Class PartialBatchDeployment


  • public final class PartialBatchDeployment
    extends Object
    Mutable batch inference settings per deployment.
    • Constructor Detail

      • PartialBatchDeployment

        public PartialBatchDeployment()
    • Method Detail

      • codeConfiguration

        public PartialCodeConfiguration codeConfiguration()
        Get the codeConfiguration property: Code configuration for the endpoint deployment.
        Returns:
        the codeConfiguration value.
      • withCodeConfiguration

        public PartialBatchDeployment withCodeConfiguration​(PartialCodeConfiguration codeConfiguration)
        Set the codeConfiguration property: Code configuration for the endpoint deployment.
        Parameters:
        codeConfiguration - the codeConfiguration value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • compute

        public String compute()
        Get the compute property: Compute binding definition.
        Returns:
        the compute value.
      • withCompute

        public PartialBatchDeployment withCompute​(String compute)
        Set the compute property: Compute binding definition.
        Parameters:
        compute - the compute value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • description

        public String description()
        Get the description property: Description of the endpoint deployment.
        Returns:
        the description value.
      • withDescription

        public PartialBatchDeployment withDescription​(String description)
        Set the description property: Description of the endpoint deployment.
        Parameters:
        description - the description value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • environmentId

        public String environmentId()
        Get the environmentId property: ARM resource ID of the environment specification for the endpoint deployment.
        Returns:
        the environmentId value.
      • withEnvironmentId

        public PartialBatchDeployment withEnvironmentId​(String environmentId)
        Set the environmentId property: ARM resource ID of the environment specification for the endpoint deployment.
        Parameters:
        environmentId - the environmentId value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • environmentVariables

        public Map<String,​String> environmentVariables()
        Get the environmentVariables property: Environment variables configuration for the deployment.
        Returns:
        the environmentVariables value.
      • withEnvironmentVariables

        public PartialBatchDeployment withEnvironmentVariables​(Map<String,​String> environmentVariables)
        Set the environmentVariables property: Environment variables configuration for the deployment.
        Parameters:
        environmentVariables - the environmentVariables value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • errorThreshold

        public Integer errorThreshold()
        Get the errorThreshold property: Error threshold, if the error count for the entire input goes above this value, the batch inference will be aborted. Range is [-1, int.MaxValue]. For FileDataset, this value is the count of file failures. For TabularDataset, this value is the count of record failures. If set to -1 (the lower bound), all failures during batch inference will be ignored.
        Returns:
        the errorThreshold value.
      • withErrorThreshold

        public PartialBatchDeployment withErrorThreshold​(Integer errorThreshold)
        Set the errorThreshold property: Error threshold, if the error count for the entire input goes above this value, the batch inference will be aborted. Range is [-1, int.MaxValue]. For FileDataset, this value is the count of file failures. For TabularDataset, this value is the count of record failures. If set to -1 (the lower bound), all failures during batch inference will be ignored.
        Parameters:
        errorThreshold - the errorThreshold value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • loggingLevel

        public BatchLoggingLevel loggingLevel()
        Get the loggingLevel property: Logging level for batch inference operation.
        Returns:
        the loggingLevel value.
      • withLoggingLevel

        public PartialBatchDeployment withLoggingLevel​(BatchLoggingLevel loggingLevel)
        Set the loggingLevel property: Logging level for batch inference operation.
        Parameters:
        loggingLevel - the loggingLevel value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • maxConcurrencyPerInstance

        public Integer maxConcurrencyPerInstance()
        Get the maxConcurrencyPerInstance property: Indicates number of processes per instance.
        Returns:
        the maxConcurrencyPerInstance value.
      • withMaxConcurrencyPerInstance

        public PartialBatchDeployment withMaxConcurrencyPerInstance​(Integer maxConcurrencyPerInstance)
        Set the maxConcurrencyPerInstance property: Indicates number of processes per instance.
        Parameters:
        maxConcurrencyPerInstance - the maxConcurrencyPerInstance value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • miniBatchSize

        public Long miniBatchSize()
        Get the miniBatchSize property: Size of the mini-batch passed to each batch invocation. For FileDataset, this is the number of files per mini-batch. For TabularDataset, this is the size of the records in bytes, per mini-batch.
        Returns:
        the miniBatchSize value.
      • withMiniBatchSize

        public PartialBatchDeployment withMiniBatchSize​(Long miniBatchSize)
        Set the miniBatchSize property: Size of the mini-batch passed to each batch invocation. For FileDataset, this is the number of files per mini-batch. For TabularDataset, this is the size of the records in bytes, per mini-batch.
        Parameters:
        miniBatchSize - the miniBatchSize value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • model

        public PartialAssetReferenceBase model()
        Get the model property: Reference to the model asset for the endpoint deployment.
        Returns:
        the model value.
      • withModel

        public PartialBatchDeployment withModel​(PartialAssetReferenceBase model)
        Set the model property: Reference to the model asset for the endpoint deployment.
        Parameters:
        model - the model value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • outputAction

        public BatchOutputAction outputAction()
        Get the outputAction property: Indicates how the output will be organized.
        Returns:
        the outputAction value.
      • withOutputAction

        public PartialBatchDeployment withOutputAction​(BatchOutputAction outputAction)
        Set the outputAction property: Indicates how the output will be organized.
        Parameters:
        outputAction - the outputAction value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • outputFileName

        public String outputFileName()
        Get the outputFileName property: Customized output file name for append_row output action.
        Returns:
        the outputFileName value.
      • withOutputFileName

        public PartialBatchDeployment withOutputFileName​(String outputFileName)
        Set the outputFileName property: Customized output file name for append_row output action.
        Parameters:
        outputFileName - the outputFileName value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • properties

        public Map<String,​String> properties()
        Get the properties property: Property dictionary. Properties can be added, but not removed or altered.
        Returns:
        the properties value.
      • withProperties

        public PartialBatchDeployment withProperties​(Map<String,​String> properties)
        Set the properties property: Property dictionary. Properties can be added, but not removed or altered.
        Parameters:
        properties - the properties value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • retrySettings

        public PartialBatchRetrySettings retrySettings()
        Get the retrySettings property: Retry Settings for the batch inference operation.
        Returns:
        the retrySettings value.
      • withRetrySettings

        public PartialBatchDeployment withRetrySettings​(PartialBatchRetrySettings retrySettings)
        Set the retrySettings property: Retry Settings for the batch inference operation.
        Parameters:
        retrySettings - the retrySettings value to set.
        Returns:
        the PartialBatchDeployment object itself.
      • validate

        public void validate()
        Validates the instance.
        Throws:
        IllegalArgumentException - thrown if the instance is not valid.