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 = '{{ region }}' 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 = '{{ region }}';

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 }}'
RETURNING
  ErrorCode,
  EventTime,
  Identifier,
  Operation,
  OperationStatus,
  RequestToken,
  ResourceModel,
  RetryAfter,
  StatusMessage,
  TypeName
;

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 }}'
RETURNING
  ErrorCode,
  EventTime,
  Identifier,
  Operation,
  OperationStatus,
  RequestToken,
  ResourceModel,
  RetryAfter,
  StatusMessage,
  TypeName
;

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 }}'
RETURNING
  ErrorCode,
  EventTime,
  Identifier,
  Operation,
  OperationStatus,
  RequestToken,
  ResourceModel,
  RetryAfter,
  StatusMessage,
  TypeName
;

DELETE example

/*+ delete */
DELETE FROM awscc.sagemaker.inference_components
WHERE
  Identifier = '{{ inference_component_arn }}' AND
  region = '{{ region }}'
RETURNING
  ErrorCode,
  EventTime,
  Identifier,
  Operation,
  OperationStatus,
  RequestToken,
  ResourceModel,
  RetryAfter,
  StatusMessage,
  TypeName
;

Additional Parameters

Mutable resources in the Cloud Control provider support additional optional parameters which can be supplied with INSERT, UPDATE, or DELETE operations. These include:

Parameter	Description
ClientToken	A unique identifier to ensure the idempotency of the resource request. This allows the provider to accurately distinguish between retries and new requests. A client token is valid for 36 hours once used. After that, a resource request with the same client token is treated as a new request. If you do not specify a client token, one is generated for inclusion in the request.
RoleArn	The ARN of the IAM role used to perform this resource operation. The role specified must have the permissions required for this operation. If you do not specify a role, a temporary session is created using your AWS user credentials.
TypeVersionId	For private resource types, the type version to use in this resource operation. If you do not specify a resource version, the default version is used.

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