Microsoft.MachineLearningServices (stable:2024-10-01)

2025/02/26 • 4 updated methods

OnlineDeployments_List (updated)
Description :  List Inference Endpoint Deployments.
Reference :  Link ¶

⚶ Changes

{
  "#id": "OnlineDeployments_List",
  "$responses": {
    "200": {
      "$properties": {
        "value": {
          "$properties": {
            "properties": [
              {
                "@added_9241ed0d4c8d48fea4ebb571671435a5": {
                  "#name": "startupProbe",
                  "Description": "This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes.",
                  "Required": false,
                  "Type": "object",
                  "$properties": [
                    {
                      "#name": "failureThreshold",
                      "Description": "The number of failures to allow before returning an unhealthy status.",
                      "Format": "int32",
                      "Required": false,
                      "Type": "integer"
                    },
                    {
                      "#name": "initialDelay",
                      "Description": "The delay before the first probe in ISO 8601 format.",
                      "Format": "duration",
                      "Required": false,
                      "Type": "string"
                    },
                    {
                      "#name": "period",
                      "Description": "The length of time between probes in ISO 8601 format.",
                      "Format": "duration",
                      "Required": false,
                      "Type": "string"
                    },
                    {
                      "#name": "successThreshold",
                      "Description": "The number of successful probes before returning a healthy status.",
                      "Format": "int32",
                      "Required": false,
                      "Type": "integer"
                    },
                    {
                      "#name": "timeout",
                      "Description": "The probe timeout in ISO 8601 format.",
                      "Format": "duration",
                      "Required": false,
                      "Type": "string"
                    }
                  ]
                }
              }
            ]
          }
        }
      }
    }
  }
}

⚼ Request

GET:  /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/onlineEndpoints/{endpointName}/deployments
{
subscriptionId:
{
Description: The ID of the target subscription. ,
Required: True ,
}
string ,
resourceGroupName:
{
Description: The name of the resource group. The name is case insensitive. ,
Required: True ,
}
string ,
workspaceName:
{
Description: Name of Azure Machine Learning workspace. ,
Required: True ,
}
string ,
endpointName:
{
Description: Inference endpoint name. ,
Required: True ,
}
string ,
api-version:
{
Description: The API version to use for this operation. ,
Required: True ,
}
string ,
$orderBy:
{
Description: Ordering of list. ,
Required: False ,
}
string ,
$top:
{
Description: Top of list. ,
Format: int32 ,
Required: False ,
}
integer ,
$skip:
{
Description: Continuation token for pagination. ,
Required: False ,
}
string ,
}

⚐ Response (200)

{
nextLink:
{
Description: The link to the next page of OnlineDeployment objects. If null, there are no additional pages. ,
Required: False ,
}
string ,
value:
{
Description: An array of objects of type OnlineDeployment. ,
Required: False ,
}
[
{
identity:
{
Description: Managed service identity (system assigned and/or user assigned identities) ,
Required: False ,
}
{
principalId:
{
Description: The service principal ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
tenantId:
{
Description: The tenant ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
type:
{
Description: Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). ,
Enum:
{
None: No description available. ,
SystemAssigned: No description available. ,
UserAssigned: No description available. ,
SystemAssigned,UserAssigned: No description available. ,
}
,
Required: True ,
}
enum ,
userAssignedIdentities:
{
Description: 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. ,
Required: False ,
}
object ,
}
,
kind:
{
Description: Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. ,
Required: False ,
}
string ,
properties:
{
Description: [Required] Additional attributes of the entity. ,
Required: True ,
}
{
appInsightsEnabled:
{
Description: If true, enables Application Insights logging. ,
Required: False ,
}
boolean ,
dataCollector:
{
Description: The mdc configuration, we disable mdc when it's null. ,
Required: False ,
}
{
collections:
{
Description: [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. ,
Required: True ,
}
object ,
requestLogging:
{
Description: The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional. ,
Required: False ,
}
{
captureHeaders:
{
Description: 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. ,
Required: False ,
}
[
string ,
]
,
}
,
rollingRate:
{
Description: 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. ,
Enum:
{
Year: No description available. ,
Month: No description available. ,
Day: No description available. ,
Hour: No description available. ,
Minute: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
egressPublicNetworkAccess:
{
Description: If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled. ,
Enum:
{
Enabled: No description available. ,
Disabled: No description available. ,
}
,
Required: False ,
}
enum ,
endpointComputeType:
{
Description: [Required] The compute type of the endpoint. ,
Enum:
{
Managed: No description available. ,
Kubernetes: No description available. ,
AzureMLCompute: No description available. ,
}
,
Required: True ,
}
enum ,
instanceType:
{
Description: Compute instance type. Default: Standard_F4s_v2. ,
Required: False ,
}
string ,
livenessProbe:
{
Description: Liveness probe monitors the health of the container regularly. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
model:
{
Description: The URI path to the model. ,
Required: False ,
}
string ,
modelMountPath:
{
Description: The path to mount the model in custom container. ,
Required: False ,
}
string ,
provisioningState:
{
Description: Provisioning state for the endpoint deployment. ,
Enum:
{
Creating: No description available. ,
Deleting: No description available. ,
Scaling: No description available. ,
Updating: No description available. ,
Succeeded: No description available. ,
Failed: No description available. ,
Canceled: No description available. ,
}
,
Required: False ,
}
enum ,
readinessProbe:
{
Description: Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
startupProbe:
{
Description: This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
requestSettings:
{
Description: Request settings for the deployment. ,
Required: False ,
}
{
maxConcurrentRequestsPerInstance:
{
Description: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. ,
Format: int32 ,
Required: False ,
}
integer ,
maxQueueWait:
{
Description: (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) ,
Format: duration ,
Required: False ,
}
string ,
requestTimeout:
{
Description: The scoring timeout in ISO 8601 format. Defaults to 5000ms. ,
Format: duration ,
Required: False ,
}
string ,
}
,
scaleSettings:
{
Description: Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment. ,
Required: False ,
}
{
scaleType:
{
Description: [Required] Type of deployment scaling algorithm ,
Enum:
{
Default: No description available. ,
TargetUtilization: No description available. ,
}
,
Required: True ,
}
enum ,
}
,
}
,
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code ,
Required: True ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
}
,
}
,
]
,
}

⚐ Response (default)

{
error:
{
Description: The error object. ,
Required: False ,
}
{
code:
{
Description: The error code. ,
Required: False ,
}
string ,
message:
{
Description: The error message. ,
Required: False ,
}
string ,
target:
{
Description: The error target. ,
Required: False ,
}
string ,
details:
{
Description: The error details. ,
Required: False ,
}
[
string ,
]
,
additionalInfo:
{
Description: The error additional info. ,
Required: False ,
}
[
{
type:
{
Description: The additional info type. ,
Required: False ,
}
string ,
info:
{
Description: The additional info. ,
Required: False ,
}
object ,
}
,
]
,
}
,
}
OnlineDeployments_Get (updated)
Description :  Get Inference Deployment Deployment.
Reference :  Link ¶

⚶ Changes

{
  "#id": "OnlineDeployments_Get",
  "$responses": {
    "200": {
      "$properties": {
        "properties": [
          {
            "@added_e28cc1ef576248a9a4095bd3d875e56f": {
              "#name": "startupProbe",
              "Description": "This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes.",
              "Required": false,
              "Type": "object",
              "$properties": [
                {
                  "#name": "failureThreshold",
                  "Description": "The number of failures to allow before returning an unhealthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "initialDelay",
                  "Description": "The delay before the first probe in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "period",
                  "Description": "The length of time between probes in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "successThreshold",
                  "Description": "The number of successful probes before returning a healthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "timeout",
                  "Description": "The probe timeout in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                }
              ]
            }
          }
        ]
      }
    }
  }
}

⚼ Request

GET:  /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/onlineEndpoints/{endpointName}/deployments/{deploymentName}
{
subscriptionId:
{
Description: The ID of the target subscription. ,
Required: True ,
}
string ,
resourceGroupName:
{
Description: The name of the resource group. The name is case insensitive. ,
Required: True ,
}
string ,
workspaceName:
{
Description: Name of Azure Machine Learning workspace. ,
Required: True ,
}
string ,
endpointName:
{
Description: Inference endpoint name. ,
Required: True ,
}
string ,
deploymentName:
{
Description: Inference Endpoint Deployment name. ,
Required: True ,
}
string ,
api-version:
{
Description: The API version to use for this operation. ,
Required: True ,
}
string ,
}

⚐ Response (200)

{
identity:
{
Description: Managed service identity (system assigned and/or user assigned identities) ,
Required: False ,
}
{
principalId:
{
Description: The service principal ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
tenantId:
{
Description: The tenant ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
type:
{
Description: Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). ,
Enum:
{
None: No description available. ,
SystemAssigned: No description available. ,
UserAssigned: No description available. ,
SystemAssigned,UserAssigned: No description available. ,
}
,
Required: True ,
}
enum ,
userAssignedIdentities:
{
Description: 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. ,
Required: False ,
}
object ,
}
,
kind:
{
Description: Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. ,
Required: False ,
}
string ,
properties:
{
Description: [Required] Additional attributes of the entity. ,
Required: True ,
}
{
appInsightsEnabled:
{
Description: If true, enables Application Insights logging. ,
Required: False ,
}
boolean ,
dataCollector:
{
Description: The mdc configuration, we disable mdc when it's null. ,
Required: False ,
}
{
collections:
{
Description: [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. ,
Required: True ,
}
object ,
requestLogging:
{
Description: The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional. ,
Required: False ,
}
{
captureHeaders:
{
Description: 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. ,
Required: False ,
}
[
string ,
]
,
}
,
rollingRate:
{
Description: 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. ,
Enum:
{
Year: No description available. ,
Month: No description available. ,
Day: No description available. ,
Hour: No description available. ,
Minute: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
egressPublicNetworkAccess:
{
Description: If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled. ,
Enum:
{
Enabled: No description available. ,
Disabled: No description available. ,
}
,
Required: False ,
}
enum ,
endpointComputeType:
{
Description: [Required] The compute type of the endpoint. ,
Enum:
{
Managed: No description available. ,
Kubernetes: No description available. ,
AzureMLCompute: No description available. ,
}
,
Required: True ,
}
enum ,
instanceType:
{
Description: Compute instance type. Default: Standard_F4s_v2. ,
Required: False ,
}
string ,
livenessProbe:
{
Description: Liveness probe monitors the health of the container regularly. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
model:
{
Description: The URI path to the model. ,
Required: False ,
}
string ,
modelMountPath:
{
Description: The path to mount the model in custom container. ,
Required: False ,
}
string ,
provisioningState:
{
Description: Provisioning state for the endpoint deployment. ,
Enum:
{
Creating: No description available. ,
Deleting: No description available. ,
Scaling: No description available. ,
Updating: No description available. ,
Succeeded: No description available. ,
Failed: No description available. ,
Canceled: No description available. ,
}
,
Required: False ,
}
enum ,
readinessProbe:
{
Description: Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
startupProbe:
{
Description: This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
requestSettings:
{
Description: Request settings for the deployment. ,
Required: False ,
}
{
maxConcurrentRequestsPerInstance:
{
Description: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. ,
Format: int32 ,
Required: False ,
}
integer ,
maxQueueWait:
{
Description: (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) ,
Format: duration ,
Required: False ,
}
string ,
requestTimeout:
{
Description: The scoring timeout in ISO 8601 format. Defaults to 5000ms. ,
Format: duration ,
Required: False ,
}
string ,
}
,
scaleSettings:
{
Description: Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment. ,
Required: False ,
}
{
scaleType:
{
Description: [Required] Type of deployment scaling algorithm ,
Enum:
{
Default: No description available. ,
TargetUtilization: No description available. ,
}
,
Required: True ,
}
enum ,
}
,
}
,
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code ,
Required: True ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
}
,
}

⚐ Response (default)

{
error:
{
Description: The error object. ,
Required: False ,
}
{
code:
{
Description: The error code. ,
Required: False ,
}
string ,
message:
{
Description: The error message. ,
Required: False ,
}
string ,
target:
{
Description: The error target. ,
Required: False ,
}
string ,
details:
{
Description: The error details. ,
Required: False ,
}
[
string ,
]
,
additionalInfo:
{
Description: The error additional info. ,
Required: False ,
}
[
{
type:
{
Description: The additional info type. ,
Required: False ,
}
string ,
info:
{
Description: The additional info. ,
Required: False ,
}
object ,
}
,
]
,
}
,
}
OnlineDeployments_Update (updated)
Description :  Update Online Deployment (asynchronous).
Reference :  Link ¶

⚶ Changes

{
  "#id": "OnlineDeployments_Update",
  "$responses": {
    "200": {
      "$properties": {
        "properties": [
          {
            "@added_bf4d1c1bdf68409c8622b33c622ecce0": {
              "#name": "startupProbe",
              "Description": "This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes.",
              "Required": false,
              "Type": "object",
              "$properties": [
                {
                  "#name": "failureThreshold",
                  "Description": "The number of failures to allow before returning an unhealthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "initialDelay",
                  "Description": "The delay before the first probe in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "period",
                  "Description": "The length of time between probes in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "successThreshold",
                  "Description": "The number of successful probes before returning a healthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "timeout",
                  "Description": "The probe timeout in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                }
              ]
            }
          }
        ]
      }
    }
  }
}

⚼ Request

PATCH:  /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/onlineEndpoints/{endpointName}/deployments/{deploymentName}
{
subscriptionId:
{
Description: The ID of the target subscription. ,
Required: True ,
}
string ,
resourceGroupName:
{
Description: The name of the resource group. The name is case insensitive. ,
Required: True ,
}
string ,
workspaceName:
{
Description: Name of Azure Machine Learning workspace. ,
Required: True ,
}
string ,
endpointName:
{
Description: Online Endpoint name. ,
Required: True ,
}
string ,
deploymentName:
{
Description: Inference Endpoint Deployment name. ,
Required: True ,
}
string ,
api-version:
{
Description: The API version to use for this operation. ,
Required: True ,
}
string ,
body:
{
Description: Online Endpoint entity to apply during operation. ,
Required: True ,
}
{
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code. ,
Required: False ,
}
string ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
}
,
}

⚐ Response (200)

{
identity:
{
Description: Managed service identity (system assigned and/or user assigned identities) ,
Required: False ,
}
{
principalId:
{
Description: The service principal ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
tenantId:
{
Description: The tenant ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
type:
{
Description: Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). ,
Enum:
{
None: No description available. ,
SystemAssigned: No description available. ,
UserAssigned: No description available. ,
SystemAssigned,UserAssigned: No description available. ,
}
,
Required: True ,
}
enum ,
userAssignedIdentities:
{
Description: 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. ,
Required: False ,
}
object ,
}
,
kind:
{
Description: Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. ,
Required: False ,
}
string ,
properties:
{
Description: [Required] Additional attributes of the entity. ,
Required: True ,
}
{
appInsightsEnabled:
{
Description: If true, enables Application Insights logging. ,
Required: False ,
}
boolean ,
dataCollector:
{
Description: The mdc configuration, we disable mdc when it's null. ,
Required: False ,
}
{
collections:
{
Description: [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. ,
Required: True ,
}
object ,
requestLogging:
{
Description: The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional. ,
Required: False ,
}
{
captureHeaders:
{
Description: 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. ,
Required: False ,
}
[
string ,
]
,
}
,
rollingRate:
{
Description: 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. ,
Enum:
{
Year: No description available. ,
Month: No description available. ,
Day: No description available. ,
Hour: No description available. ,
Minute: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
egressPublicNetworkAccess:
{
Description: If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled. ,
Enum:
{
Enabled: No description available. ,
Disabled: No description available. ,
}
,
Required: False ,
}
enum ,
endpointComputeType:
{
Description: [Required] The compute type of the endpoint. ,
Enum:
{
Managed: No description available. ,
Kubernetes: No description available. ,
AzureMLCompute: No description available. ,
}
,
Required: True ,
}
enum ,
instanceType:
{
Description: Compute instance type. Default: Standard_F4s_v2. ,
Required: False ,
}
string ,
livenessProbe:
{
Description: Liveness probe monitors the health of the container regularly. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
model:
{
Description: The URI path to the model. ,
Required: False ,
}
string ,
modelMountPath:
{
Description: The path to mount the model in custom container. ,
Required: False ,
}
string ,
provisioningState:
{
Description: Provisioning state for the endpoint deployment. ,
Enum:
{
Creating: No description available. ,
Deleting: No description available. ,
Scaling: No description available. ,
Updating: No description available. ,
Succeeded: No description available. ,
Failed: No description available. ,
Canceled: No description available. ,
}
,
Required: False ,
}
enum ,
readinessProbe:
{
Description: Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
startupProbe:
{
Description: This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
requestSettings:
{
Description: Request settings for the deployment. ,
Required: False ,
}
{
maxConcurrentRequestsPerInstance:
{
Description: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. ,
Format: int32 ,
Required: False ,
}
integer ,
maxQueueWait:
{
Description: (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) ,
Format: duration ,
Required: False ,
}
string ,
requestTimeout:
{
Description: The scoring timeout in ISO 8601 format. Defaults to 5000ms. ,
Format: duration ,
Required: False ,
}
string ,
}
,
scaleSettings:
{
Description: Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment. ,
Required: False ,
}
{
scaleType:
{
Description: [Required] Type of deployment scaling algorithm ,
Enum:
{
Default: No description available. ,
TargetUtilization: No description available. ,
}
,
Required: True ,
}
enum ,
}
,
}
,
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code ,
Required: True ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
}
,
}

⚐ Response (202)

{
x-ms-async-operation-timeout:
{
Description: Timeout for the client to use when polling the asynchronous operation. ,
}
string ,
location:
{
Description: URI to poll for asynchronous operation result. ,
}
string ,
retry-after:
{
Description: Duration the client should wait between requests, in seconds. ,
}
integer ,
}

⚐ Response (default)

{
error:
{
Description: The error object. ,
Required: False ,
}
{
code:
{
Description: The error code. ,
Required: False ,
}
string ,
message:
{
Description: The error message. ,
Required: False ,
}
string ,
target:
{
Description: The error target. ,
Required: False ,
}
string ,
details:
{
Description: The error details. ,
Required: False ,
}
[
string ,
]
,
additionalInfo:
{
Description: The error additional info. ,
Required: False ,
}
[
{
type:
{
Description: The additional info type. ,
Required: False ,
}
string ,
info:
{
Description: The additional info. ,
Required: False ,
}
object ,
}
,
]
,
}
,
}
OnlineDeployments_CreateOrUpdate (updated)
Description :  Create or update Inference Endpoint Deployment (asynchronous).
Reference :  Link ¶

⚶ Changes

{
  "#id": "OnlineDeployments_CreateOrUpdate",
  "$parameters": {
    "body": {
      "$properties": {
        "properties": [
          {
            "@added_794fea25030a40ac9caf406e7a41700b": {
              "#name": "startupProbe",
              "Description": "This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes.",
              "Required": false,
              "Type": "object",
              "$properties": [
                {
                  "#name": "failureThreshold",
                  "Description": "The number of failures to allow before returning an unhealthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "initialDelay",
                  "Description": "The delay before the first probe in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "period",
                  "Description": "The length of time between probes in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "successThreshold",
                  "Description": "The number of successful probes before returning a healthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "timeout",
                  "Description": "The probe timeout in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                }
              ]
            }
          }
        ]
      }
    }
  },
  "$responses": {
    "200": {
      "$properties": {
        "properties": [
          {
            "@added_706d19559e95478b87e835fd547b286b": {
              "#name": "startupProbe",
              "Description": "This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes.",
              "Required": false,
              "Type": "object",
              "$properties": [
                {
                  "#name": "failureThreshold",
                  "Description": "The number of failures to allow before returning an unhealthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "initialDelay",
                  "Description": "The delay before the first probe in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "period",
                  "Description": "The length of time between probes in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "successThreshold",
                  "Description": "The number of successful probes before returning a healthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "timeout",
                  "Description": "The probe timeout in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                }
              ]
            }
          }
        ]
      }
    },
    "201": {
      "$properties": {
        "properties": [
          {
            "@added_06f44991a76d49919dbaea8584fbd481": {
              "#name": "startupProbe",
              "Description": "This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes.",
              "Required": false,
              "Type": "object",
              "$properties": [
                {
                  "#name": "failureThreshold",
                  "Description": "The number of failures to allow before returning an unhealthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "initialDelay",
                  "Description": "The delay before the first probe in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "period",
                  "Description": "The length of time between probes in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                },
                {
                  "#name": "successThreshold",
                  "Description": "The number of successful probes before returning a healthy status.",
                  "Format": "int32",
                  "Required": false,
                  "Type": "integer"
                },
                {
                  "#name": "timeout",
                  "Description": "The probe timeout in ISO 8601 format.",
                  "Format": "duration",
                  "Required": false,
                  "Type": "string"
                }
              ]
            }
          }
        ]
      }
    }
  }
}

⚼ Request

PUT:  /subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.MachineLearningServices/workspaces/{workspaceName}/onlineEndpoints/{endpointName}/deployments/{deploymentName}
{
subscriptionId:
{
Description: The ID of the target subscription. ,
Required: True ,
}
string ,
resourceGroupName:
{
Description: The name of the resource group. The name is case insensitive. ,
Required: True ,
}
string ,
workspaceName:
{
Description: Name of Azure Machine Learning workspace. ,
Required: True ,
}
string ,
endpointName:
{
Description: Inference endpoint name. ,
Required: True ,
}
string ,
deploymentName:
{
Description: Inference Endpoint Deployment name. ,
Required: True ,
}
string ,
api-version:
{
Description: The API version to use for this operation. ,
Required: True ,
}
string ,
body:
{
Description: Inference Endpoint entity to apply during operation. ,
Required: True ,
}
{
identity:
{
Description: Managed service identity (system assigned and/or user assigned identities) ,
Required: False ,
}
{
principalId:
{
Description: The service principal ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
tenantId:
{
Description: The tenant ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
type:
{
Description: Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). ,
Enum:
{
None: No description available. ,
SystemAssigned: No description available. ,
UserAssigned: No description available. ,
SystemAssigned,UserAssigned: No description available. ,
}
,
Required: True ,
}
enum ,
userAssignedIdentities:
{
Description: 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. ,
Required: False ,
}
object ,
}
,
kind:
{
Description: Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. ,
Required: False ,
}
string ,
properties:
{
Description: [Required] Additional attributes of the entity. ,
Required: True ,
}
{
appInsightsEnabled:
{
Description: If true, enables Application Insights logging. ,
Required: False ,
}
boolean ,
dataCollector:
{
Description: The mdc configuration, we disable mdc when it's null. ,
Required: False ,
}
{
collections:
{
Description: [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. ,
Required: True ,
}
object ,
requestLogging:
{
Description: The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional. ,
Required: False ,
}
{
captureHeaders:
{
Description: 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. ,
Required: False ,
}
[
string ,
]
,
}
,
rollingRate:
{
Description: 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. ,
Enum:
{
Year: No description available. ,
Month: No description available. ,
Day: No description available. ,
Hour: No description available. ,
Minute: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
egressPublicNetworkAccess:
{
Description: If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled. ,
Enum:
{
Enabled: No description available. ,
Disabled: No description available. ,
}
,
Required: False ,
}
enum ,
endpointComputeType:
{
Description: [Required] The compute type of the endpoint. ,
Enum:
{
Managed: No description available. ,
Kubernetes: No description available. ,
AzureMLCompute: No description available. ,
}
,
Required: True ,
}
enum ,
instanceType:
{
Description: Compute instance type. Default: Standard_F4s_v2. ,
Required: False ,
}
string ,
livenessProbe:
{
Description: Liveness probe monitors the health of the container regularly. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
model:
{
Description: The URI path to the model. ,
Required: False ,
}
string ,
modelMountPath:
{
Description: The path to mount the model in custom container. ,
Required: False ,
}
string ,
provisioningState:
{
Description: Provisioning state for the endpoint deployment. ,
Enum:
{
Creating: No description available. ,
Deleting: No description available. ,
Scaling: No description available. ,
Updating: No description available. ,
Succeeded: No description available. ,
Failed: No description available. ,
Canceled: No description available. ,
}
,
Required: False ,
}
enum ,
readinessProbe:
{
Description: Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
startupProbe:
{
Description: This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
requestSettings:
{
Description: Request settings for the deployment. ,
Required: False ,
}
{
maxConcurrentRequestsPerInstance:
{
Description: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. ,
Format: int32 ,
Required: False ,
}
integer ,
maxQueueWait:
{
Description: (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) ,
Format: duration ,
Required: False ,
}
string ,
requestTimeout:
{
Description: The scoring timeout in ISO 8601 format. Defaults to 5000ms. ,
Format: duration ,
Required: False ,
}
string ,
}
,
scaleSettings:
{
Description: Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment. ,
Required: False ,
}
{
scaleType:
{
Description: [Required] Type of deployment scaling algorithm ,
Enum:
{
Default: No description available. ,
TargetUtilization: No description available. ,
}
,
Required: True ,
}
enum ,
}
,
}
,
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code ,
Required: True ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
}
,
}
,
}

⚐ Response (200)

{
identity:
{
Description: Managed service identity (system assigned and/or user assigned identities) ,
Required: False ,
}
{
principalId:
{
Description: The service principal ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
tenantId:
{
Description: The tenant ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
type:
{
Description: Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). ,
Enum:
{
None: No description available. ,
SystemAssigned: No description available. ,
UserAssigned: No description available. ,
SystemAssigned,UserAssigned: No description available. ,
}
,
Required: True ,
}
enum ,
userAssignedIdentities:
{
Description: 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. ,
Required: False ,
}
object ,
}
,
kind:
{
Description: Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. ,
Required: False ,
}
string ,
properties:
{
Description: [Required] Additional attributes of the entity. ,
Required: True ,
}
{
appInsightsEnabled:
{
Description: If true, enables Application Insights logging. ,
Required: False ,
}
boolean ,
dataCollector:
{
Description: The mdc configuration, we disable mdc when it's null. ,
Required: False ,
}
{
collections:
{
Description: [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. ,
Required: True ,
}
object ,
requestLogging:
{
Description: The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional. ,
Required: False ,
}
{
captureHeaders:
{
Description: 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. ,
Required: False ,
}
[
string ,
]
,
}
,
rollingRate:
{
Description: 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. ,
Enum:
{
Year: No description available. ,
Month: No description available. ,
Day: No description available. ,
Hour: No description available. ,
Minute: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
egressPublicNetworkAccess:
{
Description: If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled. ,
Enum:
{
Enabled: No description available. ,
Disabled: No description available. ,
}
,
Required: False ,
}
enum ,
endpointComputeType:
{
Description: [Required] The compute type of the endpoint. ,
Enum:
{
Managed: No description available. ,
Kubernetes: No description available. ,
AzureMLCompute: No description available. ,
}
,
Required: True ,
}
enum ,
instanceType:
{
Description: Compute instance type. Default: Standard_F4s_v2. ,
Required: False ,
}
string ,
livenessProbe:
{
Description: Liveness probe monitors the health of the container regularly. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
model:
{
Description: The URI path to the model. ,
Required: False ,
}
string ,
modelMountPath:
{
Description: The path to mount the model in custom container. ,
Required: False ,
}
string ,
provisioningState:
{
Description: Provisioning state for the endpoint deployment. ,
Enum:
{
Creating: No description available. ,
Deleting: No description available. ,
Scaling: No description available. ,
Updating: No description available. ,
Succeeded: No description available. ,
Failed: No description available. ,
Canceled: No description available. ,
}
,
Required: False ,
}
enum ,
readinessProbe:
{
Description: Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
startupProbe:
{
Description: This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
requestSettings:
{
Description: Request settings for the deployment. ,
Required: False ,
}
{
maxConcurrentRequestsPerInstance:
{
Description: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. ,
Format: int32 ,
Required: False ,
}
integer ,
maxQueueWait:
{
Description: (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) ,
Format: duration ,
Required: False ,
}
string ,
requestTimeout:
{
Description: The scoring timeout in ISO 8601 format. Defaults to 5000ms. ,
Format: duration ,
Required: False ,
}
string ,
}
,
scaleSettings:
{
Description: Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment. ,
Required: False ,
}
{
scaleType:
{
Description: [Required] Type of deployment scaling algorithm ,
Enum:
{
Default: No description available. ,
TargetUtilization: No description available. ,
}
,
Required: True ,
}
enum ,
}
,
}
,
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code ,
Required: True ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
}
,
}

⚐ Response (201)

{
$headers:
{
x-ms-async-operation-timeout:
{
Description: Timeout for the client to use when polling the asynchronous operation. ,
}
string ,
azure-asyncoperation:
{
Description: URI to poll for asynchronous operation status. ,
}
string ,
}
,
$schema:
{
identity:
{
Description: Managed service identity (system assigned and/or user assigned identities) ,
Required: False ,
}
{
principalId:
{
Description: The service principal ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
tenantId:
{
Description: The tenant ID of the system assigned identity. This property will only be provided for a system assigned identity. ,
Format: uuid ,
Required: False ,
}
string ,
type:
{
Description: Type of managed service identity (where both SystemAssigned and UserAssigned types are allowed). ,
Enum:
{
None: No description available. ,
SystemAssigned: No description available. ,
UserAssigned: No description available. ,
SystemAssigned,UserAssigned: No description available. ,
}
,
Required: True ,
}
enum ,
userAssignedIdentities:
{
Description: 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. ,
Required: False ,
}
object ,
}
,
kind:
{
Description: Metadata used by portal/tooling/etc to render different UX experiences for resources of the same type. ,
Required: False ,
}
string ,
properties:
{
Description: [Required] Additional attributes of the entity. ,
Required: True ,
}
{
appInsightsEnabled:
{
Description: If true, enables Application Insights logging. ,
Required: False ,
}
boolean ,
dataCollector:
{
Description: The mdc configuration, we disable mdc when it's null. ,
Required: False ,
}
{
collections:
{
Description: [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. ,
Required: True ,
}
object ,
requestLogging:
{
Description: The request logging configuration for mdc, it includes advanced logging settings for all collections. It's optional. ,
Required: False ,
}
{
captureHeaders:
{
Description: 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. ,
Required: False ,
}
[
string ,
]
,
}
,
rollingRate:
{
Description: 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. ,
Enum:
{
Year: No description available. ,
Month: No description available. ,
Day: No description available. ,
Hour: No description available. ,
Minute: No description available. ,
}
,
Required: False ,
}
enum ,
}
,
egressPublicNetworkAccess:
{
Description: If Enabled, allow egress public network access. If Disabled, this will create secure egress. Default: Enabled. ,
Enum:
{
Enabled: No description available. ,
Disabled: No description available. ,
}
,
Required: False ,
}
enum ,
endpointComputeType:
{
Description: [Required] The compute type of the endpoint. ,
Enum:
{
Managed: No description available. ,
Kubernetes: No description available. ,
AzureMLCompute: No description available. ,
}
,
Required: True ,
}
enum ,
instanceType:
{
Description: Compute instance type. Default: Standard_F4s_v2. ,
Required: False ,
}
string ,
livenessProbe:
{
Description: Liveness probe monitors the health of the container regularly. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
model:
{
Description: The URI path to the model. ,
Required: False ,
}
string ,
modelMountPath:
{
Description: The path to mount the model in custom container. ,
Required: False ,
}
string ,
provisioningState:
{
Description: Provisioning state for the endpoint deployment. ,
Enum:
{
Creating: No description available. ,
Deleting: No description available. ,
Scaling: No description available. ,
Updating: No description available. ,
Succeeded: No description available. ,
Failed: No description available. ,
Canceled: No description available. ,
}
,
Required: False ,
}
enum ,
readinessProbe:
{
Description: Readiness probe validates if the container is ready to serve traffic. The properties and defaults are the same as liveness probe. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
startupProbe:
{
Description: This verifies whether the application within a container is started. Startup probes run before any other probe, and, unless it finishes successfully, disables other probes. ,
Required: False ,
}
{
failureThreshold:
{
Description: The number of failures to allow before returning an unhealthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
initialDelay:
{
Description: The delay before the first probe in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
period:
{
Description: The length of time between probes in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
successThreshold:
{
Description: The number of successful probes before returning a healthy status. ,
Format: int32 ,
Required: False ,
}
integer ,
timeout:
{
Description: The probe timeout in ISO 8601 format. ,
Format: duration ,
Required: False ,
}
string ,
}
,
requestSettings:
{
Description: Request settings for the deployment. ,
Required: False ,
}
{
maxConcurrentRequestsPerInstance:
{
Description: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1. ,
Format: int32 ,
Required: False ,
}
integer ,
maxQueueWait:
{
Description: (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) ,
Format: duration ,
Required: False ,
}
string ,
requestTimeout:
{
Description: The scoring timeout in ISO 8601 format. Defaults to 5000ms. ,
Format: duration ,
Required: False ,
}
string ,
}
,
scaleSettings:
{
Description: Scale settings for the deployment. If it is null or not provided, it defaults to TargetUtilizationScaleSettings for KubernetesOnlineDeployment and to DefaultScaleSettings for ManagedOnlineDeployment. ,
Required: False ,
}
{
scaleType:
{
Description: [Required] Type of deployment scaling algorithm ,
Enum:
{
Default: No description available. ,
TargetUtilization: No description available. ,
}
,
Required: True ,
}
enum ,
}
,
}
,
sku:
{
Description: Sku details required for ARM contract for Autoscaling. ,
Required: False ,
}
{
name:
{
Description: The name of the SKU. Ex - P3. It is typically a letter+number code ,
Required: True ,
}
string ,
tier:
{
Description: 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. ,
Enum:
{
Free: No description available. ,
Basic: No description available. ,
Standard: No description available. ,
Premium: No description available. ,
}
,
Required: False ,
}
enum ,
size:
{
Description: The SKU size. When the name field is the combination of tier and some other value, this would be the standalone code. ,
Required: False ,
}
string ,
family:
{
Description: If the service has different generations of hardware, for the same SKU, then that can be captured here. ,
Required: False ,
}
string ,
capacity:
{
Description: 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. ,
Format: int32 ,
Required: False ,
}
integer ,
}
,
}
,
}

⚐ Response (default)

{
error:
{
Description: The error object. ,
Required: False ,
}
{
code:
{
Description: The error code. ,
Required: False ,
}
string ,
message:
{
Description: The error message. ,
Required: False ,
}
string ,
target:
{
Description: The error target. ,
Required: False ,
}
string ,
details:
{
Description: The error details. ,
Required: False ,
}
[
string ,
]
,
additionalInfo:
{
Description: The error additional info. ,
Required: False ,
}
[
{
type:
{
Description: The additional info type. ,
Required: False ,
}
string ,
info:
{
Description: The additional info. ,
Required: False ,
}
object ,
}
,
]
,
}
,
}