Interface EvaluationDatasetMetricConfig.Builder

All Superinterfaces:
Buildable, CopyableBuilder<EvaluationDatasetMetricConfig.Builder,EvaluationDatasetMetricConfig>, SdkBuilder<EvaluationDatasetMetricConfig.Builder,EvaluationDatasetMetricConfig>, SdkPojo
Enclosing class:
EvaluationDatasetMetricConfig
public static interface EvaluationDatasetMetricConfig.Builder extends SdkPojo, CopyableBuilder<EvaluationDatasetMetricConfig.Builder,EvaluationDatasetMetricConfig>

  • Method Details

    • taskType

      EvaluationDatasetMetricConfig.Builder taskType(String taskType)

      The task type you want the model to carry out.

      Parameters:
      taskType - The task type you want the model to carry out.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • taskType

      EvaluationDatasetMetricConfig.Builder taskType(EvaluationTaskType taskType)

      The task type you want the model to carry out.

      Parameters:
      taskType - The task type you want the model to carry out.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • dataset

      EvaluationDatasetMetricConfig.Builder dataset(EvaluationDataset dataset)

      Specifies the prompt dataset.

      Parameters:
      dataset - Specifies the prompt dataset.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • dataset

      default EvaluationDatasetMetricConfig.Builder dataset(Consumer<EvaluationDataset.Builder> dataset)

      Specifies the prompt dataset.

      This is a convenience method that creates an instance of the EvaluationDataset.Builder avoiding the need to create one manually via EvaluationDataset.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to dataset(EvaluationDataset).

      Parameters:
      dataset - a consumer that will call methods on EvaluationDataset.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • metricNames

      EvaluationDatasetMetricConfig.Builder metricNames(Collection<String> metricNames)

      The names of the metrics used. For automated model evaluation jobs valid values are "Builtin.Accuracy", "Builtin.Robustness", and "Builtin.Toxicity". In human-based model evaluation jobs the array of strings must match the name parameter specified in HumanEvaluationCustomMetric.

      Parameters:
      metricNames - The names of the metrics used. For automated model evaluation jobs valid values are "Builtin.Accuracy", "Builtin.Robustness", and "Builtin.Toxicity". In human-based model evaluation jobs the array of strings must match the name parameter specified in HumanEvaluationCustomMetric.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • metricNames

      EvaluationDatasetMetricConfig.Builder metricNames(String... metricNames)

      The names of the metrics used. For automated model evaluation jobs valid values are "Builtin.Accuracy", "Builtin.Robustness", and "Builtin.Toxicity". In human-based model evaluation jobs the array of strings must match the name parameter specified in HumanEvaluationCustomMetric.

      Parameters:
      metricNames - The names of the metrics used. For automated model evaluation jobs valid values are "Builtin.Accuracy", "Builtin.Robustness", and "Builtin.Toxicity". In human-based model evaluation jobs the array of strings must match the name parameter specified in HumanEvaluationCustomMetric.
      Returns:
      Returns a reference to this object so that method calls can be chained together.