inference_components

Creates, updates, deletes or gets an inference_component resource or lists inference_components in a region

Overview

Name	inference_components
Type	Resource
Description	Resource Type definition for AWS::SageMaker::InferenceComponent
Id	awscc.sagemaker.inference_components

Fields

get (all properties)

Name	Datatype	Description
inference_component_arn	string	The Amazon Resource Name (ARN) of the inference component
inference_component_name	string	The name of the inference component
endpoint_arn	string	The Amazon Resource Name (ARN) of the endpoint the inference component is associated with
endpoint_name	string	The name of the endpoint used to run the monitoring job.
variant_name	string	The name of the endpoint variant the inference component is associated with
failure_reason	string	The failure reason if the inference component is in a failed state
▶specification	object	The specification for the inference component
▶runtime_config	object	The runtime config for the inference component
▶deployment_config	object	The deployment config for the inference component
inference_component_status	string
creation_time	string
▶tags	array	An array of tags to apply to the resource
region	string	AWS region.

list (identifiers only)

Name	Datatype	Description
inference_component_arn	string	The Amazon Resource Name (ARN) of the inference component
region	string	AWS region.

For more information, see AWS::SageMaker::InferenceComponent.

Methods

Name	Resource	Accessible by	Required Params
create_resource	inference_components	INSERT	EndpointName, Specification, region
delete_resource	inference_components	DELETE	Identifier, region
update_resource	inference_components	UPDATE	Identifier, PatchDocument, region
list_resources	inference_components_list_only	SELECT	region
get_resource	inference_components	SELECT	Identifier, region

SELECT examples

get (all properties)

Gets all properties from an individual inference_component.

SELECT
  region,
  inference_component_arn,
  inference_component_name,
  endpoint_arn,
  endpoint_name,
  variant_name,
  failure_reason,
  specification,
  runtime_config,
  deployment_config,
  inference_component_status,
  creation_time,
  last_modified_time,
  tags
FROM awscc.sagemaker.inference_components
WHERE
  region = 'us-east-1' AND
  Identifier = '{{ inference_component_arn }}';

list (identifiers only)

Lists all inference_components in a region.

SELECT
  region,
  inference_component_arn
FROM awscc.sagemaker.inference_components_list_only
WHERE
  region = 'us-east-1';

INSERT example

Use the following StackQL query and manifest file to create a new inference_component resource, using stack-deploy.

Required Properties

/*+ create */
INSERT INTO awscc.sagemaker.inference_components (
  EndpointName,
  Specification,
  region
)
SELECT
  '{{ endpoint_name }}',
  '{{ specification }}',
  '{{ region }}';

All Properties

/*+ create */
INSERT INTO awscc.sagemaker.inference_components (
  InferenceComponentName,
  EndpointArn,
  EndpointName,
  VariantName,
  Specification,
  RuntimeConfig,
  DeploymentConfig,
  Tags,
  region
)
SELECT
  '{{ inference_component_name }}',
  '{{ endpoint_arn }}',
  '{{ endpoint_name }}',
  '{{ variant_name }}',
  '{{ specification }}',
  '{{ runtime_config }}',
  '{{ deployment_config }}',
  '{{ tags }}',
  '{{ region }}';

Manifest

version: 1
name: stack name
description: stack description
providers:
  - aws
globals:
  - name: region
    value: '{{ vars.AWS_REGION }}'
resources:
  - name: inference_component
    props:
      - name: inference_component_name
        value: '{{ inference_component_name }}'
      - name: endpoint_arn
        value: '{{ endpoint_arn }}'
      - name: endpoint_name
        value: '{{ endpoint_name }}'
      - name: variant_name
        value: '{{ variant_name }}'
      - name: specification
        value:
          model_name: '{{ model_name }}'
          base_inference_component_name: '{{ base_inference_component_name }}'
          container:
            deployed_image:
              specified_image: '{{ specified_image }}'
              resolved_image: null
              resolution_time: '{{ resolution_time }}'
            image: null
            artifact_url: '{{ artifact_url }}'
            environment: {}
          startup_parameters:
            model_data_download_timeout_in_seconds: '{{ model_data_download_timeout_in_seconds }}'
            container_startup_health_check_timeout_in_seconds: null
          compute_resource_requirements:
            number_of_cpu_cores_required: null
            number_of_accelerator_devices_required: null
            min_memory_required_in_mb: '{{ min_memory_required_in_mb }}'
            max_memory_required_in_mb: null
      - name: runtime_config
        value:
          copy_count: '{{ copy_count }}'
          desired_copy_count: null
          current_copy_count: null
      - name: deployment_config
        value:
          rolling_update_policy:
            maximum_batch_size:
              type: '{{ type }}'
              value: '{{ value }}'
            wait_interval_in_seconds: '{{ wait_interval_in_seconds }}'
            rollback_maximum_batch_size: null
            maximum_execution_timeout_in_seconds: '{{ maximum_execution_timeout_in_seconds }}'
          auto_rollback_configuration:
            alarms:
              - alarm_name: '{{ alarm_name }}'
      - name: tags
        value:
          - value: '{{ value }}'
            key: '{{ key }}'

UPDATE example

Use the following StackQL query and manifest file to update a inference_component resource, using stack-deploy.

/*+ update */
UPDATE awscc.sagemaker.inference_components
SET PatchDocument = string('{{ {
    "InferenceComponentName": inference_component_name,
    "EndpointArn": endpoint_arn,
    "EndpointName": endpoint_name,
    "VariantName": variant_name,
    "DeploymentConfig": deployment_config,
    "Tags": tags
} | generate_patch_document }}')
WHERE
  region = '{{ region }}' AND
  Identifier = '{{ inference_component_arn }}';

DELETE example

/*+ delete */
DELETE FROM awscc.sagemaker.inference_components
WHERE
  Identifier = '{{ inference_component_arn }}' AND
  region = 'us-east-1';

Permissions

To operate on the inference_components resource, the following permissions are required:

Create

sagemaker:AddTags,
sagemaker:ListTags,
sagemaker:CreateInferenceComponent,
sagemaker:DescribeInferenceComponent

Update

sagemaker:UpdateInferenceComponent,
sagemaker:UpdateInferenceComponentRuntimeConfig,
sagemaker:DescribeInferenceComponent,
sagemaker:AddTags,
sagemaker:ListTags,
sagemaker:DeleteTags

Delete

sagemaker:DescribeInferenceComponent,
sagemaker:DeleteInferenceComponent,
sagemaker:DeleteTags

Read

sagemaker:DescribeInferenceComponent,
sagemaker:ListTags

List

sagemaker:ListInferenceComponents,
sagemaker:DescribeInferenceComponent,
sagemaker:ListTags