Interface LlmAsAJudgeEvaluatorConfig.Builder
- All Superinterfaces:
Buildable,CopyableBuilder<LlmAsAJudgeEvaluatorConfig.Builder,,LlmAsAJudgeEvaluatorConfig> SdkBuilder<LlmAsAJudgeEvaluatorConfig.Builder,,LlmAsAJudgeEvaluatorConfig> SdkPojo
- Enclosing class:
LlmAsAJudgeEvaluatorConfig
-
Method Summary
Modifier and TypeMethodDescriptioninstructions(String instructions) The evaluation instructions that guide the language model in assessing agent performance, including criteria and evaluation guidelines.modelConfig(Consumer<EvaluatorModelConfig.Builder> modelConfig) The model configuration that specifies which foundation model to use and how to configure it for evaluation.modelConfig(EvaluatorModelConfig modelConfig) The model configuration that specifies which foundation model to use and how to configure it for evaluation.ratingScale(Consumer<RatingScale.Builder> ratingScale) The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.ratingScale(RatingScale ratingScale) The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder
copyMethods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder
applyMutation, buildMethods inherited from interface software.amazon.awssdk.core.SdkPojo
equalsBySdkFields, sdkFieldNameToField, sdkFields
-
Method Details
-
instructions
The evaluation instructions that guide the language model in assessing agent performance, including criteria and evaluation guidelines.
- Parameters:
instructions- The evaluation instructions that guide the language model in assessing agent performance, including criteria and evaluation guidelines.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
ratingScale
The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.
- Parameters:
ratingScale- The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
ratingScale
The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.
This is a convenience method that creates an instance of theRatingScale.Builderavoiding the need to create one manually viaRatingScale.builder().When the
Consumercompletes,SdkBuilder.build()is called immediately and its result is passed toratingScale(RatingScale).- Parameters:
ratingScale- a consumer that will call methods onRatingScale.Builder- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-
modelConfig
The model configuration that specifies which foundation model to use and how to configure it for evaluation.
- Parameters:
modelConfig- The model configuration that specifies which foundation model to use and how to configure it for evaluation.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelConfig
default LlmAsAJudgeEvaluatorConfig.Builder modelConfig(Consumer<EvaluatorModelConfig.Builder> modelConfig) The model configuration that specifies which foundation model to use and how to configure it for evaluation.
This is a convenience method that creates an instance of theEvaluatorModelConfig.Builderavoiding the need to create one manually viaEvaluatorModelConfig.builder().When the
Consumercompletes,SdkBuilder.build()is called immediately and its result is passed tomodelConfig(EvaluatorModelConfig).- Parameters:
modelConfig- a consumer that will call methods onEvaluatorModelConfig.Builder- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-