update_inference_experiment ¶

def update_inference_experiment(
    self,
    *,
    config_overrides: Optional[SageMakerClientConfig] = None,
    name: Optional[
        "capo_sagemaker.types.inference_experiment_name.InferenceExperimentName"
    ] = None,
    schedule: Optional[
        "capo_sagemaker.types.inference_experiment_schedule.InferenceExperimentSchedule"
    ] = None,
    description: Optional[
        "capo_sagemaker.types.inference_experiment_description.InferenceExperimentDescription"
    ] = None,
    model_variants: Optional[
        "capo_sagemaker.types.model_variant_config_list.ModelVariantConfigList"
    ] = None,
    data_storage_config: Optional[
        "capo_sagemaker.types.inference_experiment_data_storage_config.InferenceExperimentDataStorageConfig"
    ] = None,
    shadow_mode_config: Optional[
        "capo_sagemaker.types.shadow_mode_config.ShadowModeConfig"
    ] = None,
) -> "capo_sagemaker.types.update_inference_experiment_response.UpdateInferenceExperimentResponse":
    """<p> Updates an inference experiment that you created. The status of the inference experiment has to be either <code>Created</code>, <code>Running</code>. For more information on the status of an inference experiment, see <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeInferenceExperiment.html">DescribeInferenceExperiment</a>. </p>

    Args:
        name: <p>The name of the inference experiment to be updated.</p>
        schedule: <p> The duration for which the inference experiment will run. If the status of the inference experiment is <code>Created</code>, then you can update both the start and end dates. If the status of the inference experiment is <code>Running</code>, then you can update only the end date. </p>
        description: <p>The description of the inference experiment.</p>
        model_variants: <p> An array of <code>ModelVariantConfig</code> objects. There is one for each variant, whose infrastructure configuration you want to update. </p>
        data_storage_config: <p>The Amazon S3 location and configuration for storing inference request and response data.</p>
        shadow_mode_config: <p> The configuration of <code>ShadowMode</code> inference experiment type. Use this field to specify a production variant which takes all the inference requests, and a shadow variant to which Amazon SageMaker replicates a percentage of the inference requests. For the shadow variant also specify the percentage of requests that Amazon SageMaker replicates. </p>

    Raises:
        capo_sagemaker.errors.conflict_exception.ConflictException: <p>There was a conflict when you attempted to modify a SageMaker entity such as an <code>Experiment</code> or <code>Artifact</code>.</p>
        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.update_inference_experiment_request.UpdateInferenceExperimentRequest]",
    ) -> OperationResponse[
        "capo_sagemaker.types.update_inference_experiment_response.UpdateInferenceExperimentResponse"
    ]:
        import capo_sagemaker._operations.sage_maker.update_inference_experiment

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

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("UpdateInferenceExperiment")
    )
    input_: capo_sagemaker.types.update_inference_experiment_request.UpdateInferenceExperimentRequest = {}
    if name is not None:
        input_["name"] = name
    if schedule is not None:
        input_["schedule"] = schedule
    if description is not None:
        input_["description"] = description
    if model_variants is not None:
        input_["model_variants"] = model_variants
    if data_storage_config is not None:
        input_["data_storage_config"] = data_storage_config
    if shadow_mode_config is not None:
        input_["shadow_mode_config"] = shadow_mode_config

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