Interface CfnEndpointConfigProps
- All Superinterfaces:
software.amazon.jsii.JsiiSerializable
- All Known Implementing Classes:
CfnEndpointConfigProps.Jsii$Proxy
CfnEndpointConfig.
Example:
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import software.amazon.awscdk.services.sagemaker.*;
CfnEndpointConfigProps cfnEndpointConfigProps = CfnEndpointConfigProps.builder()
.productionVariants(List.of(ProductionVariantProperty.builder()
.variantName("variantName")
// the properties below are optional
.acceleratorType("acceleratorType")
.containerStartupHealthCheckTimeoutInSeconds(123)
.enableSsmAccess(false)
.inferenceAmiVersion("inferenceAmiVersion")
.initialInstanceCount(123)
.initialVariantWeight(123)
.instanceType("instanceType")
.managedInstanceScaling(ManagedInstanceScalingProperty.builder()
.maxInstanceCount(123)
.minInstanceCount(123)
.status("status")
.build())
.modelDataDownloadTimeoutInSeconds(123)
.modelName("modelName")
.routingConfig(RoutingConfigProperty.builder()
.routingStrategy("routingStrategy")
.build())
.serverlessConfig(ServerlessConfigProperty.builder()
.maxConcurrency(123)
.memorySizeInMb(123)
// the properties below are optional
.provisionedConcurrency(123)
.build())
.volumeSizeInGb(123)
.build()))
// the properties below are optional
.asyncInferenceConfig(AsyncInferenceConfigProperty.builder()
.outputConfig(AsyncInferenceOutputConfigProperty.builder()
.kmsKeyId("kmsKeyId")
.notificationConfig(AsyncInferenceNotificationConfigProperty.builder()
.errorTopic("errorTopic")
.includeInferenceResponseIn(List.of("includeInferenceResponseIn"))
.successTopic("successTopic")
.build())
.s3FailurePath("s3FailurePath")
.s3OutputPath("s3OutputPath")
.build())
// the properties below are optional
.clientConfig(AsyncInferenceClientConfigProperty.builder()
.maxConcurrentInvocationsPerInstance(123)
.build())
.build())
.dataCaptureConfig(DataCaptureConfigProperty.builder()
.captureOptions(List.of(CaptureOptionProperty.builder()
.captureMode("captureMode")
.build()))
.destinationS3Uri("destinationS3Uri")
.initialSamplingPercentage(123)
// the properties below are optional
.captureContentTypeHeader(CaptureContentTypeHeaderProperty.builder()
.csvContentTypes(List.of("csvContentTypes"))
.jsonContentTypes(List.of("jsonContentTypes"))
.build())
.enableCapture(false)
.kmsKeyId("kmsKeyId")
.build())
.enableNetworkIsolation(false)
.endpointConfigName("endpointConfigName")
.executionRoleArn("executionRoleArn")
.explainerConfig(ExplainerConfigProperty.builder()
.clarifyExplainerConfig(ClarifyExplainerConfigProperty.builder()
.shapConfig(ClarifyShapConfigProperty.builder()
.shapBaselineConfig(ClarifyShapBaselineConfigProperty.builder()
.mimeType("mimeType")
.shapBaseline("shapBaseline")
.shapBaselineUri("shapBaselineUri")
.build())
// the properties below are optional
.numberOfSamples(123)
.seed(123)
.textConfig(ClarifyTextConfigProperty.builder()
.granularity("granularity")
.language("language")
.build())
.useLogit(false)
.build())
// the properties below are optional
.enableExplanations("enableExplanations")
.inferenceConfig(ClarifyInferenceConfigProperty.builder()
.contentTemplate("contentTemplate")
.featureHeaders(List.of("featureHeaders"))
.featuresAttribute("featuresAttribute")
.featureTypes(List.of("featureTypes"))
.labelAttribute("labelAttribute")
.labelHeaders(List.of("labelHeaders"))
.labelIndex(123)
.maxPayloadInMb(123)
.maxRecordCount(123)
.probabilityAttribute("probabilityAttribute")
.probabilityIndex(123)
.build())
.build())
.build())
.kmsKeyId("kmsKeyId")
.shadowProductionVariants(List.of(ProductionVariantProperty.builder()
.variantName("variantName")
// the properties below are optional
.acceleratorType("acceleratorType")
.containerStartupHealthCheckTimeoutInSeconds(123)
.enableSsmAccess(false)
.inferenceAmiVersion("inferenceAmiVersion")
.initialInstanceCount(123)
.initialVariantWeight(123)
.instanceType("instanceType")
.managedInstanceScaling(ManagedInstanceScalingProperty.builder()
.maxInstanceCount(123)
.minInstanceCount(123)
.status("status")
.build())
.modelDataDownloadTimeoutInSeconds(123)
.modelName("modelName")
.routingConfig(RoutingConfigProperty.builder()
.routingStrategy("routingStrategy")
.build())
.serverlessConfig(ServerlessConfigProperty.builder()
.maxConcurrency(123)
.memorySizeInMb(123)
// the properties below are optional
.provisionedConcurrency(123)
.build())
.volumeSizeInGb(123)
.build()))
.tags(List.of(CfnTag.builder()
.key("key")
.value("value")
.build()))
.vpcConfig(VpcConfigProperty.builder()
.securityGroupIds(List.of("securityGroupIds"))
.subnets(List.of("subnets"))
.build())
.build();
- See Also:
-
Nested Class Summary
Nested ClassesModifier and TypeInterfaceDescriptionstatic final classA builder forCfnEndpointConfigPropsstatic final classAn implementation forCfnEndpointConfigProps -
Method Summary
Modifier and TypeMethodDescriptionbuilder()default ObjectSpecifies configuration for how an endpoint performs asynchronous inference.default ObjectSpecifies how to capture endpoint data for model monitor.default Objectdefault StringThe name of the endpoint configuration.default Stringdefault ObjectA parameter to activate explainers.default StringThe Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.A list ofProductionVariantobjects, one for each model that you want to host at this endpoint.default ObjectArray ofProductionVariantobjects.getTags()A list of key-value pairs to apply to this resource.default ObjectMethods inherited from interface software.amazon.jsii.JsiiSerializable
$jsii$toJson
-
Method Details
-
getProductionVariants
A list ofProductionVariantobjects, one for each model that you want to host at this endpoint.- See Also:
-
getAsyncInferenceConfig
Specifies configuration for how an endpoint performs asynchronous inference.- See Also:
-
getDataCaptureConfig
Specifies how to capture endpoint data for model monitor.The data capture configuration applies to all production variants hosted at the endpoint.
- See Also:
-
getEnableNetworkIsolation
- See Also:
-
getEndpointConfigName
The name of the endpoint configuration.- See Also:
-
getExecutionRoleArn
- See Also:
-
getExplainerConfig
A parameter to activate explainers.- See Also:
-
getKmsKeyId
The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.- Key ID:
1234abcd-12ab-34cd-56ef-1234567890ab - Key ARN:
arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab - Alias name:
alias/ExampleAlias - Alias name ARN:
arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias
The KMS key policy must grant permission to the IAM role that you specify in your
CreateEndpoint,UpdateEndpointrequests. For more information, refer to the AWS Key Management Service section Using Key Policies in AWS KMSCertain Nitro-based instances include local storage, dependent on the instance type. Local storage volumes are encrypted using a hardware module on the instance. You can't request a
KmsKeyIdwhen using an instance type with local storage. If any of the models that you specify in theProductionVariantsparameter use nitro-based instances with local storage, do not specify a value for theKmsKeyIdparameter. If you specify a value forKmsKeyIdwhen using any nitro-based instances with local storage, the call toCreateEndpointConfigfails.For a list of instance types that support local instance storage, see Instance Store Volumes .
For more information about local instance storage encryption, see SSD Instance Store Volumes .
- See Also:
- Key ID:
-
getShadowProductionVariants
Array ofProductionVariantobjects.There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on
ProductionVariants. If you use this field, you can only specify one variant forProductionVariantsand one variant forShadowProductionVariants.- See Also:
-
getTags
A list of key-value pairs to apply to this resource.For more information, see Resource Tag and Using Cost Allocation Tags .
- See Also:
-
getVpcConfig
- See Also:
-
builder
- Returns:
- a
CfnEndpointConfigProps.BuilderofCfnEndpointConfigProps
-