Package software.amazon.awssdk.services.sagemaker.model

Interface CreateModelPackageRequest.Builder

All Superinterfaces:
AwsRequest.Builder, Buildable, CopyableBuilder<CreateModelPackageRequest.Builder,CreateModelPackageRequest>, SageMakerRequest.Builder, SdkBuilder<CreateModelPackageRequest.Builder,CreateModelPackageRequest>, SdkPojo, SdkRequest.Builder
Enclosing class:
CreateModelPackageRequest
public static interface CreateModelPackageRequest.Builder extends SageMakerRequest.Builder, SdkPojo, CopyableBuilder<CreateModelPackageRequest.Builder,CreateModelPackageRequest>

  • Method Details

    • modelPackageName

      CreateModelPackageRequest.Builder modelPackageName(String 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • modelPackageGroupName

      CreateModelPackageRequest.Builder modelPackageGroupName(String 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • modelPackageDescription

      CreateModelPackageRequest.Builder modelPackageDescription(String modelPackageDescription)

      A description of the model package.

      Parameters:
      modelPackageDescription - A description of the model package.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • inferenceSpecification

      CreateModelPackageRequest.Builder inferenceSpecification(InferenceSpecification inferenceSpecification)

      Specifies details about inference jobs that you can run with models based on this model package, including the following information:

      • 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.

      Parameters:
      inferenceSpecification - Specifies details about inference jobs that you can run with models based on this model package, including the following information:

      • 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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • inferenceSpecification

      default CreateModelPackageRequest.Builder inferenceSpecification(Consumer<InferenceSpecification.Builder> inferenceSpecification)

      Specifies details about inference jobs that you can run with models based on this model package, including the following information:

      • 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.

      This is a convenience method that creates an instance of the InferenceSpecification.Builder avoiding the need to create one manually via InferenceSpecification.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to inferenceSpecification(InferenceSpecification).

      Parameters:
      inferenceSpecification - a consumer that will call methods on InferenceSpecification.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • validationSpecification

      CreateModelPackageRequest.Builder validationSpecification(ModelPackageValidationSpecification validationSpecification)

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

      Parameters:
      validationSpecification - Specifies configurations for one or more transform jobs that SageMaker runs to test the model package.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • validationSpecification

      default CreateModelPackageRequest.Builder validationSpecification(Consumer<ModelPackageValidationSpecification.Builder> validationSpecification)

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

      This is a convenience method that creates an instance of the ModelPackageValidationSpecification.Builder avoiding the need to create one manually via ModelPackageValidationSpecification.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to validationSpecification(ModelPackageValidationSpecification).

      Parameters:
      validationSpecification - a consumer that will call methods on ModelPackageValidationSpecification.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • sourceAlgorithmSpecification

      CreateModelPackageRequest.Builder sourceAlgorithmSpecification(SourceAlgorithmSpecification sourceAlgorithmSpecification)

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

      Parameters:
      sourceAlgorithmSpecification - Details about the algorithm that was used to create the model package.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • sourceAlgorithmSpecification

      default CreateModelPackageRequest.Builder sourceAlgorithmSpecification(Consumer<SourceAlgorithmSpecification.Builder> sourceAlgorithmSpecification)

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

      This is a convenience method that creates an instance of the SourceAlgorithmSpecification.Builder avoiding the need to create one manually via SourceAlgorithmSpecification.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to sourceAlgorithmSpecification(SourceAlgorithmSpecification).

      Parameters:
      sourceAlgorithmSpecification - a consumer that will call methods on SourceAlgorithmSpecification.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • certifyForMarketplace

      CreateModelPackageRequest.Builder certifyForMarketplace(Boolean 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • tags

      CreateModelPackageRequest.Builder tags(Collection<Tag> 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.

      If you supply ModelPackageGroupName, your model package belongs to the model group you specify and uses the tags associated with the model group. In this case, you cannot supply a tag argument.

      Parameters:
      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.

      If you supply ModelPackageGroupName, your model package belongs to the model group you specify and uses the tags associated with the model group. In this case, you cannot supply a tag argument.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • tags

      CreateModelPackageRequest.Builder tags(Tag... 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.

      If you supply ModelPackageGroupName, your model package belongs to the model group you specify and uses the tags associated with the model group. In this case, you cannot supply a tag argument.

      Parameters:
      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.

      If you supply ModelPackageGroupName, your model package belongs to the model group you specify and uses the tags associated with the model group. In this case, you cannot supply a tag argument.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • tags

      CreateModelPackageRequest.Builder tags(Consumer<Tag.Builder>... 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.

      If you supply ModelPackageGroupName, your model package belongs to the model group you specify and uses the tags associated with the model group. In this case, you cannot supply a tag argument.

      This is a convenience method that creates an instance of the Tag.Builder avoiding the need to create one manually via Tag.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to tags(List<Tag>).

      Parameters:
      tags - a consumer that will call methods on Tag.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • modelApprovalStatus

      CreateModelPackageRequest.Builder modelApprovalStatus(String 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • modelApprovalStatus

      CreateModelPackageRequest.Builder modelApprovalStatus(ModelApprovalStatus 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • metadataProperties

      CreateModelPackageRequest.Builder metadataProperties(MetadataProperties metadataProperties)
      Sets the value of the MetadataProperties property for this object.
      Parameters:
      metadataProperties - The new value for the MetadataProperties property for this object.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • metadataProperties

      default CreateModelPackageRequest.Builder metadataProperties(Consumer<MetadataProperties.Builder> metadataProperties)
      Sets the value of the MetadataProperties property for this object. This is a convenience method that creates an instance of the MetadataProperties.Builder avoiding the need to create one manually via MetadataProperties.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to metadataProperties(MetadataProperties).

      Parameters:
      metadataProperties - a consumer that will call methods on MetadataProperties.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • modelMetrics

      CreateModelPackageRequest.Builder modelMetrics(ModelMetrics modelMetrics)

      A structure that contains model metrics reports.

      Parameters:
      modelMetrics - A structure that contains model metrics reports.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • modelMetrics

      default CreateModelPackageRequest.Builder modelMetrics(Consumer<ModelMetrics.Builder> modelMetrics)

      A structure that contains model metrics reports.

      This is a convenience method that creates an instance of the ModelMetrics.Builder avoiding the need to create one manually via ModelMetrics.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to modelMetrics(ModelMetrics).

      Parameters:
      modelMetrics - a consumer that will call methods on ModelMetrics.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • clientToken

      CreateModelPackageRequest.Builder clientToken(String clientToken)

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

      Parameters:
      clientToken - A unique token that guarantees that the call to this API is idempotent.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • domain

      CreateModelPackageRequest.Builder domain(String domain)

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

      Parameters:
      domain - The machine learning domain of your model package and its components. Common machine learning domains include computer vision and natural language processing.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • task

      CreateModelPackageRequest.Builder task(String 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • samplePayloadUrl

      CreateModelPackageRequest.Builder samplePayloadUrl(String samplePayloadUrl)

      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). This archive can hold multiple files that are all equally used in the load test. Each file in the archive must satisfy the size constraints of the InvokeEndpoint call.

      Parameters:
      samplePayloadUrl - 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). This archive can hold multiple files that are all equally used in the load test. Each file in the archive must satisfy the size constraints of the InvokeEndpoint call.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • customerMetadataProperties

      CreateModelPackageRequest.Builder customerMetadataProperties(Map<String,String> customerMetadataProperties)

      The metadata properties associated with the model package versions.

      Parameters:
      customerMetadataProperties - The metadata properties associated with the model package versions.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • driftCheckBaselines

      CreateModelPackageRequest.Builder driftCheckBaselines(DriftCheckBaselines 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • driftCheckBaselines

      default CreateModelPackageRequest.Builder driftCheckBaselines(Consumer<DriftCheckBaselines.Builder> 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.

      This is a convenience method that creates an instance of the DriftCheckBaselines.Builder avoiding the need to create one manually via DriftCheckBaselines.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to driftCheckBaselines(DriftCheckBaselines).

      Parameters:
      driftCheckBaselines - a consumer that will call methods on DriftCheckBaselines.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • additionalInferenceSpecifications

      CreateModelPackageRequest.Builder additionalInferenceSpecifications(Collection<AdditionalInferenceSpecificationDefinition> 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • additionalInferenceSpecifications

      CreateModelPackageRequest.Builder additionalInferenceSpecifications(AdditionalInferenceSpecificationDefinition... 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.

      Parameters:
      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.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • additionalInferenceSpecifications

      CreateModelPackageRequest.Builder additionalInferenceSpecifications(Consumer<AdditionalInferenceSpecificationDefinition.Builder>... 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.

      This is a convenience method that creates an instance of the AdditionalInferenceSpecificationDefinition.Builder avoiding the need to create one manually via AdditionalInferenceSpecificationDefinition.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to additionalInferenceSpecifications(List<AdditionalInferenceSpecificationDefinition>).

      Parameters:
      additionalInferenceSpecifications - a consumer that will call methods on AdditionalInferenceSpecificationDefinition.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • skipModelValidation

      CreateModelPackageRequest.Builder skipModelValidation(String skipModelValidation)

      Indicates if you want to skip model validation.

      Parameters:
      skipModelValidation - Indicates if you want to skip model validation.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • skipModelValidation

      CreateModelPackageRequest.Builder skipModelValidation(SkipModelValidation skipModelValidation)

      Indicates if you want to skip model validation.

      Parameters:
      skipModelValidation - Indicates if you want to skip model validation.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • sourceUri

      CreateModelPackageRequest.Builder sourceUri(String sourceUri)

      The URI of the source for the model package. If you want to clone a model package, set it to the model package Amazon Resource Name (ARN). If you want to register a model, set it to the model ARN.

      Parameters:
      sourceUri - The URI of the source for the model package. If you want to clone a model package, set it to the model package Amazon Resource Name (ARN). If you want to register a model, set it to the model ARN.
      Returns:
      Returns a reference to this object so that method calls can be chained together.

    • overrideConfiguration

      CreateModelPackageRequest.Builder overrideConfiguration(AwsRequestOverrideConfiguration overrideConfiguration)
      Description copied from interface: AwsRequest.Builder
      Add an optional request override configuration.
      Specified by:
      overrideConfiguration in interface AwsRequest.Builder
      Parameters:
      overrideConfiguration - The override configuration.
      Returns:
      This object for method chaining.

    • overrideConfiguration

      CreateModelPackageRequest.Builder overrideConfiguration(Consumer<AwsRequestOverrideConfiguration.Builder> builderConsumer)
      Description copied from interface: AwsRequest.Builder
      Add an optional request override configuration.
      Specified by:
      overrideConfiguration in interface AwsRequest.Builder
      Parameters:
      builderConsumer - A Consumer to which an empty AwsRequestOverrideConfiguration.Builder will be given.
      Returns:
      This object for method chaining.