pulumi-azure-native-kotlin/com.pulumi.azurenative.machinelearningservices.kotlin.inputs/BatchDeploymentArgs

BatchDeploymentArgs

data class BatchDeploymentArgs(val codeConfiguration: Output<CodeConfigurationArgs>? = null, val compute: Output<ComputeConfigurationArgs>? = null, val description: Output<String>? = null, val environmentId: Output<String>? = null, val environmentVariables: Output<Map<String, String>>? = null, val errorThreshold: Output<Int>? = null, val loggingLevel: Output<Either<String, BatchLoggingLevel>>? = null, val miniBatchSize: Output<Double>? = null, val model: Output<Any>? = null, val outputConfiguration: Output<BatchOutputConfigurationArgs>? = null, val partitionKeys: Output<List<String>>? = null, val properties: Output<Map<String, String>>? = null, val retrySettings: Output<BatchRetrySettingsArgs>? = null) : ConvertibleToJava<BatchDeploymentArgs>

Batch inference settings per deployment.

Constructors

Link copied to clipboard
fun BatchDeploymentArgs(codeConfiguration: Output<CodeConfigurationArgs>? = null, compute: Output<ComputeConfigurationArgs>? = null, description: Output<String>? = null, environmentId: Output<String>? = null, environmentVariables: Output<Map<String, String>>? = null, errorThreshold: Output<Int>? = null, loggingLevel: Output<Either<String, BatchLoggingLevel>>? = null, miniBatchSize: Output<Double>? = null, model: Output<Any>? = null, outputConfiguration: Output<BatchOutputConfigurationArgs>? = null, partitionKeys: Output<List<String>>? = null, properties: Output<Map<String, String>>? = null, retrySettings: Output<BatchRetrySettingsArgs>? = null)

Functions

Link copied to clipboard
open override fun toJava(): BatchDeploymentArgs

Properties

Link copied to clipboard
val codeConfiguration: Output<CodeConfigurationArgs>? = null

Code configuration for the endpoint deployment.

Link copied to clipboard
val compute: Output<ComputeConfigurationArgs>? = null

Configuration for compute binding.

Link copied to clipboard
val description: Output<String>? = null

Description of the endpoint deployment.

Link copied to clipboard
val environmentId: Output<String>? = null

ARM resource ID of the environment specification for the endpoint deployment.

Link copied to clipboard
val environmentVariables: Output<Map<String, String>>? = null

Environment variables configuration for the deployment.

Link copied to clipboard
val errorThreshold: Output<Int>? = null

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.

Link copied to clipboard
val loggingLevel: Output<Either<String, BatchLoggingLevel>>? = null

Logging level for batch inference operation.

Link copied to clipboard
val miniBatchSize: Output<Double>? = null

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.

Link copied to clipboard
val model: Output<Any>? = null

Reference to the model asset for the endpoint deployment.

Link copied to clipboard
val outputConfiguration: Output<BatchOutputConfigurationArgs>? = null

Output configuration for the batch inference operation.

Link copied to clipboard
val partitionKeys: Output<List<String>>? = null

Partition keys list used for Named partitioning.

Link copied to clipboard
val properties: Output<Map<String, String>>? = null

Property dictionary. Properties can be added, but not removed or altered.

Link copied to clipboard
val retrySettings: Output<BatchRetrySettingsArgs>? = null

Retry Settings for the batch inference operation.