models

Creates, updates, deletes, gets or lists a models resource.

Overview

Name	models
Type	Resource
Id	aws.sagemaker.models

Fields

The following fields are returned by SELECT queries:

describe_model

Name	Datatype	Description
containers	array	The containers in the inference pipeline.
creation_time	string (date-time)	A timestamp that shows when the model was created.
deployment_recommendation	object	A set of recommended deployment configurations for the model.
enable_network_isolation	boolean	If True, no inbound or outbound network calls can be made to or from the model container.
execution_role_arn	string	The Amazon Resource Name (ARN) of the IAM role that you specified for the model. (pattern: <code>arn:aws[a-z-]*:iam::\d{12}:role/?[a-zA-Z_0-9+=,.@-_/]+</code>)
inference_execution_config	object	Specifies details of how containers in a multi-container endpoint are called.
model_arn	string	The Amazon Resource Name (ARN) of the model. (pattern: <code>arn:aws[a-z-]:sagemaker:[a-z0-9-]:[0-9]{12}:model/.*</code>)
model_name	string	Name of the SageMaker model. (pattern: <code>[a-zA-Z0-9]([-a-zA-Z0-9]*[a-zA-Z0-9])?</code>)
primary_container	object	Describes the container, as part of model definition.
vpc_config	object	Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC. For more information, see Give SageMaker Access to Resources in your Amazon VPC.

list_models

Name	Datatype	Description
creation_time	string (date-time)	A timestamp that indicates when the model was created.
model_arn	string	The Amazon Resource Name (ARN) of the model. (pattern: <code>arn:aws[a-z-]:sagemaker:[a-z0-9-]:[0-9]{12}:model/.*</code>)
model_name	string	The name of the model that you want a summary for. (pattern: <code>[a-zA-Z0-9]([-a-zA-Z0-9]*[a-zA-Z0-9])?</code>)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
describe_model	select	region		Describes a model that you created using the CreateModel API.
list_models	select	region		Lists models created with the CreateModel API.
create_model	insert	region, ModelName		Creates a model in SageMaker. In the request, you name the model and describe a primary container. For the primary container, you specify the Docker image that contains inference code, artifacts (from prior training), and a custom environment map that the inference code uses when you deploy the model for predictions. Use this API to create a model if you want to use SageMaker hosting services or run a batch transform job. To host your model, you create an endpoint configuration with the CreateEndpointConfig API, and then create an endpoint with the CreateEndpoint API. SageMaker then deploys all of the containers that you defined for the model in the hosting environment. To run a batch transform using your model, you start a job with the CreateTransformJob API. SageMaker uses your model and your dataset to get inferences which are then saved to a specified S3 location. In the request, you also provide an IAM role that SageMaker can assume to access model artifacts and docker image for deployment on ML compute hosting instances or for batch transform jobs. In addition, you also use the IAM role to manage permissions the inference code needs. For example, if the inference code access any other Amazon Web Services resources, you grant necessary permissions via this role.
delete_model	delete	region		Deletes a model. The DeleteModel API deletes only the model entry that was created in SageMaker when you called the CreateModel API. It does not delete model artifacts, inference code, or the IAM role that you specified when creating the model.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
region	string	AWS region (default: us-east-1)

SELECT examples

describe_model

Describes a model that you created using the CreateModel API.

SELECT
containers,
creation_time,
deployment_recommendation,
enable_network_isolation,
execution_role_arn,
inference_execution_config,
model_arn,
model_name,
primary_container,
vpc_config
FROM aws.sagemaker.models
WHERE region = '{{ region }}' -- required
;

list_models

Lists models created with the CreateModel API.

SELECT
creation_time,
model_arn,
model_name
FROM aws.sagemaker.models
WHERE region = '{{ region }}' -- required
;

INSERT examples

create_model

Creates a model in SageMaker. In the request, you name the model and describe a primary container. For the primary container, you specify the Docker image that contains inference code, artifacts (from prior training), and a custom environment map that the inference code uses when you deploy the model for predictions. Use this API to create a model if you want to use SageMaker hosting services or run a batch transform job. To host your model, you create an endpoint configuration with the CreateEndpointConfig API, and then create an endpoint with the CreateEndpoint API. SageMaker then deploys all of the containers that you defined for the model in the hosting environment. To run a batch transform using your model, you start a job with the CreateTransformJob API. SageMaker uses your model and your dataset to get inferences which are then saved to a specified S3 location. In the request, you also provide an IAM role that SageMaker can assume to access model artifacts and docker image for deployment on ML compute hosting instances or for batch transform jobs. In addition, you also use the IAM role to manage permissions the inference code needs. For example, if the inference code access any other Amazon Web Services resources, you grant necessary permissions via this role.

INSERT INTO aws.sagemaker.models (
ModelName,
PrimaryContainer,
Containers,
InferenceExecutionConfig,
ExecutionRoleArn,
Tags,
VpcConfig,
EnableNetworkIsolation,
region
)
SELECT 
'{{ ModelName }}' /* required */,
'{{ PrimaryContainer }}',
'{{ Containers }}',
'{{ InferenceExecutionConfig }}',
'{{ ExecutionRoleArn }}',
'{{ Tags }}',
'{{ VpcConfig }}',
{{ EnableNetworkIsolation }},
'{{ region }}'
RETURNING
model_arn
;

Manifest

# Description fields are for documentation purposes
- name: models
props:
  - name: region
    value: "{{ region }}"
    description: Required parameter for the models resource.
  - name: ModelName
    value: "{{ ModelName }}"
    description: |
      The name of the new model.
  - name: PrimaryContainer
    description: |
      The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
    value:
      ContainerHostname: "{{ ContainerHostname }}"
      Image: "{{ Image }}"
      ImageConfig:
        RepositoryAccessMode: "{{ RepositoryAccessMode }}"
        RepositoryAuthConfig:
          RepositoryCredentialsProviderArn: "{{ RepositoryCredentialsProviderArn }}"
      Mode: "{{ Mode }}"
      ModelDataUrl: "{{ ModelDataUrl }}"
      ModelDataSource:
        S3DataSource:
          S3Uri: "{{ S3Uri }}"
          S3DataType: "{{ S3DataType }}"
          CompressionType: "{{ CompressionType }}"
          ModelAccessConfig:
            AcceptEula: {{ AcceptEula }}
          HubAccessConfig:
            HubContentArn: "{{ HubContentArn }}"
          ManifestS3Uri: "{{ ManifestS3Uri }}"
          ETag: "{{ ETag }}"
          ManifestEtag: "{{ ManifestEtag }}"
      AdditionalModelDataSources:
        - ChannelName: "{{ ChannelName }}"
          S3DataSource:
            S3Uri: "{{ S3Uri }}"
            S3DataType: "{{ S3DataType }}"
            CompressionType: "{{ CompressionType }}"
            ModelAccessConfig:
              AcceptEula: {{ AcceptEula }}
            HubAccessConfig:
              HubContentArn: "{{ HubContentArn }}"
            ManifestS3Uri: "{{ ManifestS3Uri }}"
            ETag: "{{ ETag }}"
            ManifestEtag: "{{ ManifestEtag }}"
      Environment: "{{ Environment }}"
      ModelPackageName: "{{ ModelPackageName }}"
      InferenceSpecificationName: "{{ InferenceSpecificationName }}"
      MultiModelConfig:
        ModelCacheSetting: "{{ ModelCacheSetting }}"
      ContainerMetricsConfig:
        MetricsEndpoints:
          - MetricsEndpointPath: "{{ MetricsEndpointPath }}"
            MetricPublishFrequencyInSeconds: {{ MetricPublishFrequencyInSeconds }}
  - name: Containers
    description: |
      Specifies the containers in the inference pipeline.
    value:
      - ContainerHostname: "{{ ContainerHostname }}"
        Image: "{{ Image }}"
        ImageConfig:
          RepositoryAccessMode: "{{ RepositoryAccessMode }}"
          RepositoryAuthConfig:
            RepositoryCredentialsProviderArn: "{{ RepositoryCredentialsProviderArn }}"
        Mode: "{{ Mode }}"
        ModelDataUrl: "{{ ModelDataUrl }}"
        ModelDataSource:
          S3DataSource:
            S3Uri: "{{ S3Uri }}"
            S3DataType: "{{ S3DataType }}"
            CompressionType: "{{ CompressionType }}"
            ModelAccessConfig:
              AcceptEula: {{ AcceptEula }}
            HubAccessConfig:
              HubContentArn: "{{ HubContentArn }}"
            ManifestS3Uri: "{{ ManifestS3Uri }}"
            ETag: "{{ ETag }}"
            ManifestEtag: "{{ ManifestEtag }}"
        AdditionalModelDataSources: "{{ AdditionalModelDataSources }}"
        Environment: "{{ Environment }}"
        ModelPackageName: "{{ ModelPackageName }}"
        InferenceSpecificationName: "{{ InferenceSpecificationName }}"
        MultiModelConfig:
          ModelCacheSetting: "{{ ModelCacheSetting }}"
        ContainerMetricsConfig:
          MetricsEndpoints:
            - MetricsEndpointPath: "{{ MetricsEndpointPath }}"
              MetricPublishFrequencyInSeconds: {{ MetricPublishFrequencyInSeconds }}
  - name: InferenceExecutionConfig
    description: |
      Specifies details of how containers in a multi-container endpoint are called.
    value:
      Mode: "{{ Mode }}"
  - name: ExecutionRoleArn
    value: "{{ ExecutionRoleArn }}"
    description: |
      The Amazon Resource Name (ARN) of the IAM role that SageMaker can assume to access model artifacts and docker image for deployment on ML compute instances or for batch transform jobs. Deploying on ML compute instances is part of model hosting. For more information, see SageMaker Roles. To be able to pass this role to SageMaker, the caller of this API must have the iam:PassRole permission.
  - name: Tags
    description: |
      An array of key-value pairs. You can use tags to categorize your Amazon Web Services resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging Amazon Web Services Resources.
    value:
      - Key: "{{ Key }}"
        Value: "{{ Value }}"
  - name: VpcConfig
    description: |
      Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC. For more information, see Give SageMaker Access to Resources in your Amazon VPC.
    value:
      SecurityGroupIds:
        - "{{ SecurityGroupIds }}"
      Subnets:
        - "{{ Subnets }}"
  - name: EnableNetworkIsolation
    value: {{ EnableNetworkIsolation }}
    description: |
      Isolates the model container. No inbound or outbound network calls can be made to or from the model container.

DELETE examples

delete_model

Deletes a model. The DeleteModel API deletes only the model entry that was created in SageMaker when you called the CreateModel API. It does not delete model artifacts, inference code, or the IAM role that you specified when creating the model.

DELETE FROM aws.sagemaker.models
WHERE region = '{{ region }}' --required
;