Amazonka.SageMaker.CreateModelPackage

Creates a model package that you can use to create SageMaker models or list on Amazon Web Services Marketplace, or a versioned model that is part of a model group. Buyers can subscribe to model packages listed on Amazon Web Services Marketplace to create models in 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 Amazon Web Services 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.

Creating a Request

data CreateModelPackage

See: newCreateModelPackage smart constructor.

Constructors

CreateModelPackage'

Fields

• additionalInferenceSpecifications :: Maybe (NonEmpty AdditionalInferenceSpecificationDefinition)

  An array of additional Inference Specification objects. Each additional Inference Specification specifies artifacts based on this model package that can be used on inference endpoints. Generally used with SageMaker Neo to store the compiled artifacts.

• certifyForMarketplace :: Maybe Bool

  Whether to certify the model package for listing on Amazon Web Services Marketplace.

  This parameter is optional for unversioned models, and does not apply to versioned models.

• clientToken :: Maybe Text

  A unique token that guarantees that the call to this API is idempotent.

• customerMetadataProperties :: Maybe (HashMap Text Text)

  The metadata properties associated with the model package versions.

• domain :: Maybe Text

  The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.

• driftCheckBaselines :: Maybe DriftCheckBaselines

  Represents the drift check baselines that can be used when the model monitor is set using the model package. For more information, see the topic on Drift Detection against Previous Baselines in SageMaker Pipelines in the Amazon SageMaker Developer Guide.

• inferenceSpecification :: Maybe 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.
• metadataProperties :: Maybe MetadataProperties
• modelApprovalStatus :: Maybe 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.

• modelMetrics :: Maybe ModelMetrics

  A structure that contains model metrics reports.

• modelPackageDescription :: Maybe Text

  A description of the model package.

• modelPackageGroupName :: Maybe Text

  The name or Amazon Resource Name (ARN) of the model package group that this model version belongs to.

  This parameter is required for versioned models, and does not apply to unversioned models.

• modelPackageName :: Maybe Text

  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.

• samplePayloadUrl :: Maybe Text

  The Amazon Simple Storage Service (Amazon S3) path where the sample payload are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

• sourceAlgorithmSpecification :: Maybe SourceAlgorithmSpecification

  Details about the algorithm that was used to create the model package.

• tags :: Maybe [Tag]

  A list of key value pairs associated with the model. For more information, see Tagging Amazon Web Services resources in the Amazon Web Services General Reference Guide.

• task :: Maybe Text

  The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification. The following tasks are supported by Inference Recommender: "IMAGE_CLASSIFICATION" | "OBJECT_DETECTION" | "TEXT_GENERATION" |"IMAGE_SEGMENTATION" | "FILL_MASK" | "CLASSIFICATION" | "REGRESSION" | "OTHER".

  Specify "OTHER" if none of the tasks listed fit your use case.

• validationSpecification :: Maybe ModelPackageValidationSpecification

  Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.

Instances

ToJSON CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

toJSON :: CreateModelPackage -> Value

toEncoding :: CreateModelPackage -> Encoding

toJSONList :: [CreateModelPackage] -> Value

toEncodingList :: [CreateModelPackage] -> Encoding

ToHeaders CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

toHeaders :: CreateModelPackage -> [Header]

ToPath CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

toPath :: CreateModelPackage -> ByteString

ToQuery CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

toQuery :: CreateModelPackage -> QueryString

AWSRequest CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Associated Types

type AWSResponse CreateModelPackage

Methods

request :: (Service -> Service) -> CreateModelPackage -> Request CreateModelPackage

response :: MonadResource m => (ByteStringLazy -> IO ByteStringLazy) -> Service -> Proxy CreateModelPackage -> ClientResponse ClientBody -> m (Either Error (ClientResponse (AWSResponse CreateModelPackage)))

Generic CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Associated Types

type Rep CreateModelPackage :: Type -> Type

Methods

from :: CreateModelPackage -> Rep CreateModelPackage x

to :: Rep CreateModelPackage x -> CreateModelPackage

Read CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

readsPrec :: Int -> ReadS CreateModelPackage

readList :: ReadS [CreateModelPackage]

readPrec :: ReadPrec CreateModelPackage

readListPrec :: ReadPrec [CreateModelPackage]

Show CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

showsPrec :: Int -> CreateModelPackage -> ShowS

show :: CreateModelPackage -> String

showList :: [CreateModelPackage] -> ShowS

NFData CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

rnf :: CreateModelPackage -> ()

Eq CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

(==) :: CreateModelPackage -> CreateModelPackage -> Bool

(/=) :: CreateModelPackage -> CreateModelPackage -> Bool

Hashable CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

hashWithSalt :: Int -> CreateModelPackage -> Int

hash :: CreateModelPackage -> Int

type AWSResponse CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

type AWSResponse CreateModelPackage = CreateModelPackageResponse

type Rep CreateModelPackage

Defined in Amazonka.SageMaker.CreateModelPackage

type Rep CreateModelPackage = D1 ('MetaData "CreateModelPackage" "Amazonka.SageMaker.CreateModelPackage" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "CreateModelPackage'" 'PrefixI 'True) ((((S1 ('MetaSel ('Just "additionalInferenceSpecifications") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (NonEmpty AdditionalInferenceSpecificationDefinition))) :*: S1 ('MetaSel ('Just "certifyForMarketplace") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Bool))) :*: (S1 ('MetaSel ('Just "clientToken") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "customerMetadataProperties") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (HashMap Text Text))))) :*: ((S1 ('MetaSel ('Just "domain") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "driftCheckBaselines") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe DriftCheckBaselines))) :*: (S1 ('MetaSel ('Just "inferenceSpecification") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe InferenceSpecification)) :*: (S1 ('MetaSel ('Just "metadataProperties") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe MetadataProperties)) :*: S1 ('MetaSel ('Just "modelApprovalStatus") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ModelApprovalStatus)))))) :*: (((S1 ('MetaSel ('Just "modelMetrics") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ModelMetrics)) :*: S1 ('MetaSel ('Just "modelPackageDescription") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text))) :*: (S1 ('MetaSel ('Just "modelPackageGroupName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "modelPackageName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)))) :*: ((S1 ('MetaSel ('Just "samplePayloadUrl") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "sourceAlgorithmSpecification") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe SourceAlgorithmSpecification))) :*: (S1 ('MetaSel ('Just "tags") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [Tag])) :*: (S1 ('MetaSel ('Just "task") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "validationSpecification") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ModelPackageValidationSpecification))))))))

newCreateModelPackage :: CreateModelPackage

Create a value of CreateModelPackage with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

CreateModelPackage, createModelPackage_additionalInferenceSpecifications - An array of additional Inference Specification objects. Each additional Inference Specification specifies artifacts based on this model package that can be used on inference endpoints. Generally used with SageMaker Neo to store the compiled artifacts.

CreateModelPackage, createModelPackage_certifyForMarketplace - Whether to certify the model package for listing on Amazon Web Services Marketplace.

This parameter is optional for unversioned models, and does not apply to versioned models.

$sel:clientToken:CreateModelPackage', createModelPackage_clientToken - A unique token that guarantees that the call to this API is idempotent.

CreateModelPackage, createModelPackage_customerMetadataProperties - The metadata properties associated with the model package versions.

CreateModelPackage, createModelPackage_domain - The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.

CreateModelPackage, createModelPackage_driftCheckBaselines - Represents the drift check baselines that can be used when the model monitor is set using the model package. For more information, see the topic on Drift Detection against Previous Baselines in SageMaker Pipelines in the Amazon SageMaker Developer Guide.

CreateModelPackage, createModelPackage_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.

CreateModelPackage, createModelPackage_metadataProperties - Undocumented member.

CreateModelPackage, createModelPackage_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.

CreateModelPackage, createModelPackage_modelMetrics - A structure that contains model metrics reports.

CreateModelPackage, createModelPackage_modelPackageDescription - A description of the model package.

CreateModelPackage, createModelPackage_modelPackageGroupName - The name or Amazon Resource Name (ARN) of the model package group that this model version belongs to.

This parameter is required for versioned models, and does not apply to unversioned models.

CreateModelPackage, createModelPackage_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.

CreateModelPackage, createModelPackage_samplePayloadUrl - The Amazon Simple Storage Service (Amazon S3) path where the sample payload are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

CreateModelPackage, createModelPackage_sourceAlgorithmSpecification - Details about the algorithm that was used to create the model package.

CreateModelPackage, createModelPackage_tags - A list of key value pairs associated with the model. For more information, see Tagging Amazon Web Services resources in the Amazon Web Services General Reference Guide.

CreateModelPackage, createModelPackage_task - The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification. The following tasks are supported by Inference Recommender: "IMAGE_CLASSIFICATION" | "OBJECT_DETECTION" | "TEXT_GENERATION" |"IMAGE_SEGMENTATION" | "FILL_MASK" | "CLASSIFICATION" | "REGRESSION" | "OTHER".

Specify "OTHER" if none of the tasks listed fit your use case.

CreateModelPackage, createModelPackage_validationSpecification - Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.

Request Lenses

createModelPackage_additionalInferenceSpecifications :: Lens' CreateModelPackage (Maybe (NonEmpty AdditionalInferenceSpecificationDefinition))

An array of additional Inference Specification objects. Each additional Inference Specification specifies artifacts based on this model package that can be used on inference endpoints. Generally used with SageMaker Neo to store the compiled artifacts.

createModelPackage_certifyForMarketplace :: Lens' CreateModelPackage (Maybe Bool)

Whether to certify the model package for listing on Amazon Web Services Marketplace.

This parameter is optional for unversioned models, and does not apply to versioned models.

createModelPackage_clientToken :: Lens' CreateModelPackage (Maybe Text)

A unique token that guarantees that the call to this API is idempotent.

createModelPackage_customerMetadataProperties :: Lens' CreateModelPackage (Maybe (HashMap Text Text))

The metadata properties associated with the model package versions.

createModelPackage_domain :: Lens' CreateModelPackage (Maybe Text)

The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.

createModelPackage_driftCheckBaselines :: Lens' CreateModelPackage (Maybe DriftCheckBaselines)

Represents the drift check baselines that can be used when the model monitor is set using the model package. For more information, see the topic on Drift Detection against Previous Baselines in SageMaker Pipelines in the Amazon SageMaker Developer Guide.

createModelPackage_inferenceSpecification :: Lens' CreateModelPackage (Maybe 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.

createModelPackage_metadataProperties :: Lens' CreateModelPackage (Maybe MetadataProperties)

Undocumented member.

createModelPackage_modelApprovalStatus :: Lens' CreateModelPackage (Maybe 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.

createModelPackage_modelMetrics :: Lens' CreateModelPackage (Maybe ModelMetrics)

A structure that contains model metrics reports.

createModelPackage_modelPackageDescription :: Lens' CreateModelPackage (Maybe Text)

A description of the model package.

createModelPackage_modelPackageGroupName :: Lens' CreateModelPackage (Maybe Text)

The name or Amazon Resource Name (ARN) of the model package group that this model version belongs to.

This parameter is required for versioned models, and does not apply to unversioned models.

createModelPackage_modelPackageName :: Lens' CreateModelPackage (Maybe Text)

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.

createModelPackage_samplePayloadUrl :: Lens' CreateModelPackage (Maybe Text)

The Amazon Simple Storage Service (Amazon S3) path where the sample payload are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

createModelPackage_sourceAlgorithmSpecification :: Lens' CreateModelPackage (Maybe SourceAlgorithmSpecification)

Details about the algorithm that was used to create the model package.

createModelPackage_tags :: Lens' CreateModelPackage (Maybe [Tag])

A list of key value pairs associated with the model. For more information, see Tagging Amazon Web Services resources in the Amazon Web Services General Reference Guide.

createModelPackage_task :: Lens' CreateModelPackage (Maybe Text)

The machine learning task your model package accomplishes. Common machine learning tasks include object detection and image classification. The following tasks are supported by Inference Recommender: "IMAGE_CLASSIFICATION" | "OBJECT_DETECTION" | "TEXT_GENERATION" |"IMAGE_SEGMENTATION" | "FILL_MASK" | "CLASSIFICATION" | "REGRESSION" | "OTHER".

Specify "OTHER" if none of the tasks listed fit your use case.

createModelPackage_validationSpecification :: Lens' CreateModelPackage (Maybe ModelPackageValidationSpecification)

Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.

Destructuring the Response

data CreateModelPackageResponse

See: newCreateModelPackageResponse smart constructor.

Constructors

CreateModelPackageResponse'

Fields

• httpStatus :: Int

  The response's http status code.

• modelPackageArn :: Text

  The Amazon Resource Name (ARN) of the new model package.

Instances

Generic CreateModelPackageResponse

Defined in Amazonka.SageMaker.CreateModelPackage

Associated Types

type Rep CreateModelPackageResponse :: Type -> Type

Methods

from :: CreateModelPackageResponse -> Rep CreateModelPackageResponse x

to :: Rep CreateModelPackageResponse x -> CreateModelPackageResponse

Read CreateModelPackageResponse

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

readsPrec :: Int -> ReadS CreateModelPackageResponse

readList :: ReadS [CreateModelPackageResponse]

readPrec :: ReadPrec CreateModelPackageResponse

readListPrec :: ReadPrec [CreateModelPackageResponse]

Show CreateModelPackageResponse

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

showsPrec :: Int -> CreateModelPackageResponse -> ShowS

show :: CreateModelPackageResponse -> String

showList :: [CreateModelPackageResponse] -> ShowS

NFData CreateModelPackageResponse

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

rnf :: CreateModelPackageResponse -> ()

Eq CreateModelPackageResponse

Defined in Amazonka.SageMaker.CreateModelPackage

Methods

(==) :: CreateModelPackageResponse -> CreateModelPackageResponse -> Bool

(/=) :: CreateModelPackageResponse -> CreateModelPackageResponse -> Bool

type Rep CreateModelPackageResponse

Defined in Amazonka.SageMaker.CreateModelPackage

type Rep CreateModelPackageResponse = D1 ('MetaData "CreateModelPackageResponse" "Amazonka.SageMaker.CreateModelPackage" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "CreateModelPackageResponse'" 'PrefixI 'True) (S1 ('MetaSel ('Just "httpStatus") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int) :*: S1 ('MetaSel ('Just "modelPackageArn") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text)))

newCreateModelPackageResponse

Arguments

:: Int

$sel:httpStatus:CreateModelPackageResponse'

-> Text

CreateModelPackageResponse

-> CreateModelPackageResponse

Create a value of CreateModelPackageResponse with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:httpStatus:CreateModelPackageResponse', createModelPackageResponse_httpStatus - The response's http status code.

CreateModelPackageResponse, createModelPackageResponse_modelPackageArn - The Amazon Resource Name (ARN) of the new model package.

Response Lenses

createModelPackageResponse_httpStatus :: Lens' CreateModelPackageResponse Int

The response's http status code.

createModelPackageResponse_modelPackageArn :: Lens' CreateModelPackageResponse Text

The Amazon Resource Name (ARN) of the new model package.