interface LlmAsAJudgeEvaluatorConfigProperty

Language	Type name
.NET	`Amazon.CDK.CfnPropertyMixins.AWS.BedrockAgentCore.CfnEvaluatorPropsMixin.LlmAsAJudgeEvaluatorConfigProperty`
Go	`github.com/aws/aws-cdk-go/awscdkcfnpropertymixins/v2/awsbedrockagentcore#CfnEvaluatorPropsMixin_LlmAsAJudgeEvaluatorConfigProperty`
Java	`software.amazon.awscdk.cfnpropertymixins.services.bedrockagentcore.CfnEvaluatorPropsMixin.LlmAsAJudgeEvaluatorConfigProperty`
Python	`aws_cdk.cfn_property_mixins.aws_bedrockagentcore.CfnEvaluatorPropsMixin.LlmAsAJudgeEvaluatorConfigProperty`
TypeScript	`@aws-cdk/cfn-property-mixins` » `aws_bedrockagentcore` » `CfnEvaluatorPropsMixin` » `LlmAsAJudgeEvaluatorConfigProperty`

The configuration for LLM-as-a-Judge evaluation.

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_bedrockagentcore as bedrockagentcore } from '@aws-cdk/cfn-property-mixins';

declare const additionalModelRequestFields: any;
const llmAsAJudgeEvaluatorConfigProperty: bedrockagentcore.CfnEvaluatorPropsMixin.LlmAsAJudgeEvaluatorConfigProperty = {
  instructions: 'instructions',
  modelConfig: {
    bedrockEvaluatorModelConfig: {
      additionalModelRequestFields: additionalModelRequestFields,
      inferenceConfig: {
        maxTokens: 123,
        temperature: 123,
        topP: 123,
      },
      modelId: 'modelId',
    },
  },
  ratingScale: {
    categorical: [{
      definition: 'definition',
      label: 'label',
    }],
    numerical: [{
      definition: 'definition',
      label: 'label',
      value: 123,
    }],
  },
};

Properties

Name	Type	Description
instructions?	`string`	The evaluation instructions that guide the language model in assessing agent performance.
modelConfig?	`IResolvable` `\|` `EvaluatorModelConfigProperty`	The model configuration that specifies which foundation model to use for evaluation.
ratingScale?	`IResolvable` `\|` `RatingScaleProperty`	The rating scale that defines how evaluators should score agent performance.

instructions?

Type: string (optional)

The evaluation instructions that guide the language model in assessing agent performance.

modelConfig?

Type: IResolvable | EvaluatorModelConfigProperty (optional)

The model configuration that specifies which foundation model to use for evaluation.

ratingScale?

Type: IResolvable | RatingScaleProperty (optional)

The rating scale that defines how evaluators should score agent performance.

AWS CDK