get_evaluator ¶

def get_evaluator(
    self,
    evaluator_id: "capo_bedrock_agentcore_control.types.evaluator_id.EvaluatorId",
    *,
    config_overrides: Optional[BedrockAgentCoreControlClientConfig] = None,
    included_data: Optional[
        "capo_bedrock_agentcore_control.types.included_data.IncludedData"
    ] = None,
) -> "capo_bedrock_agentcore_control.types.get_evaluator_response.GetEvaluatorResponse":
    """<p> Retrieves detailed information about an evaluator, including its configuration, status, and metadata. Works with both built-in and custom evaluators. </p>

    Args:
        evaluator_id: <p> The unique identifier of the evaluator to retrieve. Can be a built-in evaluator ID (e.g., Builtin.Helpfulness) or a custom evaluator ID. </p>
        included_data: <p> Controls which data is returned in the response. <code>ALL_DATA</code> (default) returns the full evaluator including decrypted instructions and rating scale. For evaluators encrypted with a customer managed KMS key, this requires <code>kms:Decrypt</code> permission on the key. <code>METADATA_ONLY</code> returns evaluator metadata and model configuration without instructions or rating scale, and does not require any KMS permissions. </p>

    Raises:
        capo_bedrock_agentcore_control.errors.access_denied_exception.AccessDeniedException: <p>This exception is thrown when a request is denied per access permissions</p>
        capo_bedrock_agentcore_control.errors.internal_server_exception.InternalServerException: <p>This exception is thrown if there was an unexpected error during processing of request</p>
        capo_bedrock_agentcore_control.errors.resource_not_found_exception.ResourceNotFoundException: <p>This exception is thrown when a resource referenced by the operation does not exist</p>
        capo_bedrock_agentcore_control.errors.throttling_exception.ThrottlingException: <p>This exception is thrown when the number of requests exceeds the limit</p>
        capo_bedrock_agentcore_control.errors.validation_exception.ValidationException: <p>The input fails to satisfy the constraints specified by the service.</p>
        capo_bedrock_agentcore_control.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_bedrock_agentcore_control.types.get_evaluator_request.GetEvaluatorRequest]",
    ) -> OperationResponse[
        "capo_bedrock_agentcore_control.types.get_evaluator_response.GetEvaluatorResponse"
    ]:
        import capo_bedrock_agentcore_control._operations.amazon_bedrock_agent_core_control.get_evaluator

        output, http_response = (
            capo_bedrock_agentcore_control._operations.amazon_bedrock_agent_core_control.get_evaluator.get_evaluator(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    def _redact_output(
        output: "capo_bedrock_agentcore_control.types.get_evaluator_response.GetEvaluatorResponse",
    ) -> dict[str, Any]:
        import capo_bedrock_agentcore_control.types.get_evaluator_response

        return capo_bedrock_agentcore_control.types.get_evaluator_response.redact_sensitive(
            output
        )

    interceptors_, options_ = self.operation_options(
        config_overrides,
        OperationLogging("GetEvaluator", redact_output=_redact_output),
    )
    input_: capo_bedrock_agentcore_control.types.get_evaluator_request.GetEvaluatorRequest = {
        "evaluator_id": evaluator_id
    }
    if included_data is not None:
        input_["included_data"] = included_data

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output