Class EvaluatorConfig

java.lang.Object
software.amazon.awssdk.services.bedrockagentcorecontrol.model.EvaluatorConfig
All Implemented Interfaces:
Serializable, SdkPojo, ToCopyableBuilder<EvaluatorConfig.Builder,EvaluatorConfig>
@Generated("software.amazon.awssdk:codegen") public final class EvaluatorConfig extends Object implements SdkPojo, Serializable, ToCopyableBuilder<EvaluatorConfig.Builder,EvaluatorConfig>

The configuration that defines how an evaluator assesses agent performance, including the evaluation method and parameters.

See Also:

  • Method Details

    • llmAsAJudge

      public final LlmAsAJudgeEvaluatorConfig llmAsAJudge()

      The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

      Returns:
      The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

    • codeBased

      public final CodeBasedEvaluatorConfig codeBased()

      Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

      Returns:
      Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

    • derived

      public final DerivedEvaluatorConfig derived()

      The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.

      Returns:
      The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.

    • toBuilder

      public EvaluatorConfig.Builder toBuilder()
      Description copied from interface: ToCopyableBuilder
      Take this object and create a builder that contains all of the current property values of this object.
      Specified by:
      toBuilder in interface ToCopyableBuilder<EvaluatorConfig.Builder,EvaluatorConfig>
      Returns:
      a builder for type T

    • builder

      public static EvaluatorConfig.Builder builder()

    • serializableBuilderClass

      public static Class<? extends EvaluatorConfig.Builder> serializableBuilderClass()

    • hashCode

      public final int hashCode()
      Overrides:
      hashCode in class Object

    • equals

      public final boolean equals(Object obj)
      Overrides:
      equals in class Object

    • equalsBySdkFields

      public final boolean equalsBySdkFields(Object obj)
      Description copied from interface: SdkPojo
      Indicates whether some other object is "equal to" this one by SDK fields. An SDK field is a modeled, non-inherited field in an SdkPojo class, and is generated based on a service model.

      If an SdkPojo class does not have any inherited fields, equalsBySdkFields and equals are essentially the same.

      Specified by:
      equalsBySdkFields in interface SdkPojo
      Parameters:
      obj - the object to be compared with
      Returns:
      true if the other object equals to this object by sdk fields, false otherwise.

    • toString

      public final String toString()
      Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value.
      Overrides:
      toString in class Object

    • getValueForField

      public final <T> Optional<T> getValueForField(String fieldName, Class<T> clazz)

    • fromLlmAsAJudge

      public static EvaluatorConfig fromLlmAsAJudge(LlmAsAJudgeEvaluatorConfig llmAsAJudge)
      Create an instance of this class with llmAsAJudge() initialized to the given value.

      The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

      Parameters:
      llmAsAJudge - The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

    • fromLlmAsAJudge

      public static EvaluatorConfig fromLlmAsAJudge(Consumer<LlmAsAJudgeEvaluatorConfig.Builder> llmAsAJudge)
      Create an instance of this class with llmAsAJudge() initialized to the given value.

      The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

      Parameters:
      llmAsAJudge - The LLM-as-a-Judge configuration that uses a language model to evaluate agent performance based on custom instructions and rating scales.

    • fromCodeBased

      public static EvaluatorConfig fromCodeBased(CodeBasedEvaluatorConfig codeBased)
      Create an instance of this class with codeBased() initialized to the given value.

      Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

      Parameters:
      codeBased - Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

    • fromCodeBased

      public static EvaluatorConfig fromCodeBased(Consumer<CodeBasedEvaluatorConfig.Builder> codeBased)
      Create an instance of this class with codeBased() initialized to the given value.

      Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

      Parameters:
      codeBased - Configuration for a code-based evaluator that uses a customer-managed Lambda function to programmatically assess agent performance.

    • fromDerived

      public static EvaluatorConfig fromDerived(DerivedEvaluatorConfig derived)
      Create an instance of this class with derived() initialized to the given value.

      The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.

      Parameters:
      derived - The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.

    • fromDerived

      public static EvaluatorConfig fromDerived(Consumer<DerivedEvaluatorConfig.Builder> derived)
      Create an instance of this class with derived() initialized to the given value.

      The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.

      Parameters:
      derived - The configuration for an evaluator derived from an existing base evaluator (a built-in or third-party evaluator), run on your own model. The base evaluator supplies the prompt and scoring.

    • type

      public EvaluatorConfig.Type type()
      Retrieve an enum value representing which member of this object is populated. When this class is returned in a service response, this will be EvaluatorConfig.Type.UNKNOWN_TO_SDK_VERSION if the service returned a member that is only known to a newer SDK version. When this class is created directly in your code, this will be EvaluatorConfig.Type.UNKNOWN_TO_SDK_VERSION if zero members are set, and null if more than one member is set.

    • sdkFields

      public final List<SdkField<?>> sdkFields()
      Specified by:
      sdkFields in interface SdkPojo
      Returns:
      List of SdkField in this POJO. May be empty list but should never be null.

    • sdkFieldNameToField

      public final Map<String,SdkField<?>> sdkFieldNameToField()
      Specified by:
      sdkFieldNameToField in interface SdkPojo
      Returns:
      The mapping between the field name and its corresponding field.