get_scaling_configuration_recommendation ¶

def get_scaling_configuration_recommendation(
    self,
    *,
    config_overrides: Optional[SageMakerClientConfig] = None,
    inference_recommendations_job_name: Optional[
        "capo_sagemaker.types.recommendation_job_name.RecommendationJobName"
    ] = None,
    recommendation_id: Optional["capo_sagemaker.types.string.String"] = None,
    endpoint_name: Optional[
        "capo_sagemaker.types.endpoint_name.EndpointName"
    ] = None,
    target_cpu_utilization_per_core: Optional[
        "capo_sagemaker.types.utilization_percentage_per_core.UtilizationPercentagePerCore"
    ] = None,
    scaling_policy_objective: Optional[
        "capo_sagemaker.types.scaling_policy_objective.ScalingPolicyObjective"
    ] = None,
) -> "capo_sagemaker.types.get_scaling_configuration_recommendation_response.GetScalingConfigurationRecommendationResponse":
    """<p>Starts an Amazon SageMaker Inference Recommender autoscaling recommendation job. Returns recommendations for autoscaling policies that you can apply to your SageMaker endpoint.</p>

    Args:
        inference_recommendations_job_name: <p>The name of a previously completed Inference Recommender job.</p>
        recommendation_id: <p>The recommendation ID of a previously completed inference recommendation. This ID should come from one of the recommendations returned by the job specified in the <code>InferenceRecommendationsJobName</code> field.</p> <p>Specify either this field or the <code>EndpointName</code> field.</p>
        endpoint_name: <p>The name of an endpoint benchmarked during a previously completed inference recommendation job. This name should come from one of the recommendations returned by the job specified in the <code>InferenceRecommendationsJobName</code> field.</p> <p>Specify either this field or the <code>RecommendationId</code> field.</p>
        target_cpu_utilization_per_core: <p>The percentage of how much utilization you want an instance to use before autoscaling. The default value is 50%.</p>
        scaling_policy_objective: <p>An object where you specify the anticipated traffic pattern for an endpoint.</p>

    Raises:
        capo_sagemaker.errors.resource_not_found.ResourceNotFound: <p>Resource being access is not found.</p>
        capo_sagemaker.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_sagemaker.types.get_scaling_configuration_recommendation_request.GetScalingConfigurationRecommendationRequest]",
    ) -> OperationResponse[
        "capo_sagemaker.types.get_scaling_configuration_recommendation_response.GetScalingConfigurationRecommendationResponse"
    ]:
        import capo_sagemaker._operations.sage_maker.get_scaling_configuration_recommendation

        output, http_response = (
            capo_sagemaker._operations.sage_maker.get_scaling_configuration_recommendation.get_scaling_configuration_recommendation(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("GetScalingConfigurationRecommendation")
    )
    input_: capo_sagemaker.types.get_scaling_configuration_recommendation_request.GetScalingConfigurationRecommendationRequest = {}
    if inference_recommendations_job_name is not None:
        input_["inference_recommendations_job_name"] = (
            inference_recommendations_job_name
        )
    if recommendation_id is not None:
        input_["recommendation_id"] = recommendation_id
    if endpoint_name is not None:
        input_["endpoint_name"] = endpoint_name
    if target_cpu_utilization_per_core is not None:
        input_["target_cpu_utilization_per_core"] = target_cpu_utilization_per_core
    if scaling_policy_objective is not None:
        input_["scaling_policy_objective"] = scaling_policy_objective

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