CodeBasedOptions Struct
Options for configuring a code-based custom evaluator using a Lambda function.
Uses a Lambda function to implement custom evaluation logic.
| Source | aws-bedrockagentcore/lib/evaluation/evaluator-config.ts |
|---|---|
| Type last changed |
Example
ts
declare const evalFunction: lambda.IFunction;
const codeEvaluator = new agentcore.Evaluator(this, 'CodeEvaluator', {
evaluatorName: 'custom_code_evaluator',
level: agentcore.EvaluationLevel.TOOL_CALL,
description: 'Evaluates tool call accuracy using custom logic',
evaluatorConfig: agentcore.EvaluatorConfig.codeBased({
lambdaFunction: evalFunction,
timeout: cdk.Duration.seconds(30),
}),
});
python
# eval_function: lambda.IFunction
code_evaluator = agentcore.Evaluator(self, "CodeEvaluator",
evaluator_name="custom_code_evaluator",
level=agentcore.EvaluationLevel.TOOL_CALL,
description="Evaluates tool call accuracy using custom logic",
evaluator_config=agentcore.EvaluatorConfig.code_based(
lambda_function=eval_function,
timeout=cdk.Duration.seconds(30)
)
)
java
IFunction evalFunction;
Evaluator codeEvaluator = Evaluator.Builder.create(this, "CodeEvaluator")
.evaluatorName("custom_code_evaluator")
.level(EvaluationLevel.TOOL_CALL)
.description("Evaluates tool call accuracy using custom logic")
.evaluatorConfig(EvaluatorConfig.codeBased(CodeBasedOptions.builder()
.lambdaFunction(evalFunction)
.timeout(Duration.seconds(30))
.build()))
.build();
csharp
// Install: dotnet add package Amazon.CDK.Lib
IFunction evalFunction;
var codeEvaluator = new Evaluator(this, "CodeEvaluator", new EvaluatorProps {
EvaluatorName = "custom_code_evaluator",
Level = EvaluationLevel.TOOL_CALL,
Description = "Evaluates tool call accuracy using custom logic",
EvaluatorConfig = EvaluatorConfig.CodeBased(new CodeBasedOptions {
LambdaFunction = evalFunction,
Timeout = Duration.Seconds(30)
})
});
go
// Install: go get github.com/aws/aws-cdk-go/awscdk/v2
var evalFunction IFunction
codeEvaluator := agentcore.NewEvaluator(this, jsii.String("CodeEvaluator"), &EvaluatorProps{
EvaluatorName: jsii.String("custom_code_evaluator"),
Level: agentcore.EvaluationLevel_TOOL_CALL(),
Description: jsii.String("Evaluates tool call accuracy using custom logic"),
EvaluatorConfig: agentcore.EvaluatorConfig_CodeBased(&CodeBasedOptions{
LambdaFunction: evalFunction,
Timeout: cdk.Duration_Seconds(jsii.Number(30)),
}),
})
Properties
lambdaFunctionIFunctionlambda_functionIFunctionlambdaFunctionIFunctionLambdaFunctionIFunctionLambdaFunctionIFunction required #The Lambda function used for evaluation.
The function will be granted invoke permissions for the bedrock-agentcore.amazonaws.com service principal, scoped to this specific evaluator resource.
timeoutoptionalDurationtimeoutoptionalDurationtimeoutoptionalDurationTimeoutoptionalDurationTimeoutoptionalDuration #The timeout for the Lambda function invocation during evaluation.
Default: The AgentCore evaluation service's default Lambda timeout is used
When not specified, the AgentCore evaluation service uses its default timeout for Lambda-based evaluators.