New-AzMLWorkspaceOnlineDeployment
Create or update Inference Endpoint Deployment (asynchronous).
Syntax
Default (Default)
New-AzMLWorkspaceOnlineDeployment
-EndpointName <String>
-Name <String>
-ResourceGroupName <String>
-WorkspaceName <String>
[-SubscriptionId <String>]
-EndpointComputeType <EndpointComputeType>
-Location <String>
[-AppInsightsEnabled]
[-CodeId <String>]
[-CodeScoringScript <String>]
[-DataCollectorCollection <Hashtable>]
[-DataCollectorRollingRate <RollingRateType>]
[-Description <String>]
[-EgressPublicNetworkAccess <EgressPublicNetworkAccessType>]
[-EndpointDeploymentPropertiesBaseProperty <Hashtable>]
[-EnvironmentId <String>]
[-EnvironmentVariable <Hashtable>]
[-IdentityType <ManagedServiceIdentityType>]
[-IdentityUserAssigned <Hashtable>]
[-InstanceType <String>]
[-Kind <String>]
[-LivenessProbeFailureThreshold <Int32>]
[-LivenessProbeInitialDelay <TimeSpan>]
[-LivenessProbePeriod <TimeSpan>]
[-LivenessProbeSuccessThreshold <Int32>]
[-LivenessProbeTimeout <TimeSpan>]
[-Model <String>]
[-ModelMountPath <String>]
[-ReadinessProbeFailureThreshold <Int32>]
[-ReadinessProbeInitialDelay <TimeSpan>]
[-ReadinessProbePeriod <TimeSpan>]
[-ReadinessProbeSuccessThreshold <Int32>]
[-ReadinessProbeTimeout <TimeSpan>]
[-RequestLoggingCaptureHeader <String[]>]
[-RequestMaxConcurrentPerInstance <Int32>]
[-RequestMaxQueueWait <TimeSpan>]
[-RequestTimeout <TimeSpan>]
[-ScaleType <ScaleType>]
[-SkuCapacity <Int32>]
[-SkuFamily <String>]
[-SkuName <String>]
[-SkuSize <String>]
[-SkuTier <SkuTier>]
[-Tag <Hashtable>]
[-DefaultProfile <PSObject>]
[-AsJob]
[-NoWait]
[-WhatIf]
[-Confirm]
[<CommonParameters>]
Description
Create or update Inference Endpoint Deployment (asynchronous).
Examples
Example 1: Create or update Inference Endpoint Deployment (asynchronous)
New-AzMLWorkspaceOnlineDeployment -ResourceGroupName ml-rg-test -WorkspaceName mlworkspace-cli01 -EndpointName online-pwsh01 -Name blue -Location "eastus" -EndpointComputeType 'Managed' `
-CodeId "/subscriptions/9e223dbe-3399-4e19-88eb-0975f02ac87f/resourceGroups/ml-rg-test/providers/Microsoft.MachineLearningServices/workspaces/mlworkspace-cli01/codes/787fc793-1ac7-414e-a035-7248767b7b23/versions/1" -CodeScoringScript "score.py" `
-EnvironmentId "/subscriptions/9e223dbe-3399-4e19-88eb-0975f02ac87f/resourceGroups/ml-rg-test/providers/Microsoft.MachineLearningServices/workspaces/mlworkspace-cli01/environments/CliV2AnonymousEnvironment/versions/8a424b013f5b0177929a1697d772da41" `
-Model "/subscriptions/9e223dbe-3399-4e19-88eb-0975f02ac87f/resourceGroups/ml-rg-test/providers/Microsoft.MachineLearningServices/workspaces/mlworkspace-cli01/models/a99089c5-23a6-4431-9ecd-37c70f01c9bc/versions/1" -InstanceType "Standard_F2s_v2" `
-SkuName "Default" -SkuCapacity 1
Location Name SystemDataCreatedAt SystemDataCreatedBy SystemDataCreatedByType SystemDataLastModifiedAt SystemDataLastModifiedBy SystemDataLastModifiedByType Kind ResourceGroupName
-------- ---- ------------------- ------------------- ----------------------- ------------------------ ------------------------ ---------------------------- ---- -----------------
eastus blue 5/19/2022 2:52:06 AM UserName (Example) 5/19/2022 2:52:06 AM Managed ml-rg-test
Create or update Inference Endpoint Deployment (asynchronous)
Parameters
-AppInsightsEnabled
If true, enables Application Insights logging.
Parameter properties
Type: SwitchParameter
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-AsJob
Run the command as a job
Parameter properties
Type: SwitchParameter
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-CodeId
ARM resource ID of the code asset.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-CodeScoringScript
[Required] The script to execute on startup.
eg.
"score.py"
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Confirm
Prompts you for confirmation before running the cmdlet.
Parameter properties
Type: SwitchParameter
Default value: None Supports wildcards: False DontShow: False Aliases: cf
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-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.
Parameter properties
Type: Hashtable
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-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.
Parameter properties
Type: RollingRateType
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-DefaultProfile
The DefaultProfile parameter is not functional.
Use the SubscriptionId parameter when available if executing the cmdlet against a different subscription.
Parameter properties
Type: PSObject
Default value: None Supports wildcards: False DontShow: False Aliases: AzureRMContext, AzureCredential
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Description
Description of the endpoint deployment.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-EgressPublicNetworkAccess
If Enabled, allow egress public network access.
If Disabled, this will create secure egress.
Default: Enabled.
Parameter properties
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-EndpointComputeType
[Required] The compute type of the endpoint.
Parameter properties
Parameter sets
(All)
Position: Named Mandatory: True Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-EndpointDeploymentPropertiesBaseProperty
Property dictionary.
Properties can be added, but not removed or altered.
Parameter properties
Type: Hashtable
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-EndpointName
Inference endpoint name.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: True Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-EnvironmentId
ARM resource ID or AssetId of the environment specification for the endpoint deployment.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-EnvironmentVariable
Environment variables configuration for the deployment.
Parameter properties
Type: Hashtable
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-IdentityType
Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed).
Parameter properties
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-IdentityUserAssigned
The set of user assigned identities associated with the resource.
The userAssignedIdentities dictionary keys will be ARM resource ids in the form: '/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.ManagedIdentity/userAssignedIdentities/{identityName}.
The dictionary values can be empty objects ({}) in requests.
Parameter properties
Type: Hashtable
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-InstanceType
Compute instance type.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Kind
Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-LivenessProbeFailureThreshold
The number of failures to allow before returning an unhealthy status.
Parameter properties
Type: Int32
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-LivenessProbeInitialDelay
The delay before the first probe in ISO 8601 format.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-LivenessProbePeriod
The length of time between probes in ISO 8601 format.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-LivenessProbeSuccessThreshold
The number of successful probes before returning a healthy status.
Parameter properties
Type: Int32
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-LivenessProbeTimeout
The probe timeout in ISO 8601 format.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Location
The geo-location where the resource lives
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: True Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Model
The URI path to the model.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ModelMountPath
The path to mount the model in custom container.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Name
Inference Endpoint Deployment name.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: True Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-NoWait
Run the command asynchronously
Parameter properties
Type: SwitchParameter
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ReadinessProbeFailureThreshold
The number of failures to allow before returning an unhealthy status.
Parameter properties
Type: Int32
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ReadinessProbeInitialDelay
The delay before the first probe in ISO 8601 format.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ReadinessProbePeriod
The length of time between probes in ISO 8601 format.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ReadinessProbeSuccessThreshold
The number of successful probes before returning a healthy status.
Parameter properties
Type: Int32
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ReadinessProbeTimeout
The probe timeout in ISO 8601 format.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
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.
Type: String [ ]
Default value: None Supports wildcards: False DontShow: False
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-RequestMaxConcurrentPerInstance
The number of maximum concurrent requests per node allowed per deployment.
Defaults to 1.
Parameter properties
Type: Int32
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-RequestMaxQueueWait
(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)
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-RequestTimeout
The scoring timeout in ISO 8601 format.Defaults to 5000ms.
Parameter properties
Type: TimeSpan
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ResourceGroupName
The name of the resource group.
The name is case insensitive.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: True Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-ScaleType
[Required] Type of deployment scaling algorithm
Parameter properties
Type: ScaleType
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-SkuCapacity
If the SKU supports scale out/in then the capacity integer should be included.
If scale out/in is not possible for the resource this may be omitted.
Parameter properties
Type: Int32
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-SkuFamily
If the service has different generations of hardware, for the same SKU, then that can be captured here.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-SkuName
The name of the SKU.
Ex - P3.
It is typically a letter+number code
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-SkuSize
The SKU size.
When the name field is the combination of tier and some other value, this would be the standalone code.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-SkuTier
This field is required to be implemented by the Resource Provider if the service has more than one tier, but is not required on a PUT.
Parameter properties
Type: SkuTier
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-SubscriptionId
The ID of the target subscription.
Parameter properties
Type: String
Default value: (Get-AzContext).Subscription.Id Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-Tag
Resource tags.
Parameter properties
Type: Hashtable
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-WhatIf
Shows what would happen if the cmdlet runs.
The cmdlet is not run.
Parameter properties
Type: SwitchParameter
Default value: None Supports wildcards: False DontShow: False Aliases: wi
Parameter sets
(All)
Position: Named Mandatory: False Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
-WorkspaceName
Name of Azure Machine Learning workspace.
Parameter properties
Type: String
Default value: None Supports wildcards: False DontShow: False
Parameter sets
(All)
Position: Named Mandatory: True Value from pipeline: False Value from pipeline by property name: False Value from remaining arguments: False
CommonParameters
This cmdlet supports the common parameters: -Debug, -ErrorAction, -ErrorVariable,
-InformationAction, -InformationVariable, -OutBuffer, -OutVariable, -PipelineVariable,
-ProgressAction, -Verbose, -WarningAction, and -WarningVariable. For more information, see
about_CommonParameters .
Outputs
