Interface EvaluateRequest.Builder

  • Method Details

    • evaluatorId

      EvaluateRequest.Builder evaluatorId(String evaluatorId)

      The unique identifier of the evaluator to use for scoring. Can be a built-in evaluator (e.g., Builtin.Helpfulness, Builtin.Correctness) or a custom evaluator Id created through the control plane API.

      Parameters:
      evaluatorId - The unique identifier of the evaluator to use for scoring. Can be a built-in evaluator (e.g., Builtin.Helpfulness, Builtin.Correctness) or a custom evaluator Id created through the control plane API.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • evaluationInput

      EvaluateRequest.Builder evaluationInput(EvaluationInput evaluationInput)

      The input data containing agent session spans to be evaluated. Includes a list of spans in OpenTelemetry format from supported frameworks like Strands (AgentCore Runtime) or LangGraph with OpenInference instrumentation.

      Parameters:
      evaluationInput - The input data containing agent session spans to be evaluated. Includes a list of spans in OpenTelemetry format from supported frameworks like Strands (AgentCore Runtime) or LangGraph with OpenInference instrumentation.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • evaluationInput

      default EvaluateRequest.Builder evaluationInput(Consumer<EvaluationInput.Builder> evaluationInput)

      The input data containing agent session spans to be evaluated. Includes a list of spans in OpenTelemetry format from supported frameworks like Strands (AgentCore Runtime) or LangGraph with OpenInference instrumentation.

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

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

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

      EvaluateRequest.Builder evaluationTarget(EvaluationTarget evaluationTarget)

      The specific trace or span IDs to evaluate within the provided input. Allows targeting evaluation at different levels: individual tool calls, single request-response interactions (traces), or entire conversation sessions.

      Parameters:
      evaluationTarget - The specific trace or span IDs to evaluate within the provided input. Allows targeting evaluation at different levels: individual tool calls, single request-response interactions (traces), or entire conversation sessions.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • evaluationTarget

      default EvaluateRequest.Builder evaluationTarget(Consumer<EvaluationTarget.Builder> evaluationTarget)

      The specific trace or span IDs to evaluate within the provided input. Allows targeting evaluation at different levels: individual tool calls, single request-response interactions (traces), or entire conversation sessions.

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

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

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

      EvaluateRequest.Builder evaluationReferenceInputs(Collection<EvaluationReferenceInput> evaluationReferenceInputs)

      Ground truth data to compare against agent responses during evaluation. Allows to provide expected responses, assertions, and expected tool trajectories at different evaluation levels. Session-level reference inputs apply to the entire conversation, while trace-level reference inputs target specific request-response interactions identified by trace ID.

      Parameters:
      evaluationReferenceInputs - Ground truth data to compare against agent responses during evaluation. Allows to provide expected responses, assertions, and expected tool trajectories at different evaluation levels. Session-level reference inputs apply to the entire conversation, while trace-level reference inputs target specific request-response interactions identified by trace ID.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • evaluationReferenceInputs

      EvaluateRequest.Builder evaluationReferenceInputs(EvaluationReferenceInput... evaluationReferenceInputs)

      Ground truth data to compare against agent responses during evaluation. Allows to provide expected responses, assertions, and expected tool trajectories at different evaluation levels. Session-level reference inputs apply to the entire conversation, while trace-level reference inputs target specific request-response interactions identified by trace ID.

      Parameters:
      evaluationReferenceInputs - Ground truth data to compare against agent responses during evaluation. Allows to provide expected responses, assertions, and expected tool trajectories at different evaluation levels. Session-level reference inputs apply to the entire conversation, while trace-level reference inputs target specific request-response interactions identified by trace ID.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • evaluationReferenceInputs

      EvaluateRequest.Builder evaluationReferenceInputs(Consumer<EvaluationReferenceInput.Builder>... evaluationReferenceInputs)

      Ground truth data to compare against agent responses during evaluation. Allows to provide expected responses, assertions, and expected tool trajectories at different evaluation levels. Session-level reference inputs apply to the entire conversation, while trace-level reference inputs target specific request-response interactions identified by trace ID.

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

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to evaluationReferenceInputs(List<EvaluationReferenceInput>).

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

      EvaluateRequest.Builder overrideConfiguration(AwsRequestOverrideConfiguration overrideConfiguration)
      Description copied from interface: AwsRequest.Builder
      Add an optional request override configuration.
      Specified by:
      overrideConfiguration in interface AwsRequest.Builder
      Parameters:
      overrideConfiguration - The override configuration.
      Returns:
      This object for method chaining.
    • overrideConfiguration

      Description copied from interface: AwsRequest.Builder
      Add an optional request override configuration.
      Specified by:
      overrideConfiguration in interface AwsRequest.Builder
      Parameters:
      builderConsumer - A Consumer to which an empty AwsRequestOverrideConfiguration.Builder will be given.
      Returns:
      This object for method chaining.