KubernetesOnlineDeployment Class

Reference

Definition

Namespace:: Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401

Assembly:: Az.MachineLearningServices.private.dll

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

Properties specific to a KubernetesOnlineDeployment.

[System.ComponentModel.TypeConverter(typeof(Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.KubernetesOnlineDeploymentTypeConverter))]
public class KubernetesOnlineDeployment : Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.IKubernetesOnlineDeployment, Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Runtime.IValidates

[<System.ComponentModel.TypeConverter(typeof(Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.KubernetesOnlineDeploymentTypeConverter))>]
type KubernetesOnlineDeployment = class
    interface IKubernetesOnlineDeployment
    interface IJsonSerializable
    interface IOnlineDeploymentProperties
    interface IEndpointDeploymentPropertiesBase
    interface IValidates

Public Class KubernetesOnlineDeployment
Implements IKubernetesOnlineDeployment, IValidates

Inheritance: Object
KubernetesOnlineDeployment

Attributes: TypeConverterAttribute

Implements: IEndpointDeploymentPropertiesBase IKubernetesOnlineDeployment IOnlineDeploymentProperties IJsonSerializable IValidates

Constructors

KubernetesOnlineDeployment()

Creates an new KubernetesOnlineDeployment instance.

Properties

AppInsightsEnabled	If true, enables Application Insights logging.
CodeConfiguration	Code configuration for the endpoint deployment.
CodeConfigurationCodeId	ARM resource ID of the code asset.
CodeConfigurationScoringScript	[Required] The script to execute on startup. eg. "score.py"
ContainerResourceLimitCpu	Number of vCPUs request/limit for container. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/
ContainerResourceLimitGpu	Number of Nvidia GPU cards request/limit for container. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/
ContainerResourceLimitMemory	Memory size request/limit for container. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/
ContainerResourceRequestCpu	Number of vCPUs request/limit for container. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/
ContainerResourceRequestGpu	Number of Nvidia GPU cards request/limit for container. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/
ContainerResourceRequestMemory	Memory size request/limit for container. More info: https://kubernetes.io/docs/concepts/configuration/manage-compute-resources-container/
DataCollector	The mdc configuration, we disable mdc when it's null.
DataCollectorCollection	[Required] The collection configuration. Each collection has it own configuration to collect model data and the name of collection can be arbitrary string. Model data collector can be used for either payload logging or custom logging or both of them. Collection request and response are reserved for payload logging, others are for custom logging.
DataCollectorRequestLogging	The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional.
DataCollectorRollingRate	When model data is collected to blob storage, we need to roll the data to different path to avoid logging all of them in a single blob file. If the rolling rate is hour, all data will be collected in the blob path /yyyy/MM/dd/HH/. If it's day, all data will be collected in blob path /yyyy/MM/dd/. The other benefit of rolling path is that model monitoring ui is able to select a time range of data very quickly.
Description	Description of the endpoint deployment.
EgressPublicNetworkAccess	If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled.
EndpointComputeType	[Required] The compute type of the endpoint.
EnvironmentId	ARM resource ID or AssetId of the environment specification for the endpoint deployment.
EnvironmentVariable	Environment variables configuration for the deployment.
InstanceType	Compute instance type.
LivenessProbe	Liveness probe monitors the health of the container regularly.
LivenessProbeFailureThreshold	The number of failures to allow before returning an unhealthy status.
LivenessProbeInitialDelay	The delay before the first probe in ISO 8601 format.
LivenessProbePeriod	The length of time between probes in ISO 8601 format.
LivenessProbeSuccessThreshold	The number of successful probes before returning a healthy status.
LivenessProbeTimeout	The probe timeout in ISO 8601 format.
Model	The URI path to the model.
ModelMountPath	The path to mount the model in custom container.
Property	Property dictionary. Properties can be added, but not removed or altered.
ProvisioningState	Provisioning state for the endpoint deployment.
ReadinessProbe	Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe.
ReadinessProbeFailureThreshold	The number of failures to allow before returning an unhealthy status.
ReadinessProbeInitialDelay	The delay before the first probe in ISO 8601 format.
ReadinessProbePeriod	The length of time between probes in ISO 8601 format.
ReadinessProbeSuccessThreshold	The number of successful probes before returning a healthy status.
ReadinessProbeTimeout	The probe timeout in ISO 8601 format.
RequestLoggingCaptureHeader	For payload logging, we only collect payload by default. If customers also want to collect the specified headers, they can set them in captureHeaders so that backend will collect those headers along with payload.
RequestSetting	Request settings for the deployment.
RequestSettingMaxConcurrentRequestsPerInstance	The number of maximum concurrent requests per node allowed per deployment. Defaults to 1.
RequestSettingMaxQueueWait	(Deprecated for Managed Online Endpoints) The maximum amount of time a request will stay in the queue in ISO 8601 format. Defaults to 500ms. (Now increase `request_timeout_ms` to account for any networking/queue delays)
RequestSettingRequestTimeout	The scoring timeout in ISO 8601 format. Defaults to 5000ms.
ScaleSetting	Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment.
ScaleSettingScaleType	[Required] Type of deployment scaling algorithm

Methods

DeserializeFromDictionary(IDictionary)	Deserializes a IDictionary into an instance of KubernetesOnlineDeployment.
DeserializeFromPSObject(PSObject)	Deserializes a PSObject into an instance of KubernetesOnlineDeployment.
FromJson(JsonNode)	Deserializes a JsonNode into an instance of Microsoft.Azure.PowerShell.Cmdlets.MachineLearningServices.Models.Api20240401.IKubernetesOnlineDeployment.
FromJsonString(String)	Creates a new instance of KubernetesOnlineDeployment, deserializing the content from a json string.
ToJson(JsonObject, SerializationMode)	Serializes this instance of KubernetesOnlineDeployment into a JsonNode.
ToJsonString()	Serializes this instance to a json string.
ToString()
Validate(IEventListener)	Validates that this object meets the validation criteria.

Applies to

Share via