CreateModelPackage
Creates a model package that you can use to create Amazon SageMaker models or list on AWS Marketplace, or a versioned model that is part of a model group. Buyers can subscribe to model packages listed on AWS Marketplace to create models in Amazon SageMaker.
To create a model package by specifying a Docker container that contains your
inference code and the Amazon S3 location of your model artifacts, provide values
for
InferenceSpecification
. To create a model from an algorithm resource
that you created or subscribed to in AWS Marketplace, provide a value for
SourceAlgorithmSpecification
.
There are two types of model packages:
-
Versioned - a model that is part of a model group in the model registry.
-
Unversioned - a model package that is not part of a model group.
Request Syntax
{
"CertifyForMarketplace": boolean
,
"ClientToken": "string
",
"InferenceSpecification": {
"Containers": [
{
"ContainerHostname": "string
",
"Image": "string
",
"ImageDigest": "string
",
"ModelDataUrl": "string
",
"ProductId": "string
"
}
],
"SupportedContentTypes": [ "string
" ],
"SupportedRealtimeInferenceInstanceTypes": [ "string
" ],
"SupportedResponseMIMETypes": [ "string
" ],
"SupportedTransformInstanceTypes": [ "string
" ]
},
"MetadataProperties": {
"CommitId": "string
",
"GeneratedBy": "string
",
"ProjectId": "string
",
"Repository": "string
"
},
"ModelApprovalStatus": "string
",
"ModelMetrics": {
"Bias": {
"Report": {
"ContentDigest": "string
",
"ContentType": "string
",
"S3Uri": "string
"
}
},
"Explainability": {
"Report": {
"ContentDigest": "string
",
"ContentType": "string
",
"S3Uri": "string
"
}
},
"ModelDataQuality": {
"Constraints": {
"ContentDigest": "string
",
"ContentType": "string
",
"S3Uri": "string
"
},
"Statistics": {
"ContentDigest": "string
",
"ContentType": "string
",
"S3Uri": "string
"
}
},
"ModelQuality": {
"Constraints": {
"ContentDigest": "string
",
"ContentType": "string
",
"S3Uri": "string
"
},
"Statistics": {
"ContentDigest": "string
",
"ContentType": "string
",
"S3Uri": "string
"
}
}
},
"ModelPackageDescription": "string
",
"ModelPackageGroupName": "string
",
"ModelPackageName": "string
",
"SourceAlgorithmSpecification": {
"SourceAlgorithms": [
{
"AlgorithmName": "string
",
"ModelDataUrl": "string
"
}
]
},
"Tags": [
{
"Key": "string
",
"Value": "string
"
}
],
"ValidationSpecification": {
"ValidationProfiles": [
{
"ProfileName": "string
",
"TransformJobDefinition": {
"BatchStrategy": "string
",
"Environment": {
"string
" : "string
"
},
"MaxConcurrentTransforms": number
,
"MaxPayloadInMB": number
,
"TransformInput": {
"CompressionType": "string
",
"ContentType": "string
",
"DataSource": {
"S3DataSource": {
"S3DataType": "string
",
"S3Uri": "string
"
}
},
"SplitType": "string
"
},
"TransformOutput": {
"Accept": "string
",
"AssembleWith": "string
",
"KmsKeyId": "string
",
"S3OutputPath": "string
"
},
"TransformResources": {
"InstanceCount": number
,
"InstanceType": "string
",
"VolumeKmsKeyId": "string
"
}
}
}
],
"ValidationRole": "string
"
}
}
Request Parameters
For information about the parameters that are common to all actions, see Common Parameters.
The request accepts the following data in JSON format.
- CertifyForMarketplace
-
Whether to certify the model package for listing on AWS Marketplace.
This parameter is optional for unversioned models, and does not apply to versioned models.
Type: Boolean
Required: No
- ClientToken
-
A unique token that guarantees that the call to this API is idempotent.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 36.
Pattern:
^[a-zA-Z0-9-]+$
Required: No
- InferenceSpecification
-
Specifies details about inference jobs that can be run with models based on this model package, including the following:
-
The Amazon ECR paths of containers that contain the inference code and model artifacts.
-
The instance types that the model package supports for transform jobs and real-time endpoints used for inference.
-
The input and output content formats that the model package supports for inference.
Type: InferenceSpecification object
Required: No
-
- MetadataProperties
-
Metadata properties of the tracking entity, trial, or trial component.
Type: MetadataProperties object
Required: No
- ModelApprovalStatus
-
Whether the model is approved for deployment.
This parameter is optional for versioned models, and does not apply to unversioned models.
For versioned models, the value of this parameter must be set to
Approved
to deploy the model.Type: String
Valid Values:
Approved | Rejected | PendingManualApproval
Required: No
- ModelMetrics
-
A structure that contains model metrics reports.
Type: ModelMetrics object
Required: No
- ModelPackageDescription
-
A description of the model package.
Type: String
Length Constraints: Maximum length of 1024.
Pattern:
[\p{L}\p{M}\p{Z}\p{S}\p{N}\p{P}]*
Required: No
- ModelPackageGroupName
-
The name of the model group that this model version belongs to.
This parameter is required for versioned models, and does not apply to unversioned models.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 63.
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$
Required: No
- ModelPackageName
-
The name of the model package. The name must have 1 to 63 characters. Valid characters are a-z, A-Z, 0-9, and - (hyphen).
This parameter is required for unversioned models. It is not applicable to versioned models.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 63.
Pattern:
^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}$
Required: No
- SourceAlgorithmSpecification
-
Details about the algorithm that was used to create the model package.
Type: SourceAlgorithmSpecification object
Required: No
- Tags
-
A list of key value pairs associated with the model. For more information, see Tagging AWS resources in the AWS General Reference Guide.
Type: Array of Tag objects
Array Members: Minimum number of 0 items. Maximum number of 50 items.
Required: No
- ValidationSpecification
-
Specifies configurations for one or more transform jobs that Amazon SageMaker runs to test the model package.
Type: ModelPackageValidationSpecification object
Required: No
Response Syntax
{
"ModelPackageArn": "string"
}
Response Elements
If the action is successful, the service sends back an HTTP 200 response.
The following data is returned in JSON format by the service.
- ModelPackageArn
-
The Amazon Resource Name (ARN) of the new model package.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 2048.
Pattern:
arn:aws[a-z\-]*:sagemaker:[a-z0-9\-]*:[0-9]{12}:model-package/.*
Errors
For information about the errors that are common to all actions, see Common Errors.
- ConflictException
-
There was a conflict when you attempted to modify an experiment, trial, or trial component.
HTTP Status Code: 400
- ResourceLimitExceeded
-
You have exceeded an Amazon SageMaker resource limit. For example, you might have too many training jobs created.
HTTP Status Code: 400
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: