inference_recommendations_jobs

Creates, updates, deletes, gets or lists an inference_recommendations_jobs resource.

Overview

Name	inference_recommendations_jobs
Type	Resource
Id	aws.sagemaker.inference_recommendations_jobs

Fields

The following fields are returned by SELECT queries:

describe_inference_recommendations_job

Name	Datatype	Description
completion_time	string (date-time)	A timestamp that shows when the job completed.
creation_time	string (date-time)	A timestamp that shows when the job was created.
endpoint_performances	array	The performance results from running an Inference Recommender job on an existing endpoint.
failure_reason	string	If the job fails, provides information why the job failed.
inference_recommendations	array	The recommendations made by Inference Recommender.
input_config	object	Returns information about the versioned model package Amazon Resource Name (ARN), the traffic pattern, and endpoint configurations you provided when you initiated the job.
job_arn	string	The Amazon Resource Name (ARN) of the job. (pattern: <code>arn:aws[a-z-]:sagemaker:[a-z0-9-]:[0-9]{12}:inference-recommendations-job/.*</code>)
job_description	string	The job description that you provided when you initiated the job.
job_name	string	The name of the job. The name must be unique within an Amazon Web Services Region in the Amazon Web Services account. (pattern: <code>[a-zA-Z0-9](-*[a-zA-Z0-9]){0,63}</code>)
job_type	string	The job type that you provided when you initiated the job. (Default, Advanced)
last_modified_time	string (date-time)	A timestamp that shows when the job was last modified.
role_arn	string	The Amazon Resource Name (ARN) of the Amazon Web Services Identity and Access Management (IAM) role you provided when you initiated the job. (pattern: <code>arn:aws[a-z-]*:iam::\d{12}:role/?[a-zA-Z_0-9+=,.@-_/]+</code>)
status	string	The status of the job. (PENDING, IN_PROGRESS, COMPLETED, FAILED, STOPPING, STOPPED, DELETING, DELETED)
stopping_conditions	object	The stopping conditions that you provided when you initiated the job.

list_inference_recommendations_jobs

Name	Datatype	Description
completion_time	string (date-time)	A timestamp that shows when the job completed.
creation_time	string (date-time)	A timestamp that shows when the job was created.
failure_reason	string	If the job fails, provides information why the job failed.
job_arn	string	The Amazon Resource Name (ARN) of the recommendation job. (pattern: <code>arn:aws[a-z-]:sagemaker:[a-z0-9-]:[0-9]{12}:inference-recommendations-job/.*</code>)
job_description	string	The job description.
job_name	string	The name of the job. (pattern: <code>[a-zA-Z0-9](-*[a-zA-Z0-9]){0,63}</code>)
job_type	string	The recommendation job type. (Default, Advanced)
last_modified_time	string (date-time)	A timestamp that shows when the job was last modified.
model_name	string	The name of the created model. (pattern: <code>[a-zA-Z0-9]([-a-zA-Z0-9]*[a-zA-Z0-9])?</code>)
model_package_version_arn	string	The Amazon Resource Name (ARN) of a versioned model package. (pattern: <code>arn:aws[a-z-]*:sagemaker:[a-z0-9-]{9,16}:[0-9]{12}:model-package/[\S]{1,2048}</code>)
role_arn	string	The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker to perform tasks on your behalf. (pattern: <code>arn:aws[a-z-]*:iam::\d{12}:role/?[a-zA-Z_0-9+=,.@-_/]+</code>)
sample_payload_url	string	The Amazon Simple Storage Service (Amazon S3) path where the sample payload is stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). (pattern: <code>(https|s3):​//([^/]+)/?(.*)</code>)
status	string	The status of the job. (PENDING, IN_PROGRESS, COMPLETED, FAILED, STOPPING, STOPPED, DELETING, DELETED)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
describe_inference_recommendations_job	select	region		Provides the results of the Inference Recommender job. One or more recommendation jobs are returned.
list_inference_recommendations_jobs	select	region		Lists recommendation jobs that satisfy various filters.
create_inference_recommendations_job	insert	region, JobName, JobType, RoleArn, InputConfig		Starts a recommendation job. You can create either an instance recommendation or load test job.

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_inference_recommendations_job

Provides the results of the Inference Recommender job. One or more recommendation jobs are returned.

SELECT
completion_time,
creation_time,
endpoint_performances,
failure_reason,
inference_recommendations,
input_config,
job_arn,
job_description,
job_name,
job_type,
last_modified_time,
role_arn,
status,
stopping_conditions
FROM aws.sagemaker.inference_recommendations_jobs
WHERE region = '{{ region }}' -- required
;

list_inference_recommendations_jobs

Lists recommendation jobs that satisfy various filters.

SELECT
completion_time,
creation_time,
failure_reason,
job_arn,
job_description,
job_name,
job_type,
last_modified_time,
model_name,
model_package_version_arn,
role_arn,
sample_payload_url,
status
FROM aws.sagemaker.inference_recommendations_jobs
WHERE region = '{{ region }}' -- required
;

INSERT examples

create_inference_recommendations_job

Starts a recommendation job. You can create either an instance recommendation or load test job.

INSERT INTO aws.sagemaker.inference_recommendations_jobs (
JobName,
JobType,
RoleArn,
InputConfig,
JobDescription,
StoppingConditions,
OutputConfig,
Tags,
region
)
SELECT 
'{{ JobName }}' /* required */,
'{{ JobType }}' /* required */,
'{{ RoleArn }}' /* required */,
'{{ InputConfig }}' /* required */,
'{{ JobDescription }}',
'{{ StoppingConditions }}',
'{{ OutputConfig }}',
'{{ Tags }}',
'{{ region }}'
RETURNING
job_arn
;

Manifest

# Description fields are for documentation purposes
- name: inference_recommendations_jobs
props:
  - name: region
    value: "{{ region }}"
    description: Required parameter for the inference_recommendations_jobs resource.
  - name: JobName
    value: "{{ JobName }}"
    description: |
      A name for the recommendation job. The name must be unique within the Amazon Web Services Region and within your Amazon Web Services account. The job name is passed down to the resources created by the recommendation job. The names of resources (such as the model, endpoint configuration, endpoint, and compilation) that are prefixed with the job name are truncated at 40 characters.
  - name: JobType
    value: "{{ JobType }}"
    description: |
      Defines the type of recommendation job. Specify Default to initiate an instance recommendation and Advanced to initiate a load test. If left unspecified, Amazon SageMaker Inference Recommender will run an instance recommendation (DEFAULT) job.
    valid_values: ['Default', 'Advanced']
  - name: RoleArn
    value: "{{ RoleArn }}"
    description: |
      The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker to perform tasks on your behalf.
  - name: InputConfig
    description: |
      Provides information about the versioned model package Amazon Resource Name (ARN), the traffic pattern, and endpoint configurations.
    value:
      ModelPackageVersionArn: "{{ ModelPackageVersionArn }}"
      ModelName: "{{ ModelName }}"
      JobDurationInSeconds: {{ JobDurationInSeconds }}
      TrafficPattern:
        TrafficType: "{{ TrafficType }}"
        Phases:
          - InitialNumberOfUsers: {{ InitialNumberOfUsers }}
            SpawnRate: {{ SpawnRate }}
            DurationInSeconds: {{ DurationInSeconds }}
        Stairs:
          DurationInSeconds: {{ DurationInSeconds }}
          NumberOfSteps: {{ NumberOfSteps }}
          UsersPerStep: {{ UsersPerStep }}
      ResourceLimit:
        MaxNumberOfTests: {{ MaxNumberOfTests }}
        MaxParallelOfTests: {{ MaxParallelOfTests }}
      EndpointConfigurations:
        - InstanceType: "{{ InstanceType }}"
          ServerlessConfig:
            MemorySizeInMB: {{ MemorySizeInMB }}
            MaxConcurrency: {{ MaxConcurrency }}
            ProvisionedConcurrency: {{ ProvisionedConcurrency }}
          InferenceSpecificationName: "{{ InferenceSpecificationName }}"
          EnvironmentParameterRanges:
            CategoricalParameterRanges:
              - Name: "{{ Name }}"
                Value: "{{ Value }}"
      VolumeKmsKeyId: "{{ VolumeKmsKeyId }}"
      ContainerConfig:
        Domain: "{{ Domain }}"
        Task: "{{ Task }}"
        Framework: "{{ Framework }}"
        FrameworkVersion: "{{ FrameworkVersion }}"
        PayloadConfig:
          SamplePayloadUrl: "{{ SamplePayloadUrl }}"
          SupportedContentTypes:
            - "{{ SupportedContentTypes }}"
        NearestModelName: "{{ NearestModelName }}"
        SupportedInstanceTypes:
          - "{{ SupportedInstanceTypes }}"
        SupportedEndpointType: "{{ SupportedEndpointType }}"
        DataInputConfig: "{{ DataInputConfig }}"
        SupportedResponseMIMETypes:
          - "{{ SupportedResponseMIMETypes }}"
      Endpoints:
        - EndpointName: "{{ EndpointName }}"
      VpcConfig:
        SecurityGroupIds:
          - "{{ SecurityGroupIds }}"
        Subnets:
          - "{{ Subnets }}"
  - name: JobDescription
    value: "{{ JobDescription }}"
    description: |
      Description of the recommendation job.
  - name: StoppingConditions
    description: |
      A set of conditions for stopping a recommendation job. If any of the conditions are met, the job is automatically stopped.
    value:
      MaxInvocations: {{ MaxInvocations }}
      ModelLatencyThresholds:
        - Percentile: "{{ Percentile }}"
          ValueInMilliseconds: {{ ValueInMilliseconds }}
      FlatInvocations: "{{ FlatInvocations }}"
  - name: OutputConfig
    description: |
      Provides information about the output artifacts and the KMS key to use for Amazon S3 server-side encryption.
    value:
      KmsKeyId: "{{ KmsKeyId }}"
      CompiledOutputConfig:
        S3OutputUri: "{{ S3OutputUri }}"
  - name: Tags
    description: |
      The metadata that you apply to Amazon Web Services resources to help you categorize and organize them. Each tag consists of a key and a value, both of which you define. For more information, see Tagging Amazon Web Services Resources in the Amazon Web Services General Reference.
    value:
      - Key: "{{ Key }}"
        Value: "{{ Value }}"