CfnInferenceComponent L1 construct
Creates an inference component, which is a SageMaker AI hosting object that you can use to deploy a model to an endpoint.
In the inference component settings, you specify the model, the endpoint, and how the model utilizes the resources that the endpoint hosts. You can optimize resource utilization by tailoring how the required CPU cores, accelerators, and memory are allocated. You can deploy multiple inference components to an endpoint, where each inference component contains one model and the resource utilization needs for that individual model. After you deploy an inference component, you can directly invoke the associated model when you use the InvokeEndpoint API action.
Example
ts
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from 'aws-cdk-lib';
const cfnInferenceComponent = new sagemaker.CfnInferenceComponent(this, 'MyCfnInferenceComponent', {
endpointName: 'endpointName',
// the properties below are optional
deploymentConfig: {
autoRollbackConfiguration: {
alarms: [{
alarmName: 'alarmName',
}],
},
rollingUpdatePolicy: {
maximumBatchSize: {
type: 'type',
value: 123,
},
maximumExecutionTimeoutInSeconds: 123,
rollbackMaximumBatchSize: {
type: 'type',
value: 123,
},
waitIntervalInSeconds: 123,
},
},
endpointArn: 'endpointArn',
inferenceComponentName: 'inferenceComponentName',
runtimeConfig: {
copyCount: 123,
currentCopyCount: 123,
desiredCopyCount: 123,
placementStatus: [{
currentCopyCount: 123,
instanceType: 'instanceType',
}],
},
specification: {
baseInferenceComponentName: 'baseInferenceComponentName',
computeResourceRequirements: {
maxMemoryRequiredInMb: 123,
minMemoryRequiredInMb: 123,
numberOfAcceleratorDevicesRequired: 123,
numberOfCpuCoresRequired: 123,
},
container: {
artifactUrl: 'artifactUrl',
containerMetricsConfig: {
metricsEndpoints: [{
metricsEndpointPath: 'metricsEndpointPath',
// the properties below are optional
metricPublishFrequencyInSeconds: 123,
}],
},
deployedImage: {
resolutionTime: 'resolutionTime',
resolvedImage: 'resolvedImage',
specifiedImage: 'specifiedImage',
},
environment: {
environmentKey: 'environment',
},
image: 'image',
},
currentDataCacheConfig: {
enableCaching: false,
},
dataCacheConfig: {
enableCaching: false,
},
modelName: 'modelName',
schedulingConfig: {
availabilityZoneBalance: {
enforcementMode: 'enforcementMode',
// the properties below are optional
maxImbalance: 123,
},
placementStrategy: 'placementStrategy',
},
startupParameters: {
containerStartupHealthCheckTimeoutInSeconds: 123,
modelDataDownloadTimeoutInSeconds: 123,
},
},
specifications: [{
instanceType: 'instanceType',
// the properties below are optional
computeResourceRequirements: {
maxMemoryRequiredInMb: 123,
minMemoryRequiredInMb: 123,
numberOfAcceleratorDevicesRequired: 123,
numberOfCpuCoresRequired: 123,
},
container: {
artifactUrl: 'artifactUrl',
containerMetricsConfig: {
metricsEndpoints: [{
metricsEndpointPath: 'metricsEndpointPath',
// the properties below are optional
metricPublishFrequencyInSeconds: 123,
}],
},
environment: {
environmentKey: 'environment',
},
image: 'image',
},
currentDataCacheConfig: {
enableCaching: false,
},
dataCacheConfig: {
enableCaching: false,
},
modelName: 'modelName',
schedulingConfig: {
availabilityZoneBalance: {
enforcementMode: 'enforcementMode',
// the properties below are optional
maxImbalance: 123,
},
placementStrategy: 'placementStrategy',
},
startupParameters: {
containerStartupHealthCheckTimeoutInSeconds: 123,
modelDataDownloadTimeoutInSeconds: 123,
},
}],
tags: [{
key: 'key',
value: 'value',
}],
variantName: 'variantName',
});
python
from aws_cdk import CfnTag
# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk import aws_sagemaker as sagemaker
cfn_inference_component = sagemaker.CfnInferenceComponent(self, "MyCfnInferenceComponent",
endpoint_name="endpointName",
# the properties below are optional
deployment_config=sagemaker.CfnInferenceComponent.InferenceComponentDeploymentConfigProperty(
auto_rollback_configuration=sagemaker.CfnInferenceComponent.AutoRollbackConfigurationProperty(
alarms=[sagemaker.CfnInferenceComponent.AlarmProperty(
alarm_name="alarmName"
)]
),
rolling_update_policy=sagemaker.CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty(
maximum_batch_size=sagemaker.CfnInferenceComponent.InferenceComponentCapacitySizeProperty(
type="type",
value=123
),
maximum_execution_timeout_in_seconds=123,
rollback_maximum_batch_size=sagemaker.CfnInferenceComponent.InferenceComponentCapacitySizeProperty(
type="type",
value=123
),
wait_interval_in_seconds=123
)
),
endpoint_arn="endpointArn",
inference_component_name="inferenceComponentName",
runtime_config=sagemaker.CfnInferenceComponent.InferenceComponentRuntimeConfigProperty(
copy_count=123,
current_copy_count=123,
desired_copy_count=123,
placement_status=[sagemaker.CfnInferenceComponent.InferenceComponentPlacementStatusProperty(
current_copy_count=123,
instance_type="instanceType"
)]
),
specification=sagemaker.CfnInferenceComponent.InferenceComponentSpecificationProperty(
base_inference_component_name="baseInferenceComponentName",
compute_resource_requirements=sagemaker.CfnInferenceComponent.InferenceComponentComputeResourceRequirementsProperty(
max_memory_required_in_mb=123,
min_memory_required_in_mb=123,
number_of_accelerator_devices_required=123,
number_of_cpu_cores_required=123
),
container=sagemaker.CfnInferenceComponent.InferenceComponentContainerSpecificationProperty(
artifact_url="artifactUrl",
container_metrics_config=sagemaker.CfnInferenceComponent.ContainerMetricsConfigProperty(
metrics_endpoints=[sagemaker.CfnInferenceComponent.MetricsEndpointProperty(
metrics_endpoint_path="metricsEndpointPath",
# the properties below are optional
metric_publish_frequency_in_seconds=123
)]
),
deployed_image=sagemaker.CfnInferenceComponent.DeployedImageProperty(
resolution_time="resolutionTime",
resolved_image="resolvedImage",
specified_image="specifiedImage"
),
environment={
"environment_key": "environment"
},
image="image"
),
current_data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
model_name="modelName",
scheduling_config=sagemaker.CfnInferenceComponent.InferenceComponentSchedulingConfigProperty(
availability_zone_balance=sagemaker.CfnInferenceComponent.InferenceComponentAvailabilityZoneBalanceProperty(
enforcement_mode="enforcementMode",
# the properties below are optional
max_imbalance=123
),
placement_strategy="placementStrategy"
),
startup_parameters=sagemaker.CfnInferenceComponent.InferenceComponentStartupParametersProperty(
container_startup_health_check_timeout_in_seconds=123,
model_data_download_timeout_in_seconds=123
)
),
specifications=[sagemaker.CfnInferenceComponent.InferenceComponentSpecificationForInstanceTypeProperty(
instance_type="instanceType",
# the properties below are optional
compute_resource_requirements=sagemaker.CfnInferenceComponent.InferenceComponentComputeResourceRequirementsProperty(
max_memory_required_in_mb=123,
min_memory_required_in_mb=123,
number_of_accelerator_devices_required=123,
number_of_cpu_cores_required=123
),
container=sagemaker.CfnInferenceComponent.InferenceComponentContainerSpecificationForInstanceTypeProperty(
artifact_url="artifactUrl",
container_metrics_config=sagemaker.CfnInferenceComponent.ContainerMetricsConfigProperty(
metrics_endpoints=[sagemaker.CfnInferenceComponent.MetricsEndpointProperty(
metrics_endpoint_path="metricsEndpointPath",
# the properties below are optional
metric_publish_frequency_in_seconds=123
)]
),
environment={
"environment_key": "environment"
},
image="image"
),
current_data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
model_name="modelName",
scheduling_config=sagemaker.CfnInferenceComponent.InferenceComponentSchedulingConfigProperty(
availability_zone_balance=sagemaker.CfnInferenceComponent.InferenceComponentAvailabilityZoneBalanceProperty(
enforcement_mode="enforcementMode",
# the properties below are optional
max_imbalance=123
),
placement_strategy="placementStrategy"
),
startup_parameters=sagemaker.CfnInferenceComponent.InferenceComponentStartupParametersProperty(
container_startup_health_check_timeout_in_seconds=123,
model_data_download_timeout_in_seconds=123
)
)],
tags=[CfnTag(
key="key",
value="value"
)],
variant_name="variantName"
)
java
// 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.*;
CfnInferenceComponent cfnInferenceComponent = CfnInferenceComponent.Builder.create(this, "MyCfnInferenceComponent")
.endpointName("endpointName")
// the properties below are optional
.deploymentConfig(InferenceComponentDeploymentConfigProperty.builder()
.autoRollbackConfiguration(AutoRollbackConfigurationProperty.builder()
.alarms(List.of(AlarmProperty.builder()
.alarmName("alarmName")
.build()))
.build())
.rollingUpdatePolicy(InferenceComponentRollingUpdatePolicyProperty.builder()
.maximumBatchSize(InferenceComponentCapacitySizeProperty.builder()
.type("type")
.value(123)
.build())
.maximumExecutionTimeoutInSeconds(123)
.rollbackMaximumBatchSize(InferenceComponentCapacitySizeProperty.builder()
.type("type")
.value(123)
.build())
.waitIntervalInSeconds(123)
.build())
.build())
.endpointArn("endpointArn")
.inferenceComponentName("inferenceComponentName")
.runtimeConfig(InferenceComponentRuntimeConfigProperty.builder()
.copyCount(123)
.currentCopyCount(123)
.desiredCopyCount(123)
.placementStatus(List.of(InferenceComponentPlacementStatusProperty.builder()
.currentCopyCount(123)
.instanceType("instanceType")
.build()))
.build())
.specification(InferenceComponentSpecificationProperty.builder()
.baseInferenceComponentName("baseInferenceComponentName")
.computeResourceRequirements(InferenceComponentComputeResourceRequirementsProperty.builder()
.maxMemoryRequiredInMb(123)
.minMemoryRequiredInMb(123)
.numberOfAcceleratorDevicesRequired(123)
.numberOfCpuCoresRequired(123)
.build())
.container(InferenceComponentContainerSpecificationProperty.builder()
.artifactUrl("artifactUrl")
.containerMetricsConfig(ContainerMetricsConfigProperty.builder()
.metricsEndpoints(List.of(MetricsEndpointProperty.builder()
.metricsEndpointPath("metricsEndpointPath")
// the properties below are optional
.metricPublishFrequencyInSeconds(123)
.build()))
.build())
.deployedImage(DeployedImageProperty.builder()
.resolutionTime("resolutionTime")
.resolvedImage("resolvedImage")
.specifiedImage("specifiedImage")
.build())
.environment(Map.of(
"environmentKey", "environment"))
.image("image")
.build())
.currentDataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.dataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.modelName("modelName")
.schedulingConfig(InferenceComponentSchedulingConfigProperty.builder()
.availabilityZoneBalance(InferenceComponentAvailabilityZoneBalanceProperty.builder()
.enforcementMode("enforcementMode")
// the properties below are optional
.maxImbalance(123)
.build())
.placementStrategy("placementStrategy")
.build())
.startupParameters(InferenceComponentStartupParametersProperty.builder()
.containerStartupHealthCheckTimeoutInSeconds(123)
.modelDataDownloadTimeoutInSeconds(123)
.build())
.build())
.specifications(List.of(InferenceComponentSpecificationForInstanceTypeProperty.builder()
.instanceType("instanceType")
// the properties below are optional
.computeResourceRequirements(InferenceComponentComputeResourceRequirementsProperty.builder()
.maxMemoryRequiredInMb(123)
.minMemoryRequiredInMb(123)
.numberOfAcceleratorDevicesRequired(123)
.numberOfCpuCoresRequired(123)
.build())
.container(InferenceComponentContainerSpecificationForInstanceTypeProperty.builder()
.artifactUrl("artifactUrl")
.containerMetricsConfig(ContainerMetricsConfigProperty.builder()
.metricsEndpoints(List.of(MetricsEndpointProperty.builder()
.metricsEndpointPath("metricsEndpointPath")
// the properties below are optional
.metricPublishFrequencyInSeconds(123)
.build()))
.build())
.environment(Map.of(
"environmentKey", "environment"))
.image("image")
.build())
.currentDataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.dataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.modelName("modelName")
.schedulingConfig(InferenceComponentSchedulingConfigProperty.builder()
.availabilityZoneBalance(InferenceComponentAvailabilityZoneBalanceProperty.builder()
.enforcementMode("enforcementMode")
// the properties below are optional
.maxImbalance(123)
.build())
.placementStrategy("placementStrategy")
.build())
.startupParameters(InferenceComponentStartupParametersProperty.builder()
.containerStartupHealthCheckTimeoutInSeconds(123)
.modelDataDownloadTimeoutInSeconds(123)
.build())
.build()))
.tags(List.of(CfnTag.builder()
.key("key")
.value("value")
.build()))
.variantName("variantName")
.build();
csharp
// Install: dotnet add package Amazon.CDK.Lib
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
using Amazon.CDK.AWS.Sagemaker;
var cfnInferenceComponent = new CfnInferenceComponent(this, "MyCfnInferenceComponent", new CfnInferenceComponentProps {
EndpointName = "endpointName",
// the properties below are optional
DeploymentConfig = new InferenceComponentDeploymentConfigProperty {
AutoRollbackConfiguration = new AutoRollbackConfigurationProperty {
Alarms = new [] { new AlarmProperty {
AlarmName = "alarmName"
} }
},
RollingUpdatePolicy = new InferenceComponentRollingUpdatePolicyProperty {
MaximumBatchSize = new InferenceComponentCapacitySizeProperty {
Type = "type",
Value = 123
},
MaximumExecutionTimeoutInSeconds = 123,
RollbackMaximumBatchSize = new InferenceComponentCapacitySizeProperty {
Type = "type",
Value = 123
},
WaitIntervalInSeconds = 123
}
},
EndpointArn = "endpointArn",
InferenceComponentName = "inferenceComponentName",
RuntimeConfig = new InferenceComponentRuntimeConfigProperty {
CopyCount = 123,
CurrentCopyCount = 123,
DesiredCopyCount = 123,
PlacementStatus = new [] { new InferenceComponentPlacementStatusProperty {
CurrentCopyCount = 123,
InstanceType = "instanceType"
} }
},
Specification = new InferenceComponentSpecificationProperty {
BaseInferenceComponentName = "baseInferenceComponentName",
ComputeResourceRequirements = new InferenceComponentComputeResourceRequirementsProperty {
MaxMemoryRequiredInMb = 123,
MinMemoryRequiredInMb = 123,
NumberOfAcceleratorDevicesRequired = 123,
NumberOfCpuCoresRequired = 123
},
Container = new InferenceComponentContainerSpecificationProperty {
ArtifactUrl = "artifactUrl",
ContainerMetricsConfig = new ContainerMetricsConfigProperty {
MetricsEndpoints = new [] { new MetricsEndpointProperty {
MetricsEndpointPath = "metricsEndpointPath",
// the properties below are optional
MetricPublishFrequencyInSeconds = 123
} }
},
DeployedImage = new DeployedImageProperty {
ResolutionTime = "resolutionTime",
ResolvedImage = "resolvedImage",
SpecifiedImage = "specifiedImage"
},
Environment = new Dictionary<string, string> {
{ "environmentKey", "environment" }
},
Image = "image"
},
CurrentDataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
DataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
ModelName = "modelName",
SchedulingConfig = new InferenceComponentSchedulingConfigProperty {
AvailabilityZoneBalance = new InferenceComponentAvailabilityZoneBalanceProperty {
EnforcementMode = "enforcementMode",
// the properties below are optional
MaxImbalance = 123
},
PlacementStrategy = "placementStrategy"
},
StartupParameters = new InferenceComponentStartupParametersProperty {
ContainerStartupHealthCheckTimeoutInSeconds = 123,
ModelDataDownloadTimeoutInSeconds = 123
}
},
Specifications = new [] { new InferenceComponentSpecificationForInstanceTypeProperty {
InstanceType = "instanceType",
// the properties below are optional
ComputeResourceRequirements = new InferenceComponentComputeResourceRequirementsProperty {
MaxMemoryRequiredInMb = 123,
MinMemoryRequiredInMb = 123,
NumberOfAcceleratorDevicesRequired = 123,
NumberOfCpuCoresRequired = 123
},
Container = new InferenceComponentContainerSpecificationForInstanceTypeProperty {
ArtifactUrl = "artifactUrl",
ContainerMetricsConfig = new ContainerMetricsConfigProperty {
MetricsEndpoints = new [] { new MetricsEndpointProperty {
MetricsEndpointPath = "metricsEndpointPath",
// the properties below are optional
MetricPublishFrequencyInSeconds = 123
} }
},
Environment = new Dictionary<string, string> {
{ "environmentKey", "environment" }
},
Image = "image"
},
CurrentDataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
DataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
ModelName = "modelName",
SchedulingConfig = new InferenceComponentSchedulingConfigProperty {
AvailabilityZoneBalance = new InferenceComponentAvailabilityZoneBalanceProperty {
EnforcementMode = "enforcementMode",
// the properties below are optional
MaxImbalance = 123
},
PlacementStrategy = "placementStrategy"
},
StartupParameters = new InferenceComponentStartupParametersProperty {
ContainerStartupHealthCheckTimeoutInSeconds = 123,
ModelDataDownloadTimeoutInSeconds = 123
}
} },
Tags = new [] { new CfnTag {
Key = "key",
Value = "value"
} },
VariantName = "variantName"
});
go
// Install: go get github.com/aws/aws-cdk-go/awscdk/v2
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import "github.com/aws/aws-cdk-go/awscdk"
cfnInferenceComponent := awscdk.Aws_sagemaker.NewCfnInferenceComponent(this, jsii.String("MyCfnInferenceComponent"), &CfnInferenceComponentProps{
EndpointName: jsii.String("endpointName"),
// the properties below are optional
DeploymentConfig: &InferenceComponentDeploymentConfigProperty{
AutoRollbackConfiguration: &AutoRollbackConfigurationProperty{
Alarms: []interface{}{
&AlarmProperty{
AlarmName: jsii.String("alarmName"),
},
},
},
RollingUpdatePolicy: &InferenceComponentRollingUpdatePolicyProperty{
MaximumBatchSize: &InferenceComponentCapacitySizeProperty{
Type: jsii.String("type"),
Value: jsii.Number(123),
},
MaximumExecutionTimeoutInSeconds: jsii.Number(123),
RollbackMaximumBatchSize: &InferenceComponentCapacitySizeProperty{
Type: jsii.String("type"),
Value: jsii.Number(123),
},
WaitIntervalInSeconds: jsii.Number(123),
},
},
EndpointArn: jsii.String("endpointArn"),
InferenceComponentName: jsii.String("inferenceComponentName"),
RuntimeConfig: &InferenceComponentRuntimeConfigProperty{
CopyCount: jsii.Number(123),
CurrentCopyCount: jsii.Number(123),
DesiredCopyCount: jsii.Number(123),
PlacementStatus: []interface{}{
&InferenceComponentPlacementStatusProperty{
CurrentCopyCount: jsii.Number(123),
InstanceType: jsii.String("instanceType"),
},
},
},
Specification: &InferenceComponentSpecificationProperty{
BaseInferenceComponentName: jsii.String("baseInferenceComponentName"),
ComputeResourceRequirements: &InferenceComponentComputeResourceRequirementsProperty{
MaxMemoryRequiredInMb: jsii.Number(123),
MinMemoryRequiredInMb: jsii.Number(123),
NumberOfAcceleratorDevicesRequired: jsii.Number(123),
NumberOfCpuCoresRequired: jsii.Number(123),
},
Container: &InferenceComponentContainerSpecificationProperty{
ArtifactUrl: jsii.String("artifactUrl"),
ContainerMetricsConfig: &ContainerMetricsConfigProperty{
MetricsEndpoints: []interface{}{
&MetricsEndpointProperty{
MetricsEndpointPath: jsii.String("metricsEndpointPath"),
// the properties below are optional
MetricPublishFrequencyInSeconds: jsii.Number(123),
},
},
},
DeployedImage: &DeployedImageProperty{
ResolutionTime: jsii.String("resolutionTime"),
ResolvedImage: jsii.String("resolvedImage"),
SpecifiedImage: jsii.String("specifiedImage"),
},
Environment: map[string]*string{
"environmentKey": jsii.String("environment"),
},
Image: jsii.String("image"),
},
CurrentDataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
DataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
ModelName: jsii.String("modelName"),
SchedulingConfig: &InferenceComponentSchedulingConfigProperty{
AvailabilityZoneBalance: &InferenceComponentAvailabilityZoneBalanceProperty{
EnforcementMode: jsii.String("enforcementMode"),
// the properties below are optional
MaxImbalance: jsii.Number(123),
},
PlacementStrategy: jsii.String("placementStrategy"),
},
StartupParameters: &InferenceComponentStartupParametersProperty{
ContainerStartupHealthCheckTimeoutInSeconds: jsii.Number(123),
ModelDataDownloadTimeoutInSeconds: jsii.Number(123),
},
},
Specifications: []interface{}{
&InferenceComponentSpecificationForInstanceTypeProperty{
InstanceType: jsii.String("instanceType"),
// the properties below are optional
ComputeResourceRequirements: &InferenceComponentComputeResourceRequirementsProperty{
MaxMemoryRequiredInMb: jsii.Number(123),
MinMemoryRequiredInMb: jsii.Number(123),
NumberOfAcceleratorDevicesRequired: jsii.Number(123),
NumberOfCpuCoresRequired: jsii.Number(123),
},
Container: &InferenceComponentContainerSpecificationForInstanceTypeProperty{
ArtifactUrl: jsii.String("artifactUrl"),
ContainerMetricsConfig: &ContainerMetricsConfigProperty{
MetricsEndpoints: []interface{}{
&MetricsEndpointProperty{
MetricsEndpointPath: jsii.String("metricsEndpointPath"),
// the properties below are optional
MetricPublishFrequencyInSeconds: jsii.Number(123),
},
},
},
Environment: map[string]*string{
"environmentKey": jsii.String("environment"),
},
Image: jsii.String("image"),
},
CurrentDataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
DataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
ModelName: jsii.String("modelName"),
SchedulingConfig: &InferenceComponentSchedulingConfigProperty{
AvailabilityZoneBalance: &InferenceComponentAvailabilityZoneBalanceProperty{
EnforcementMode: jsii.String("enforcementMode"),
// the properties below are optional
MaxImbalance: jsii.Number(123),
},
PlacementStrategy: jsii.String("placementStrategy"),
},
StartupParameters: &InferenceComponentStartupParametersProperty{
ContainerStartupHealthCheckTimeoutInSeconds: jsii.Number(123),
ModelDataDownloadTimeoutInSeconds: jsii.Number(123),
},
},
},
Tags: []CfnTag{
&CfnTag{
Key: jsii.String("key"),
Value: jsii.String("value"),
},
},
VariantName: jsii.String("variantName"),
})
Initializer
ts
new CfnInferenceComponent(scope: Construct, id: string, props: CfnInferenceComponentProps)
python
CfnInferenceComponent(scope: Construct, id: str, props: CfnInferenceComponentProps)
java
new CfnInferenceComponent(Construct scope, String id, CfnInferenceComponentProps props)
csharp
new CfnInferenceComponent(Construct scope, string id, CfnInferenceComponentProps props)
go
NewCfnInferenceComponent(Scope Construct, Id *string, Props CfnInferenceComponentProps)
Construct Props
deploymentConfigIResolvable | CfnInferenceComponent.InferenceComponentDeploymentConfigPropertydeployment_configtyping.Union[IResolvable, InferenceComponentDeploymentConfigProperty]deploymentConfigIResolvableDeploymentConfigIResolvableDeploymentConfiginterface{}#The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.
The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
The name of the endpoint that hosts the inference component.
inferenceComponentNamestringinference_component_namestrinferenceComponentNameStringInferenceComponentNamestringInferenceComponentName*string#The name of the inference component.
runtimeConfigIResolvable | CfnInferenceComponent.InferenceComponentRuntimeConfigPropertyruntime_configtyping.Union[IResolvable, InferenceComponentRuntimeConfigProperty]runtimeConfigIResolvableRuntimeConfigIResolvableRuntimeConfiginterface{}#The runtime config for the inference component.
specificationIResolvable | CfnInferenceComponent.InferenceComponentSpecificationPropertyspecificationtyping.Union[IResolvable, InferenceComponentSpecificationProperty]specificationIResolvableSpecificationIResolvableSpecificationinterface{}#The specification for the inference component, for an endpoint with a single instance type.
Specify exactly one of Specification or Specifications. InstanceType is not accepted here; use Specifications for per instance type configuration.
specificationsIResolvable | IResolvable | CfnInferenceComponent.InferenceComponentSpecificationForInstanceTypeProperty[]specificationstyping.Union[IResolvable, typing.List[typing.Union[IResolvable, InferenceComponentSpecificationForInstanceTypeProperty]]]specificationsIResolvableSpecificationsIResolvableSpecificationsinterface{}#A list of specification objects for the inference component, one per instance type.
The service requires at least two entries; use the singular Specification for a single instance type.
An array of tags to apply to the resource.
The name of the production variant that hosts the inference component.
Properties
attrCreationTimestringattr_creation_timestrattrCreationTimeStringAttrCreationTimestringAttrCreationTime*stringrequired#The time when the inference component was created.
attrFailureReasonstringattr_failure_reasonstrattrFailureReasonStringAttrFailureReasonstringAttrFailureReason*stringrequired#The failure reason if the inference component is in a failed state.
attrInferenceComponentArnstringattr_inference_component_arnstrattrInferenceComponentArnStringAttrInferenceComponentArnstringAttrInferenceComponentArn*stringrequired#The Amazon Resource Name (ARN) of the inference component.
attrInferenceComponentStatusstringattr_inference_component_statusstrattrInferenceComponentStatusStringAttrInferenceComponentStatusstringAttrInferenceComponentStatus*stringrequired#The status of the inference component.
attrLastModifiedTimestringattr_last_modified_timestrattrLastModifiedTimeStringAttrLastModifiedTimestringAttrLastModifiedTime*stringrequired#The time when the inference component was last updated.
attrRuntimeConfigCurrentCopyCountnumberattr_runtime_config_current_copy_countint | floatattrRuntimeConfigCurrentCopyCountNumberAttrRuntimeConfigCurrentCopyCountdoubleAttrRuntimeConfigCurrentCopyCount*float64required#The number of runtime copies of the model container that are currently deployed.
attrRuntimeConfigDesiredCopyCountnumberattr_runtime_config_desired_copy_countint | floatattrRuntimeConfigDesiredCopyCountNumberAttrRuntimeConfigDesiredCopyCountdoubleAttrRuntimeConfigDesiredCopyCount*float64required#The number of runtime copies of the model container that you requested to deploy with the inference component.
attrRuntimeConfigPlacementStatusIResolvableattr_runtime_config_placement_statusIResolvableattrRuntimeConfigPlacementStatusIResolvableAttrRuntimeConfigPlacementStatusIResolvableAttrRuntimeConfigPlacementStatusIResolvablerequired#The placement status of the inference component across instance types.
attrSpecificationContainerDeployedImageIResolvableattr_specification_container_deployed_imageIResolvableattrSpecificationContainerDeployedImageIResolvableAttrSpecificationContainerDeployedImageIResolvableAttrSpecificationContainerDeployedImageIResolvablerequired#attrSpecificationCurrentDataCacheConfigIResolvableattr_specification_current_data_cache_configIResolvableattrSpecificationCurrentDataCacheConfigIResolvableAttrSpecificationCurrentDataCacheConfigIResolvableAttrSpecificationCurrentDataCacheConfigIResolvablerequired#Settings that affect how the inference component caches data.
cdkTagManagerTagManagercdk_tag_managerTagManagercdkTagManagerTagManagerCdkTagManagerTagManagerCdkTagManagerTagManagerrequired#Tag Manager which manages the tags for this resource.
CFN_RESOURCE_TYPE_NAMEstringcfn_resource_type_namestrCFN_RESOURCE_TYPE_NAMEStringCFN_RESOURCE_TYPE_NAMEstringCFN_RESOURCE_TYPE_NAME*stringrequiredstatic#The CloudFormation resource type name for this resource class.
cfnOptionsICfnResourceOptionscfn_optionsICfnResourceOptionscfnOptionsICfnResourceOptionsCfnOptionsICfnResourceOptionsCfnOptionsICfnResourceOptionsrequired#Options for this resource, such as condition, update policy etc.
cfnResourceTypestringcfn_resource_typestrcfnResourceTypeStringCfnResourceTypestringCfnResourceType*stringrequired#AWS resource type.
creationStackstring[]creation_stacktyping.List[str]creationStackList<String>CreationStackstring[]CreationStack*[]*stringrequired#deploymentConfigIResolvable | CfnInferenceComponent.InferenceComponentDeploymentConfigPropertydeployment_configtyping.Union[IResolvable, InferenceComponentDeploymentConfigProperty]deploymentConfigIResolvableDeploymentConfigIResolvableDeploymentConfiginterface{}#The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.
The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
The name of the endpoint that hosts the inference component.
inferenceComponentNamestringinference_component_namestrinferenceComponentNameStringInferenceComponentNamestringInferenceComponentName*string#The name of the inference component.
inferenceComponentRefInferenceComponentReferenceinference_component_refInferenceComponentReferenceinferenceComponentRefInferenceComponentReferenceInferenceComponentRefInferenceComponentReferenceInferenceComponentRefInferenceComponentReferencerequired#A reference to a InferenceComponent resource.
The logical ID for this CloudFormation stack element.
The logical ID of the element is calculated from the path of the resource node in the construct tree.
To override this value, use overrideLogicalId(newLogicalId).
Return a string that will be resolved to a CloudFormation `{ Ref }` for this element.
If, by any chance, the intrinsic reference of a resource is not a string, you could coerce it to an IResolvable through Lazy.any({ produce: resource.ref }).
runtimeConfigIResolvable | CfnInferenceComponent.InferenceComponentRuntimeConfigPropertyruntime_configtyping.Union[IResolvable, InferenceComponentRuntimeConfigProperty]runtimeConfigIResolvableRuntimeConfigIResolvableRuntimeConfiginterface{}#The runtime config for the inference component.
specificationIResolvable | CfnInferenceComponent.InferenceComponentSpecificationPropertyspecificationtyping.Union[IResolvable, InferenceComponentSpecificationProperty]specificationIResolvableSpecificationIResolvableSpecificationinterface{}#The specification for the inference component, for an endpoint with a single instance type.
specificationsIResolvable | IResolvable | CfnInferenceComponent.InferenceComponentSpecificationForInstanceTypeProperty[]specificationstyping.Union[IResolvable, typing.List[typing.Union[IResolvable, InferenceComponentSpecificationForInstanceTypeProperty]]]specificationsIResolvableSpecificationsIResolvableSpecificationsinterface{}#A list of specification objects for the inference component, one per instance type.
The stack in which this element is defined.
CfnElements must be defined within a stack scope (directly or indirectly).
An array of tags to apply to the resource.
The name of the production variant that hosts the inference component.
Methods
addDeletionOverride(path: string): voiddef add_deletion_override(self, path: str) -> Nonepublic void addDeletionOverride(String path)public void AddDeletionOverride(string path)func AddDeletionOverride(Path *string)#Syntactic sugar for `addOverride(path, undefined)`.
1 parameter
Parameters
pathpathpathpathPath— The path of the value to delete.
addDependency(target: CfnResource): voiddef add_dependency(self, target: CfnResource) -> Nonepublic void addDependency(CfnResource target)public void AddDependency(CfnResource target)func AddDependency(Target CfnResource)deprecated#Use `addResourceDependency` instead.
This method has been renamed to addResourceDependency to more clearly set it apart from construct.node.addDependency. See the documentation of that function for more details.
addDependsOn(target: CfnResource): voiddef add_depends_on(self, target: CfnResource) -> Nonepublic void addDependsOn(CfnResource target)public void AddDependsOn(CfnResource target)func AddDependsOn(Target CfnResource)deprecated#Use `addResourceDependency` instead.
notes
This can be used for resources across stacks (or nested stack) boundaries and the dependency will automatically be transferred to the relevant scope.
This method has been renamed to addResourceDependency, which makes it more clear that this method operates at a different level from the construct-level construct.node.addDependency() mechanism.
addMetadata(key: string, value: any): voiddef add_metadata(self, key: str, value: Any) -> Nonepublic void addMetadata(String key, Object value)public void AddMetadata(string key, object value)func AddMetadata(Key *string, Value interface{})#Add a value to the CloudFormation Resource Metadata.
addOverride(path: string, value: any): voiddef add_override(self, path: str, value: Any) -> Nonepublic void addOverride(String path, Object value)public void AddOverride(string path, object value)func AddOverride(Path *string, Value interface{})#Adds an override to the synthesized CloudFormation resource.
notes · 2 parameters
To add a property override, either use addPropertyOverride or prefix path with "Properties." (i.e. Properties.TopicName).
If the override is nested, separate each nested level using a dot (.) in the path parameter. If there is an array as part of the nesting, specify the index in the path.
To include a literal . in the property name, prefix with a \. In most programming languages you will need to write this as "\\." because the \ itself will need to be escaped.
For example,
typescript
cfnResource.addOverride('Properties.GlobalSecondaryIndexes.0.Projection.NonKeyAttributes', ['myattribute']);
cfnResource.addOverride('Properties.GlobalSecondaryIndexes.1.ProjectionType', 'INCLUDE');
would add the overrides
json
"Properties": {
"GlobalSecondaryIndexes": [
{
"Projection": {
"NonKeyAttributes": [ "myattribute" ]
...
}
...
},
{
"ProjectionType": "INCLUDE"
...
},
]
...
}
The value argument to addOverride will not be processed or translated in any way. Pass raw JSON values in here with the correct capitalization for CloudFormation. If you pass CDK classes or structs, they will be rendered with lowercased key names, and CloudFormation will reject the template.
Parameters
pathpathpathpathPath— - The path of the property, you can use dot notation to override values in complex types.valuevaluevaluevalueValue— - The value.
addPropertyDeletionOverride(propertyPath: string): voiddef add_property_deletion_override(self, property_path: str) -> Nonepublic void addPropertyDeletionOverride(String propertyPath)public void AddPropertyDeletionOverride(string propertyPath)func AddPropertyDeletionOverride(PropertyPath *string)#Adds an override that deletes the value of a property from the resource definition.
1 parameter
Parameters
propertyPathproperty_pathpropertyPathpropertyPathPropertyPath— The path to the property.
addPropertyOverride(propertyPath: string, value: any): voiddef add_property_override(self, property_path: str, value: Any) -> Nonepublic void addPropertyOverride(String propertyPath, Object value)public void AddPropertyOverride(string propertyPath, object value)func AddPropertyOverride(PropertyPath *string, Value interface{})#Adds an override to a resource property.
Syntactic sugar for addOverride("Properties.<...>", value).
2 parameters
Parameters
propertyPathproperty_pathpropertyPathpropertyPathPropertyPath— The path of the property.valuevaluevaluevalueValue— The value.
addResourceDependency(target: CfnResource, reason?: string): voiddef add_resource_dependency(self, target: CfnResource, reason: typing.Optional[str] = None) -> Nonepublic void addResourceDependency(CfnResource target, String reason)public void AddResourceDependency(CfnResource target, string? reason = null)func AddResourceDependency(Target CfnResource, Reason *string)#Indicates that this resource depends on another resource and cannot be provisioned unless the other resource has been successfully provisioned.
notes
This can be used for resources across stacks (or nested stack) boundaries and the dependency will automatically be transferred to the relevant scope.
This method only adds dependencies between L1 resources. If you are looking for a generic construct-to-construct dependency mechanism that works for all constructs including L2s, use construct.node.addDependency instead.
applyCrossStackReferenceStrength(strength: ReferenceStrength): voiddef apply_cross_stack_reference_strength(self, strength: ReferenceStrength) -> Nonepublic void applyCrossStackReferenceStrength(ReferenceStrength strength)public void ApplyCrossStackReferenceStrength(ReferenceStrength strength)func ApplyCrossStackReferenceStrength(Strength ReferenceStrength)#Sets the cross-stack reference strength for this resource.
When set, any cross-stack reference to this resource will use the specified strength instead of the global default from the consuming stack's context.
1 parameter
Parameters
strengthstrengthstrengthstrengthStrength— - The reference strength to use for this resource.
applyRemovalPolicy(policy?: RemovalPolicy, options?: RemovalPolicyOptions): voiddef apply_removal_policy(self, policy: typing.Optional[RemovalPolicy] = None, options: typing.Optional[RemovalPolicyOptions] = None) -> Nonepublic void applyRemovalPolicy(RemovalPolicy policy, RemovalPolicyOptions options)public void ApplyRemovalPolicy(RemovalPolicy? policy = null, RemovalPolicyOptions? options = null)func ApplyRemovalPolicy(Policy RemovalPolicy, Options RemovalPolicyOptions)#Sets the deletion policy of the resource based on the removal policy specified.
notes
The Removal Policy controls what happens to this resource when it stops being managed by CloudFormation, either because you've removed it from the CDK application or because you've made a change that requires the resource to be replaced.
The resource can be deleted (RemovalPolicy.DESTROY), or left in your AWS account for data recovery and cleanup later (RemovalPolicy.RETAIN). In some cases, a snapshot can be taken of the resource prior to deletion (RemovalPolicy.SNAPSHOT). A list of resources that support this policy can be found in the following link:
arnForInferenceComponent(resource: IInferenceComponentRef): string@staticmethod def arn_for_inference_component(resource: IInferenceComponentRef) -> strpublic static String arnForInferenceComponent(IInferenceComponentRef resource)public static string ArnForInferenceComponent(IInferenceComponentRef resource)func ArnForInferenceComponent(Resource IInferenceComponentRef) *stringstatic#cfnPropertyName(cdkPropertyName: string): stringdef cfn_property_name(self, cdk_property_name: str) -> strpublic String cfnPropertyName(String cdkPropertyName)public string CfnPropertyName(string cdkPropertyName)func CfnPropertyName(CdkPropertyName *string) *string#getAtt(attributeName: string, typeHint?: ResolutionTypeHint): Referencedef get_att(self, attribute_name: str, type_hint: typing.Optional[ResolutionTypeHint] = None) -> Referencepublic Reference getAtt(String attributeName, ResolutionTypeHint typeHint)public Reference GetAtt(string attributeName, ResolutionTypeHint? typeHint = null)func GetAtt(AttributeName *string, TypeHint ResolutionTypeHint) Reference#Returns a token for an runtime attribute of this resource.
Ideally, use generated attribute accessors (e.g. resource.arn), but this can be used for future compatibility in case there is no generated attribute.
1 parameter
Parameters
attributeNameattribute_nameattributeNameattributeNameAttributeName— The name of the attribute.
getMetadata(key: string): anydef get_metadata(self, key: str) -> Anypublic Object getMetadata(String key)public object GetMetadata(string key)func GetMetadata(Key *string) interface{}#Retrieve a value value from the CloudFormation Resource Metadata.
inspect(inspector: TreeInspector): voiddef inspect(self, inspector: TreeInspector) -> Nonepublic void inspect(TreeInspector inspector)public void Inspect(TreeInspector inspector)func Inspect(Inspector TreeInspector)#Examines the CloudFormation resource and discloses attributes.
1 parameter
Parameters
inspectorinspectorinspectorinspectorInspector— tree inspector to collect and process attributes.
isCfnElement(x: any): boolean@staticmethod def is_cfn_element(x: Any) -> boolpublic static Boolean isCfnElement(Object x)public static bool IsCfnElement(object x)func IsCfnElement(X interface{}) *boolstatic#Returns `true` if a construct is a stack element (i.e. part of the synthesized cloudformation template).
Uses duck-typing instead of instanceof to allow stack elements from different versions of this library to be included in the same stack.
returns
Returns: The construct as a stack element or undefined if it is not a stack element.
isCfnInferenceComponent(x: any): boolean@staticmethod def is_cfn_inference_component(x: Any) -> boolpublic static Boolean isCfnInferenceComponent(Object x)public static bool IsCfnInferenceComponent(object x)func IsCfnInferenceComponent(X interface{}) *boolstatic#Checks whether the given object is a CfnInferenceComponent.
isCfnResource(x: any): boolean@staticmethod def is_cfn_resource(x: Any) -> boolpublic static Boolean isCfnResource(Object x)public static bool IsCfnResource(object x)func IsCfnResource(X interface{}) *boolstatic#Check whether the given object is a CfnResource.
isConstruct(x: any): boolean@staticmethod def is_construct(x: Any) -> boolpublic static Boolean isConstruct(Object x)public static bool IsConstruct(object x)func IsConstruct(X interface{}) *boolstatic#Checks if `x` is a construct.
notes · 1 parameter · returns
Use this method instead of instanceof to properly detect Construct instances, even when the construct library is symlinked.
Explanation: in JavaScript, multiple copies of the constructs library on disk are seen as independent, completely different libraries. As a consequence, the class Construct in each copy of the constructs library is seen as a different class, and an instance of one class will not test as instanceof the other class. npm install will not create installations like this, but users may manually symlink construct libraries together or use a monorepo tool: in those cases, multiple copies of the constructs library can be accidentally installed, and instanceof will behave unpredictably. It is safest to avoid using instanceof, and using this type-testing method instead.
Parameters
xxxxX— Any object.
Returns: true if x is an object created from a class which extends Construct.
obtainDependencies(): Stack | CfnResource[]def obtain_dependencies(self, ) -> typing.List[typing.Union[Stack, CfnResource]]public List<Stack> obtainDependencies()public Stack[] ObtainDependencies()func ObtainDependencies() *[]interface{}#Retrieves an array of resources and stacks this resource depends on.
For resources depended on directly, returns the CfnResource object. For dependencies on other stacks, returns the Stack object. The order of the array is not guaranteed.
overrideLogicalId(newLogicalId: string): voiddef override_logical_id(self, new_logical_id: str) -> Nonepublic void overrideLogicalId(String newLogicalId)public void OverrideLogicalId(string newLogicalId)func OverrideLogicalId(NewLogicalId *string)#Overrides the auto-generated logical ID with a specific ID.
1 parameter
Parameters
newLogicalIdnew_logical_idnewLogicalIdnewLogicalIdNewLogicalId— The new logical ID to use for this stack element.
removeDependency(target: CfnResource): voiddef remove_dependency(self, target: CfnResource) -> Nonepublic void removeDependency(CfnResource target)public void RemoveDependency(CfnResource target)func RemoveDependency(Target CfnResource)deprecated#Use `removeResourceDependency` instead
This can be used for resources across stacks (including nested stacks) and the dependency will automatically be removed from the relevant scope.
removeResourceDependency(target: CfnResource): voiddef remove_resource_dependency(self, target: CfnResource) -> Nonepublic void removeResourceDependency(CfnResource target)public void RemoveResourceDependency(CfnResource target)func RemoveResourceDependency(Target CfnResource)#Indicates that this resource no longer depends on another resource.
This can be used for resources across stacks (including nested stacks) and the dependency will automatically be removed from the relevant scope.
replaceDependency(target: CfnResource, newTarget: CfnResource): voiddef replace_dependency(self, target: CfnResource, new_target: CfnResource) -> Nonepublic void replaceDependency(CfnResource target, CfnResource newTarget)public void ReplaceDependency(CfnResource target, CfnResource newTarget)func ReplaceDependency(Target CfnResource, NewTarget CfnResource)#Replaces one dependency with another.
2 parameters
Parameters
targettargettargettargetTarget— The dependency to replace.newTargetnew_targetnewTargetnewTargetNewTarget— The new dependency to add.
toString(): stringdef to_string(self, ) -> strpublic String toString()public string ToString()func ToString() *string#Returns a string representation of this construct.
returns
Returns: a string representation of this resource
with(...mixins: IMixin[]): IConstructdef with(self, mixins: IMixin) -> IConstructpublic IConstruct with(IMixin mixins)public IConstruct With(IMixin mixins)func With(Mixins IMixin) IConstruct#Applies one or more mixins to this construct.
Mixins are applied in order. The list of constructs is captured at the start of the call, so constructs added by a mixin will not be visited. Use multiple with() calls if subsequent mixins should apply to added constructs.