Updates a custom evaluator's configuration, description, or evaluation level¶

Description¶

Updates a custom evaluator's configuration, description, or evaluation level. Built-in evaluators cannot be updated. The evaluator must not be locked for modification.

Usage¶

bedrockagentcorecontrol_update_evaluator(clientToken, evaluatorId,
  description, evaluatorConfig, level, kmsKeyArn)

Arguments¶

clientToken

A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don't specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn't return an error. For more information, see Ensuring idempotency.
evaluatorId

[required] The unique identifier of the evaluator to update.
description

The updated description of the evaluator.
evaluatorConfig

The updated configuration for the evaluator. Specify either LLM-as-a-Judge settings with instructions, rating scale, and model configuration, or code-based settings with a customer-managed Lambda function.
level

The updated evaluation level (TOOL_CALL, TRACE, or SESSION) that determines the scope of evaluation.
kmsKeyArn

The Amazon Resource Name (ARN) of a customer managed KMS key to use for encrypting sensitive evaluator data. Specify a new key ARN to rotate the encryption key, or specify a key ARN to add encryption to an evaluator that was previously created without one. When you rotate to a new key, the service decrypts the existing data with the old key and re-encrypts it with the new key. Only symmetric encryption KMS keys are supported. For more information, see Encryption at rest for AgentCore Evaluations.

Value¶

A list with the following syntax:

list(
  evaluatorArn = "string",
  evaluatorId = "string",
  updatedAt = as.POSIXct(
    "2015-01-01"
  ),
  status = "ACTIVE"|"CREATING"|"CREATE_FAILED"|"UPDATING"|"UPDATE_FAILED"|"DELETING"
)

Request syntax¶

svc$update_evaluator(
  clientToken = "string",
  evaluatorId = "string",
  description = "string",
  evaluatorConfig = list(
    llmAsAJudge = list(
      instructions = "string",
      ratingScale = list(
        numerical = list(
          list(
            definition = "string",
            value = 123.0,
            label = "string"
          )
        ),
        categorical = list(
          list(
            definition = "string",
            label = "string"
          )
        )
      ),
      modelConfig = list(
        bedrockEvaluatorModelConfig = list(
          modelId = "string",
          inferenceConfig = list(
            maxTokens = 123,
            temperature = 123.0,
            topP = 123.0,
            stopSequences = list(
              "string"
            )
          ),
          additionalModelRequestFields = list()
        ),
        responsesEvaluatorModelConfig = list(
          modelId = "string",
          maxOutputTokens = 123,
          temperature = 123.0,
          topP = 123.0,
          reasoning = list(
            effort = "string"
          )
        )
      )
    ),
    codeBased = list(
      lambdaConfig = list(
        lambdaArn = "string",
        lambdaTimeoutInSeconds = 123
      )
    ),
    derived = list(
      baseEvaluatorId = "string",
      modelConfig = list(
        bedrockEvaluatorModelConfig = list(
          modelId = "string",
          inferenceConfig = list(
            maxTokens = 123,
            temperature = 123.0,
            topP = 123.0,
            stopSequences = list(
              "string"
            )
          ),
          additionalModelRequestFields = list()
        ),
        responsesEvaluatorModelConfig = list(
          modelId = "string",
          maxOutputTokens = 123,
          temperature = 123.0,
          topP = 123.0,
          reasoning = list(
            effort = "string"
          )
        )
      )
    )
  ),
  level = "TOOL_CALL"|"TRACE"|"SESSION",
  kmsKeyArn = "string"
)