Skip to content
v2.275.0

OpenResponsesEvaluatorModelConfigProperty Struct ​

The configuration for using OpenResponses-compatible models in evaluator assessments.

Example ​

ts
// 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-lib';
const openResponsesEvaluatorModelConfigProperty: bedrockagentcore.CfnEvaluator.OpenResponsesEvaluatorModelConfigProperty = {
  modelId: 'modelId',

  // the properties below are optional
  maxOutputTokens: 123,
  reasoning: {
    effort: 'effort',
  },
  temperature: 123,
  topP: 123,
};

Properties ​

maxOutputTokensoptionalnumbermax_output_tokensoptionalint | floatmaxOutputTokensoptionalNumberMaxOutputTokensoptionaldoubleMaxOutputTokensoptional*float64#
The maximum number of output tokens to generate, including visible output and reasoning tokens.
modelIdstringmodel_idstrmodelIdStringModelIdstringModelId*stringrequired#
The identifier of the model to use for evaluation.
reasoningoptionalIResolvable | CfnEvaluator.ReasoningConfigurationPropertyreasoningoptionaltyping.Union[IResolvable, ReasoningConfigurationProperty]reasoningoptionalIResolvableReasoningoptionalIResolvableReasoningoptionalinterface{}#
The reasoning configuration for reasoning models.
temperatureoptionalnumbertemperatureoptionalint | floattemperatureoptionalNumberTemperatureoptionaldoubleTemperatureoptional*float64#
The sampling temperature between 0 and 2.
topPoptionalnumbertop_poptionalint | floattopPoptionalNumberTopPoptionaldoubleTopPoptional*float64#
The nucleus sampling probability mass between 0 and 1.