[vertexai._genai.types.common.MetricResult]
    ] = None,
    bleuResults: typing.Optional[vertexai._genai.types.common.BleuResults] = None,
    cometResult: typing.Optional[vertexai._genai.types.common.CometResult] = None,
    exactMatchResults: typing.Optional[
        vertexai._genai.types.common.ExactMatchResults
    ] = None,
    metricxResult: typing.Optional[vertexai._genai.types.common.MetricxResult] = None,
    pairwiseMetricResult: typing.Optional[
        google.genai.types.PairwiseMetricResult
    ] = None,
    pointwiseMetricResult: typing.Optional[
        google.genai.types.PointwiseMetricResult
    ] = None,
    rougeResults: typing.Optional[vertexai._genai.types.common.RougeResults] = None,
    toolCallValidResults: typing.Optional[
        vertexai._genai.types.common.ToolCallValidResults
    ] = None,
    toolNameMatchResults: typing.Optional[
        vertexai._genai.types.common.ToolNameMatchResults
    ] = None,
    toolParameterKeyMatchResults: typing.Optional[
        vertexai._genai.types.common.ToolParameterKeyMatchResults
    ] = None,
    toolParameterKvMatchResults: typing.Optional[
        vertexai._genai.types.common.ToolParameterKVMatchResults
    ] = 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.