Package software.amazon.awssdk.services.neptunedata.model

Interface CreateMlEndpointRequest.Builder

    • Method Detail

      • id

        CreateMlEndpointRequest.Builder id​(String id)

        A unique identifier for the new inference endpoint. The default is an autogenerated timestamped name.

        Parameters:
        id - A unique identifier for the new inference endpoint. The default is an autogenerated timestamped name.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • mlModelTrainingJobId

        CreateMlEndpointRequest.Builder mlModelTrainingJobId​(String mlModelTrainingJobId)

        The job Id of the completed model-training job that has created the model that the inference endpoint will point to. You must supply either the mlModelTrainingJobId or the mlModelTransformJobId.

        Parameters:
        mlModelTrainingJobId - The job Id of the completed model-training job that has created the model that the inference endpoint will point to. You must supply either the mlModelTrainingJobId or the mlModelTransformJobId.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • mlModelTransformJobId

        CreateMlEndpointRequest.Builder mlModelTransformJobId​(String mlModelTransformJobId)

        The job Id of the completed model-transform job. You must supply either the mlModelTrainingJobId or the mlModelTransformJobId.

        Parameters:
        mlModelTransformJobId - The job Id of the completed model-transform job. You must supply either the mlModelTrainingJobId or the mlModelTransformJobId.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • update

        CreateMlEndpointRequest.Builder update​(Boolean update)

        If set to true, update indicates that this is an update request. The default is false. You must supply either the mlModelTrainingJobId or the mlModelTransformJobId.

        Parameters:
        update - If set to true, update indicates that this is an update request. The default is false. You must supply either the mlModelTrainingJobId or the mlModelTransformJobId.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • neptuneIamRoleArn

        CreateMlEndpointRequest.Builder neptuneIamRoleArn​(String neptuneIamRoleArn)

        The ARN of an IAM role providing Neptune access to SageMaker and Amazon S3 resources. This must be listed in your DB cluster parameter group or an error will be thrown.

        Parameters:
        neptuneIamRoleArn - The ARN of an IAM role providing Neptune access to SageMaker and Amazon S3 resources. This must be listed in your DB cluster parameter group or an error will be thrown.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • modelName

        CreateMlEndpointRequest.Builder modelName​(String modelName)

        Model type for training. By default the Neptune ML model is automatically based on the modelType used in data processing, but you can specify a different model type here. The default is rgcn for heterogeneous graphs and kge for knowledge graphs. The only valid value for heterogeneous graphs is rgcn. Valid values for knowledge graphs are: kge, transe, distmult, and rotate.

        Parameters:
        modelName - Model type for training. By default the Neptune ML model is automatically based on the modelType used in data processing, but you can specify a different model type here. The default is rgcn for heterogeneous graphs and kge for knowledge graphs. The only valid value for heterogeneous graphs is rgcn. Valid values for knowledge graphs are: kge, transe, distmult, and rotate.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • instanceType

        CreateMlEndpointRequest.Builder instanceType​(String instanceType)

        The type of Neptune ML instance to use for online servicing. The default is ml.m5.xlarge. Choosing the ML instance for an inference endpoint depends on the task type, the graph size, and your budget.

        Parameters:
        instanceType - The type of Neptune ML instance to use for online servicing. The default is ml.m5.xlarge. Choosing the ML instance for an inference endpoint depends on the task type, the graph size, and your budget.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • instanceCount

        CreateMlEndpointRequest.Builder instanceCount​(Integer instanceCount)

        The minimum number of Amazon EC2 instances to deploy to an endpoint for prediction. The default is 1

        Parameters:
        instanceCount - The minimum number of Amazon EC2 instances to deploy to an endpoint for prediction. The default is 1
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • volumeEncryptionKMSKey

        CreateMlEndpointRequest.Builder volumeEncryptionKMSKey​(String volumeEncryptionKMSKey)

        The Amazon Key Management Service (Amazon KMS) key that SageMaker uses to encrypt data on the storage volume attached to the ML compute instances that run the training job. The default is None.

        Parameters:
        volumeEncryptionKMSKey - The Amazon Key Management Service (Amazon KMS) key that SageMaker uses to encrypt data on the storage volume attached to the ML compute instances that run the training job. The default is None.
        Returns:
        Returns a reference to this object so that method calls can be chained together.