CfnEndpointPropsMixin
- class aws_cdk.mixins_preview.aws_sagemaker.mixins.CfnEndpointPropsMixin(props, *, strategy=None)
Bases:
MixinUse the
AWS::SageMaker::Endpointresource to create an endpoint using the specified configuration in the request.Amazon SageMaker uses the endpoint to provision resources and deploy models. You create the endpoint configuration with the AWS::SageMaker::EndpointConfig resource. For more information, see Deploy a Model on Amazon SageMaker Hosting Services in the Amazon SageMaker Developer Guide .
- See:
http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-sagemaker-endpoint.html
- CloudformationResource:
AWS::SageMaker::Endpoint
- Mixin:
true
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview import mixins from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins cfn_endpoint_props_mixin = sagemaker_mixins.CfnEndpointPropsMixin(sagemaker_mixins.CfnEndpointMixinProps( deployment_config=sagemaker_mixins.CfnEndpointPropsMixin.DeploymentConfigProperty( auto_rollback_configuration=sagemaker_mixins.CfnEndpointPropsMixin.AutoRollbackConfigProperty( alarms=[sagemaker_mixins.CfnEndpointPropsMixin.AlarmProperty( alarm_name="alarmName" )] ), blue_green_update_policy=sagemaker_mixins.CfnEndpointPropsMixin.BlueGreenUpdatePolicyProperty( maximum_execution_timeout_in_seconds=123, termination_wait_in_seconds=123, traffic_routing_configuration=sagemaker_mixins.CfnEndpointPropsMixin.TrafficRoutingConfigProperty( canary_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), linear_step_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), type="type", wait_interval_in_seconds=123 ) ), rolling_update_policy=sagemaker_mixins.CfnEndpointPropsMixin.RollingUpdatePolicyProperty( maximum_batch_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), maximum_execution_timeout_in_seconds=123, rollback_maximum_batch_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), wait_interval_in_seconds=123 ) ), endpoint_config_name="endpointConfigName", endpoint_name="endpointName", exclude_retained_variant_properties=[sagemaker_mixins.CfnEndpointPropsMixin.VariantPropertyProperty( variant_property_type="variantPropertyType" )], retain_all_variant_properties=False, retain_deployment_config=False, tags=[CfnTag( key="key", value="value" )] ), strategy=mixins.PropertyMergeStrategy.OVERRIDE )
Create a mixin to apply properties to
AWS::SageMaker::Endpoint.- Parameters:
props (
Union[CfnEndpointMixinProps,Dict[str,Any]]) – L1 properties to apply.strategy (
Optional[PropertyMergeStrategy]) – (experimental) Strategy for merging nested properties. Default: - PropertyMergeStrategy.MERGE
Methods
- apply_to(construct)
Apply the mixin properties to the construct.
- Parameters:
construct (
IConstruct)- Return type:
- supports(construct)
Check if this mixin supports the given construct.
- Parameters:
construct (
IConstruct)- Return type:
bool
Attributes
- CFN_PROPERTY_KEYS = ['deploymentConfig', 'endpointConfigName', 'endpointName', 'excludeRetainedVariantProperties', 'retainAllVariantProperties', 'retainDeploymentConfig', 'tags']
Static Methods
- classmethod is_mixin(x)
(experimental) Checks if
xis a Mixin.- Parameters:
x (
Any) – Any object.- Return type:
bool- Returns:
true if
xis an object created from a class which extendsMixin.- Stability:
experimental
AlarmProperty
- class CfnEndpointPropsMixin.AlarmProperty(*, alarm_name=None)
Bases:
objectAn Amazon CloudWatch alarm configured to monitor metrics on an endpoint.
- Parameters:
alarm_name (
Optional[str]) – The name of a CloudWatch alarm in your account.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins alarm_property = sagemaker_mixins.CfnEndpointPropsMixin.AlarmProperty( alarm_name="alarmName" )
Attributes
- alarm_name
The name of a CloudWatch alarm in your account.
AutoRollbackConfigProperty
- class CfnEndpointPropsMixin.AutoRollbackConfigProperty(*, alarms=None)
Bases:
objectAutomatic rollback configuration for handling endpoint deployment failures and recovery.
- Parameters:
alarms (
Union[IResolvable,Sequence[Union[IResolvable,AlarmProperty,Dict[str,Any]]],None]) – List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker rolls back the deployment.- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins auto_rollback_config_property = sagemaker_mixins.CfnEndpointPropsMixin.AutoRollbackConfigProperty( alarms=[sagemaker_mixins.CfnEndpointPropsMixin.AlarmProperty( alarm_name="alarmName" )] )
Attributes
- alarms
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint.
If any alarms are tripped during a deployment, SageMaker rolls back the deployment.
BlueGreenUpdatePolicyProperty
- class CfnEndpointPropsMixin.BlueGreenUpdatePolicyProperty(*, maximum_execution_timeout_in_seconds=None, termination_wait_in_seconds=None, traffic_routing_configuration=None)
Bases:
objectUpdate policy for a blue/green deployment.
If this update policy is specified, SageMaker creates a new fleet during the deployment while maintaining the old fleet. SageMaker flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker uses a blue/green deployment strategy with all at once traffic shifting by default.
- Parameters:
maximum_execution_timeout_in_seconds (
Union[int,float,None]) – Maximum execution timeout for the deployment. Note that the timeout value should be larger than the total waiting time specified inTerminationWaitInSecondsandWaitIntervalInSeconds.termination_wait_in_seconds (
Union[int,float,None]) – Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0.traffic_routing_configuration (
Union[IResolvable,TrafficRoutingConfigProperty,Dict[str,Any],None]) – Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins blue_green_update_policy_property = sagemaker_mixins.CfnEndpointPropsMixin.BlueGreenUpdatePolicyProperty( maximum_execution_timeout_in_seconds=123, termination_wait_in_seconds=123, traffic_routing_configuration=sagemaker_mixins.CfnEndpointPropsMixin.TrafficRoutingConfigProperty( canary_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), linear_step_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), type="type", wait_interval_in_seconds=123 ) )
Attributes
- maximum_execution_timeout_in_seconds
Maximum execution timeout for the deployment.
Note that the timeout value should be larger than the total waiting time specified in
TerminationWaitInSecondsandWaitIntervalInSeconds.
- termination_wait_in_seconds
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet.
Default is 0.
- traffic_routing_configuration
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment.
CapacitySizeProperty
- class CfnEndpointPropsMixin.CapacitySizeProperty(*, type=None, value=None)
Bases:
objectSpecifies the type and size of the endpoint capacity to activate for a blue/green deployment, a rolling deployment, or a rollback strategy.
You can specify your batches as either instance count or the overall percentage or your fleet.
For a rollback strategy, if you don’t specify the fields in this object, or if you set the
Valueto 100%, then SageMaker uses a blue/green rollback strategy and rolls all traffic back to the blue fleet.- Parameters:
type (
Optional[str]) – Specifies the endpoint capacity type. -INSTANCE_COUNT: The endpoint activates based on the number of instances. -CAPACITY_PERCENT: The endpoint activates based on the specified percentage of capacity.value (
Union[int,float,None]) – Defines the capacity size, either as a number of instances or a capacity percentage.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins capacity_size_property = sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 )
Attributes
- type
Specifies the endpoint capacity type.
INSTANCE_COUNT: The endpoint activates based on the number of instances.CAPACITY_PERCENT: The endpoint activates based on the specified percentage of capacity.
- value
Defines the capacity size, either as a number of instances or a capacity percentage.
DeploymentConfigProperty
- class CfnEndpointPropsMixin.DeploymentConfigProperty(*, auto_rollback_configuration=None, blue_green_update_policy=None, rolling_update_policy=None)
Bases:
objectThe deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.
- Parameters:
auto_rollback_configuration (
Union[IResolvable,AutoRollbackConfigProperty,Dict[str,Any],None]) – Automatic rollback configuration for handling endpoint deployment failures and recovery.blue_green_update_policy (
Union[IResolvable,BlueGreenUpdatePolicyProperty,Dict[str,Any],None]) – Update policy for a blue/green deployment. If this update policy is specified, SageMaker creates a new fleet during the deployment while maintaining the old fleet. SageMaker flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker uses a blue/green deployment strategy with all at once traffic shifting by default.rolling_update_policy (
Union[IResolvable,RollingUpdatePolicyProperty,Dict[str,Any],None]) – Specifies a rolling deployment strategy for updating a SageMaker endpoint.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins deployment_config_property = sagemaker_mixins.CfnEndpointPropsMixin.DeploymentConfigProperty( auto_rollback_configuration=sagemaker_mixins.CfnEndpointPropsMixin.AutoRollbackConfigProperty( alarms=[sagemaker_mixins.CfnEndpointPropsMixin.AlarmProperty( alarm_name="alarmName" )] ), blue_green_update_policy=sagemaker_mixins.CfnEndpointPropsMixin.BlueGreenUpdatePolicyProperty( maximum_execution_timeout_in_seconds=123, termination_wait_in_seconds=123, traffic_routing_configuration=sagemaker_mixins.CfnEndpointPropsMixin.TrafficRoutingConfigProperty( canary_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), linear_step_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), type="type", wait_interval_in_seconds=123 ) ), rolling_update_policy=sagemaker_mixins.CfnEndpointPropsMixin.RollingUpdatePolicyProperty( maximum_batch_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), maximum_execution_timeout_in_seconds=123, rollback_maximum_batch_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), wait_interval_in_seconds=123 ) )
Attributes
- auto_rollback_configuration
Automatic rollback configuration for handling endpoint deployment failures and recovery.
- blue_green_update_policy
Update policy for a blue/green deployment.
If this update policy is specified, SageMaker creates a new fleet during the deployment while maintaining the old fleet. SageMaker flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker uses a blue/green deployment strategy with all at once traffic shifting by default.
- rolling_update_policy
Specifies a rolling deployment strategy for updating a SageMaker endpoint.
RollingUpdatePolicyProperty
- class CfnEndpointPropsMixin.RollingUpdatePolicyProperty(*, maximum_batch_size=None, maximum_execution_timeout_in_seconds=None, rollback_maximum_batch_size=None, wait_interval_in_seconds=None)
Bases:
objectSpecifies a rolling deployment strategy for updating a SageMaker endpoint.
- Parameters:
maximum_batch_size (
Union[IResolvable,CapacitySizeProperty,Dict[str,Any],None]) – Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant’s total instance count.maximum_execution_timeout_in_seconds (
Union[int,float,None]) – The time limit for the total deployment. Exceeding this limit causes a timeout.rollback_maximum_batch_size (
Union[IResolvable,CapacitySizeProperty,Dict[str,Any],None]) – Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback.wait_interval_in_seconds (
Union[int,float,None]) – The length of the baking period, during which SageMaker monitors alarms for each batch on the new fleet.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins rolling_update_policy_property = sagemaker_mixins.CfnEndpointPropsMixin.RollingUpdatePolicyProperty( maximum_batch_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), maximum_execution_timeout_in_seconds=123, rollback_maximum_batch_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), wait_interval_in_seconds=123 )
Attributes
- maximum_batch_size
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet.
Value must be between 5% to 50% of the variant’s total instance count.
- maximum_execution_timeout_in_seconds
The time limit for the total deployment.
Exceeding this limit causes a timeout.
- rollback_maximum_batch_size
Batch size for rollback to the old endpoint fleet.
Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback.
- wait_interval_in_seconds
The length of the baking period, during which SageMaker monitors alarms for each batch on the new fleet.
TrafficRoutingConfigProperty
- class CfnEndpointPropsMixin.TrafficRoutingConfigProperty(*, canary_size=None, linear_step_size=None, type=None, wait_interval_in_seconds=None)
Bases:
objectDefines the traffic routing strategy during an endpoint deployment to shift traffic from the old fleet to the new fleet.
- Parameters:
canary_size (
Union[IResolvable,CapacitySizeProperty,Dict[str,Any],None]) – Batch size for the first step to turn on traffic on the new endpoint fleet.Valuemust be less than or equal to 50% of the variant’s total instance count.linear_step_size (
Union[IResolvable,CapacitySizeProperty,Dict[str,Any],None]) – Batch size for each step to turn on traffic on the new endpoint fleet.Valuemust be 10-50% of the variant’s total instance count.type (
Optional[str]) – Traffic routing strategy type. -ALL_AT_ONCE: Endpoint traffic shifts to the new fleet in a single step. -CANARY: Endpoint traffic shifts to the new fleet in two steps. The first step is the canary, which is a small portion of the traffic. The second step is the remainder of the traffic. -LINEAR: Endpoint traffic shifts to the new fleet in n steps of a configurable size.wait_interval_in_seconds (
Union[int,float,None]) – The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet.
- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins traffic_routing_config_property = sagemaker_mixins.CfnEndpointPropsMixin.TrafficRoutingConfigProperty( canary_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), linear_step_size=sagemaker_mixins.CfnEndpointPropsMixin.CapacitySizeProperty( type="type", value=123 ), type="type", wait_interval_in_seconds=123 )
Attributes
- canary_size
Batch size for the first step to turn on traffic on the new endpoint fleet.
Valuemust be less than or equal to 50% of the variant’s total instance count.
- linear_step_size
Batch size for each step to turn on traffic on the new endpoint fleet.
Valuemust be 10-50% of the variant’s total instance count.
- type
Traffic routing strategy type.
ALL_AT_ONCE: Endpoint traffic shifts to the new fleet in a single step.CANARY: Endpoint traffic shifts to the new fleet in two steps. The first step is the canary, which is a small portion of the traffic. The second step is the remainder of the traffic.LINEAR: Endpoint traffic shifts to the new fleet in n steps of a configurable size.
- wait_interval_in_seconds
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet.
VariantPropertyProperty
- class CfnEndpointPropsMixin.VariantPropertyProperty(*, variant_property_type=None)
Bases:
objectSpecifies a production variant property type for an Endpoint.
If you are updating an Endpoint with the RetainAllVariantProperties option set to
true, theVarientPropertyobjects listed in ExcludeRetainedVariantProperties override the existing variant properties of the Endpoint.- Parameters:
variant_property_type (
Optional[str]) –The type of variant property. The supported values are:. -
DesiredInstanceCount: Overrides the existing variant instance counts using the InitialInstanceCount values in the ProductionVariants . -DesiredWeight: Overrides the existing variant weights using the InitialVariantWeight values in the ProductionVariants . -DataCaptureConfig: (Not currently supported.)- See:
- ExampleMetadata:
fixture=_generated
Example:
# The code below shows an example of how to instantiate this type. # The values are placeholders you should change. from aws_cdk.mixins_preview.aws_sagemaker import mixins as sagemaker_mixins variant_property_property = sagemaker_mixins.CfnEndpointPropsMixin.VariantPropertyProperty( variant_property_type="variantPropertyType" )
Attributes
- variant_property_type
.
DesiredInstanceCount: Overrides the existing variant instance counts using the InitialInstanceCount values in the ProductionVariants .DesiredWeight: Overrides the existing variant weights using the InitialVariantWeight values in the ProductionVariants .DataCaptureConfig: (Not currently supported.)
- See:
- Type:
The type of variant property. The supported values are