From 4c29c21253917027d0020889c23caa3626b7a22c Mon Sep 17 00:00:00 2001
From: awstools The recommended configuration to use for Real-Time Inference. The recommendation ID which uniquely identifies each recommendation. The recommended instance type for Real-Time Inference. The recommended environment variables to set in the model container for Real-Time Inference. A set of recommended deployment configurations for the model. Status of the deployment recommendation. A list of RealTimeInferenceRecommendation items.NOT_APPLICABLE
means that SageMaker
+ * is unable to provide a default recommendation for the model using the information provided.
A set of recommended deployment configurations for the model.
+ */ + DeploymentRecommendation?: DeploymentRecommendation; } /** @@ -10552,89 +10611,6 @@ export interface InferenceRecommendationsJob { ModelPackageVersionArn?: string; } -/** - * @public - *The details for a specific benchmark from an Inference Recommender job.
- */ -export interface RecommendationJobInferenceBenchmark { - /** - *The metrics of recommendations.
- */ - Metrics?: RecommendationMetrics; - - /** - *The endpoint configuration made by Inference Recommender during a recommendation job.
- */ - EndpointConfiguration?: EndpointOutputConfiguration; - - /** - *Defines the model configuration. Includes the specification name and environment parameters.
- */ - ModelConfiguration: ModelConfiguration | undefined; - - /** - *The reason why a benchmark failed.
- */ - FailureReason?: string; - - /** - *The metrics for an existing endpoint compared in an Inference Recommender job.
- */ - EndpointMetrics?: InferenceMetrics; - - /** - *A timestamp that shows when the benchmark completed.
- */ - InvocationEndTime?: Date; - - /** - *A timestamp that shows when the benchmark started.
- */ - InvocationStartTime?: Date; -} - -/** - * @public - * @enum - */ -export const RecommendationStepType = { - BENCHMARK: "BENCHMARK", -} as const; - -/** - * @public - */ -export type RecommendationStepType = (typeof RecommendationStepType)[keyof typeof RecommendationStepType]; - -/** - * @public - *A returned array object for the Steps
response field in the
- * ListInferenceRecommendationsJobSteps API command.
The type of the subtask.
- *
- * BENCHMARK
: Evaluate the performance of your model on different instance types.
The name of the Inference Recommender job.
- */ - JobName: string | undefined; - - /** - *The current status of the benchmark.
- */ - Status: RecommendationJobStatus | string | undefined; - - /** - *The details for a specific benchmark.
- */ - InferenceBenchmark?: RecommendationJobInferenceBenchmark; -} - /** * @internal */ diff --git a/clients/client-sagemaker/src/models/models_3.ts b/clients/client-sagemaker/src/models/models_3.ts index c42374853fdb..3c4ec85b21b2 100644 --- a/clients/client-sagemaker/src/models/models_3.ts +++ b/clients/client-sagemaker/src/models/models_3.ts @@ -89,6 +89,7 @@ import { UiTemplate, } from "./models_1"; import { + DeploymentRecommendation, Device, DeviceDeploymentSummary, DeviceFleetSummary, @@ -103,6 +104,7 @@ import { Endpoint, EndpointConfigSortKey, EndpointConfigSummary, + EndpointOutputConfiguration, EndpointSortKey, EndpointStatus, EndpointSummary, @@ -137,14 +139,15 @@ import { InferenceExperimentStatus, InferenceExperimentStopDesiredState, InferenceExperimentSummary, + InferenceMetrics, InferenceRecommendationsJob, - InferenceRecommendationsJobStep, LabelCounters, LabelingJobOutput, LabelingJobStatus, MetricData, ModelArtifacts, ModelCardExportJobStatus, + ModelConfiguration, ModelPackageGroupStatus, ModelPackageStatusDetails, MonitoringExecutionSummary, @@ -156,7 +159,7 @@ import { ProcessingJobStatus, ProjectStatus, RecommendationJobStatus, - RecommendationStepType, + RecommendationMetrics, ScheduleStatus, SecondaryStatus, SecondaryStatusTransition, @@ -175,6 +178,89 @@ import { Workteam, } from "./models_2"; +/** + * @public + *The details for a specific benchmark from an Inference Recommender job.
+ */ +export interface RecommendationJobInferenceBenchmark { + /** + *The metrics of recommendations.
+ */ + Metrics?: RecommendationMetrics; + + /** + *The endpoint configuration made by Inference Recommender during a recommendation job.
+ */ + EndpointConfiguration?: EndpointOutputConfiguration; + + /** + *Defines the model configuration. Includes the specification name and environment parameters.
+ */ + ModelConfiguration: ModelConfiguration | undefined; + + /** + *The reason why a benchmark failed.
+ */ + FailureReason?: string; + + /** + *The metrics for an existing endpoint compared in an Inference Recommender job.
+ */ + EndpointMetrics?: InferenceMetrics; + + /** + *A timestamp that shows when the benchmark completed.
+ */ + InvocationEndTime?: Date; + + /** + *A timestamp that shows when the benchmark started.
+ */ + InvocationStartTime?: Date; +} + +/** + * @public + * @enum + */ +export const RecommendationStepType = { + BENCHMARK: "BENCHMARK", +} as const; + +/** + * @public + */ +export type RecommendationStepType = (typeof RecommendationStepType)[keyof typeof RecommendationStepType]; + +/** + * @public + *A returned array object for the Steps
response field in the
+ * ListInferenceRecommendationsJobSteps API command.
The type of the subtask.
+ *
+ * BENCHMARK
: Evaluate the performance of your model on different instance types.
The name of the Inference Recommender job.
+ */ + JobName: string | undefined; + + /** + *The current status of the benchmark.
+ */ + Status: RecommendationJobStatus | string | undefined; + + /** + *The details for a specific benchmark.
+ */ + InferenceBenchmark?: RecommendationJobInferenceBenchmark; +} + /** * @public *Provides counts for human-labeled tasks in the labeling job.
@@ -7085,6 +7171,11 @@ export interface Model { * resources in the Amazon Web Services General Reference Guide. */ Tags?: Tag[]; + + /** + *A set of recommended deployment configurations for the model.
+ */ + DeploymentRecommendation?: DeploymentRecommendation; } /** @@ -9669,36 +9760,6 @@ export interface StopPipelineExecutionResponse { PipelineExecutionArn?: string; } -/** - * @public - */ -export interface StopProcessingJobRequest { - /** - *The name of the processing job to stop.
- */ - ProcessingJobName: string | undefined; -} - -/** - * @public - */ -export interface StopTrainingJobRequest { - /** - *The name of the training job to stop.
- */ - TrainingJobName: string | undefined; -} - -/** - * @public - */ -export interface StopTransformJobRequest { - /** - *The name of the batch transform job to stop.
- */ - TransformJobName: string | undefined; -} - /** * @internal */ diff --git a/clients/client-sagemaker/src/models/models_4.ts b/clients/client-sagemaker/src/models/models_4.ts index 479e415be8f9..4c326c8c6db1 100644 --- a/clients/client-sagemaker/src/models/models_4.ts +++ b/clients/client-sagemaker/src/models/models_4.ts @@ -58,6 +58,36 @@ import { } from "./models_2"; import { NestedFilters, ProfilerConfigForUpdate, ResourceConfigForUpdate, SearchSortOrder } from "./models_3"; +/** + * @public + */ +export interface StopProcessingJobRequest { + /** + *The name of the processing job to stop.
+ */ + ProcessingJobName: string | undefined; +} + +/** + * @public + */ +export interface StopTrainingJobRequest { + /** + *The name of the training job to stop.
+ */ + TrainingJobName: string | undefined; +} + +/** + * @public + */ +export interface StopTransformJobRequest { + /** + *The name of the batch transform job to stop.
+ */ + TransformJobName: string | undefined; +} + /** * @public */ diff --git a/clients/client-sagemaker/src/protocols/Aws_json1_1.ts b/clients/client-sagemaker/src/protocols/Aws_json1_1.ts index 60ce30711dec..14d8f2d1e3d2 100644 --- a/clients/client-sagemaker/src/protocols/Aws_json1_1.ts +++ b/clients/client-sagemaker/src/protocols/Aws_json1_1.ts @@ -1360,7 +1360,6 @@ import { InferenceExperimentSummary, InferenceRecommendation, InferenceRecommendationsJob, - InferenceRecommendationsJobStep, MetricData, MonitoringExecutionSummary, MonitoringSchedule, @@ -1371,7 +1370,6 @@ import { ProductionVariantSummary, ProfilerRuleEvaluationStatus, PropertyNameQuery, - RecommendationJobInferenceBenchmark, RecommendationMetrics, RStudioServerProDomainSettingsForUpdate, SecondaryStatusTransition, @@ -1381,6 +1379,7 @@ import { Workteam, } from "../models/models_2"; import { + InferenceRecommendationsJobStep, LabelingJobForWorkteamSummary, LabelingJobSummary, LineageGroupSummary, @@ -1560,6 +1559,7 @@ import { PutModelPackageGroupPolicyInput, QueryFilters, QueryLineageRequest, + RecommendationJobInferenceBenchmark, RegisterDevicesRequest, RenderableTask, RenderUiTemplateRequest, @@ -1586,9 +1586,6 @@ import { StopMonitoringScheduleRequest, StopNotebookInstanceInput, StopPipelineExecutionRequest, - StopProcessingJobRequest, - StopTrainingJobRequest, - StopTransformJobRequest, StudioLifecycleConfigDetails, TrainingJob, TrainingJobSummary, @@ -1606,6 +1603,9 @@ import { SearchExpression, SearchRequest, ServiceCatalogProvisioningUpdateDetails, + StopProcessingJobRequest, + StopTrainingJobRequest, + StopTransformJobRequest, UpdateActionRequest, UpdateAppImageConfigRequest, UpdateArtifactRequest, @@ -22807,6 +22807,8 @@ const de_DeployedImages = (output: any, context: __SerdeContext): DeployedImage[ // de_DeploymentConfig omitted. +// de_DeploymentRecommendation omitted. + /** * deserializeAws_json1_1DeploymentStageStatusSummaries */ @@ -23594,6 +23596,7 @@ const de_DescribeModelOutput = (output: any, context: __SerdeContext): DescribeM return take(output, { Containers: _json, CreationTime: (_: any) => __expectNonNull(__parseEpochTimestamp(__expectNumber(_))), + DeploymentRecommendation: _json, EnableNetworkIsolation: __expectBoolean, ExecutionRoleArn: __expectString, InferenceExecutionConfig: _json, @@ -26034,6 +26037,7 @@ const de_Model = (output: any, context: __SerdeContext): Model => { return take(output, { Containers: _json, CreationTime: (_: any) => __expectNonNull(__parseEpochTimestamp(__expectNumber(_))), + DeploymentRecommendation: _json, EnableNetworkIsolation: __expectBoolean, ExecutionRoleArn: __expectString, InferenceExecutionConfig: _json, @@ -27320,6 +27324,10 @@ const de_ProjectSummaryList = (output: any, context: __SerdeContext): ProjectSum // de_RealtimeInferenceInstanceTypes omitted. +// de_RealTimeInferenceRecommendation omitted. + +// de_RealTimeInferenceRecommendations omitted. + // de_RecommendationJobContainerConfig omitted. /** diff --git a/codegen/sdk-codegen/aws-models/sagemaker.json b/codegen/sdk-codegen/aws-models/sagemaker.json index 6bfd40f61d07..44912d46f882 100644 --- a/codegen/sdk-codegen/aws-models/sagemaker.json +++ b/codegen/sdk-codegen/aws-models/sagemaker.json @@ -13317,6 +13317,27 @@ "smithy.api#documentation": "The deployment configuration for an endpoint, which contains the desired deployment\n strategy and rollback configurations.
" } }, + "com.amazonaws.sagemaker#DeploymentRecommendation": { + "type": "structure", + "members": { + "RecommendationStatus": { + "target": "com.amazonaws.sagemaker#RecommendationStatus", + "traits": { + "smithy.api#documentation": "Status of the deployment recommendation. NOT_APPLICABLE
means that SageMaker\n is unable to provide a default recommendation for the model using the information provided.
A list of RealTimeInferenceRecommendation items.
" + } + } + }, + "traits": { + "smithy.api#documentation": "A set of recommended deployment configurations for the model.
" + } + }, "com.amazonaws.sagemaker#DeploymentStage": { "type": "structure", "members": { @@ -18030,6 +18051,12 @@ "smithy.api#default": false, "smithy.api#documentation": "If True
, no inbound or outbound network calls can be made to or from the\n model container.
A set of recommended deployment configurations for the model.
" + } } }, "traits": { @@ -36808,6 +36835,12 @@ "traits": { "smithy.api#documentation": "A list of key-value pairs associated with the model. For more information, see\n Tagging Amazon Web Services\n resources in the Amazon Web Services General Reference Guide.
" } + }, + "DeploymentRecommendation": { + "target": "com.amazonaws.sagemaker#DeploymentRecommendation", + "traits": { + "smithy.api#documentation": "A set of recommended deployment configurations for the model.
" + } } }, "traits": { @@ -45874,6 +45907,46 @@ "smithy.api#documentation": "The infrastructure configuration for deploying the model to a real-time inference endpoint.
" } }, + "com.amazonaws.sagemaker#RealTimeInferenceRecommendation": { + "type": "structure", + "members": { + "RecommendationId": { + "target": "com.amazonaws.sagemaker#String", + "traits": { + "smithy.api#documentation": "The recommendation ID which uniquely identifies each recommendation.
", + "smithy.api#required": {} + } + }, + "InstanceType": { + "target": "com.amazonaws.sagemaker#ProductionVariantInstanceType", + "traits": { + "smithy.api#documentation": "The recommended instance type for Real-Time Inference.
", + "smithy.api#required": {} + } + }, + "Environment": { + "target": "com.amazonaws.sagemaker#EnvironmentMap", + "traits": { + "smithy.api#documentation": "The recommended environment variables to set in the model container for Real-Time Inference.
" + } + } + }, + "traits": { + "smithy.api#documentation": "The recommended configuration to use for Real-Time Inference.
" + } + }, + "com.amazonaws.sagemaker#RealTimeInferenceRecommendations": { + "type": "list", + "member": { + "target": "com.amazonaws.sagemaker#RealTimeInferenceRecommendation" + }, + "traits": { + "smithy.api#length": { + "min": 0, + "max": 3 + } + } + }, "com.amazonaws.sagemaker#RealtimeInferenceInstanceTypes": { "type": "list", "member": { @@ -46380,6 +46453,35 @@ "smithy.api#documentation": "The metrics of recommendations.
" } }, + "com.amazonaws.sagemaker#RecommendationStatus": { + "type": "enum", + "members": { + "IN_PROGRESS": { + "target": "smithy.api#Unit", + "traits": { + "smithy.api#enumValue": "IN_PROGRESS" + } + }, + "COMPLETED": { + "target": "smithy.api#Unit", + "traits": { + "smithy.api#enumValue": "COMPLETED" + } + }, + "FAILED": { + "target": "smithy.api#Unit", + "traits": { + "smithy.api#enumValue": "FAILED" + } + }, + "NOT_APPLICABLE": { + "target": "smithy.api#Unit", + "traits": { + "smithy.api#enumValue": "NOT_APPLICABLE" + } + } + } + }, "com.amazonaws.sagemaker#RecommendationStepType": { "type": "enum", "members": {