Interface BedrockEvaluatorModelConfig.Builder

  • Method Details

    • modelId

      The identifier of the Amazon Bedrock model to use for evaluation. Must be a supported foundation model available in your region.

      Parameters:
      modelId - The identifier of the Amazon Bedrock model to use for evaluation. Must be a supported foundation model available in your region.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • inferenceConfig

      The inference configuration parameters that control model behavior during evaluation, including temperature, token limits, and sampling settings.

      Parameters:
      inferenceConfig - The inference configuration parameters that control model behavior during evaluation, including temperature, token limits, and sampling settings.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • inferenceConfig

      The inference configuration parameters that control model behavior during evaluation, including temperature, token limits, and sampling settings.

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

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

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

      BedrockEvaluatorModelConfig.Builder additionalModelRequestFields(Document additionalModelRequestFields)

      Additional model-specific request fields to customize model behavior beyond the standard inference configuration.

      Parameters:
      additionalModelRequestFields - Additional model-specific request fields to customize model behavior beyond the standard inference configuration.
      Returns:
      Returns a reference to this object so that method calls can be chained together.