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: string ,
resourceGroupName: string ,
workspaceName: string ,
endpointName: string ,
api-version: string ,
$orderBy: string ,
$top: integer ,
$skip: string ,
}

⚐ Response (200)

{
nextLink: string ,
value:
[
{
identity:
{
principalId: string ,
tenantId: string ,
type: enum ,
userAssignedIdentities: object ,
}
,
kind: string ,
properties:
{
appInsightsEnabled: boolean ,
dataCollector:
{
collections: object ,
requestLogging:
{
captureHeaders:
[
string ,
]
,
}
,
rollingRate: enum ,
}
,
egressPublicNetworkAccess: enum ,
endpointComputeType: enum ,
instanceType: string ,
livenessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
model: string ,
modelMountPath: string ,
provisioningState: enum ,
readinessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
startupProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
requestSettings:
{
maxConcurrentRequestsPerInstance: integer ,
maxQueueWait: string ,
requestTimeout: string ,
}
,
scaleSettings:
{
scaleType: enum ,
}
,
}
,
sku:
{
name: string ,
tier: enum ,
size: string ,
family: string ,
capacity: integer ,
}
,
}
,
]
,
}

⚐ Response (default)

{
error:
{
code: string ,
message: string ,
target: string ,
details:
[
string ,
]
,
additionalInfo:
[
{
type: string ,
info: 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: string ,
resourceGroupName: string ,
workspaceName: string ,
endpointName: string ,
deploymentName: string ,
api-version: string ,
}

⚐ Response (200)

{
identity:
{
principalId: string ,
tenantId: string ,
type: enum ,
userAssignedIdentities: object ,
}
,
kind: string ,
properties:
{
appInsightsEnabled: boolean ,
dataCollector:
{
collections: object ,
requestLogging:
{
captureHeaders:
[
string ,
]
,
}
,
rollingRate: enum ,
}
,
egressPublicNetworkAccess: enum ,
endpointComputeType: enum ,
instanceType: string ,
livenessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
model: string ,
modelMountPath: string ,
provisioningState: enum ,
readinessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
startupProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
requestSettings:
{
maxConcurrentRequestsPerInstance: integer ,
maxQueueWait: string ,
requestTimeout: string ,
}
,
scaleSettings:
{
scaleType: enum ,
}
,
}
,
sku:
{
name: string ,
tier: enum ,
size: string ,
family: string ,
capacity: integer ,
}
,
}

⚐ Response (default)

{
error:
{
code: string ,
message: string ,
target: string ,
details:
[
string ,
]
,
additionalInfo:
[
{
type: string ,
info: 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: string ,
resourceGroupName: string ,
workspaceName: string ,
endpointName: string ,
deploymentName: string ,
api-version: string ,
body:
{
sku:
{
capacity: integer ,
family: string ,
name: string ,
size: string ,
tier: enum ,
}
,
}
,
}

⚐ Response (200)

{
identity:
{
principalId: string ,
tenantId: string ,
type: enum ,
userAssignedIdentities: object ,
}
,
kind: string ,
properties:
{
appInsightsEnabled: boolean ,
dataCollector:
{
collections: object ,
requestLogging:
{
captureHeaders:
[
string ,
]
,
}
,
rollingRate: enum ,
}
,
egressPublicNetworkAccess: enum ,
endpointComputeType: enum ,
instanceType: string ,
livenessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
model: string ,
modelMountPath: string ,
provisioningState: enum ,
readinessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
startupProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
requestSettings:
{
maxConcurrentRequestsPerInstance: integer ,
maxQueueWait: string ,
requestTimeout: string ,
}
,
scaleSettings:
{
scaleType: enum ,
}
,
}
,
sku:
{
name: string ,
tier: enum ,
size: string ,
family: string ,
capacity: integer ,
}
,
}

⚐ Response (202)

{
x-ms-async-operation-timeout: string ,
location: string ,
retry-after: integer ,
}

⚐ Response (default)

{
error:
{
code: string ,
message: string ,
target: string ,
details:
[
string ,
]
,
additionalInfo:
[
{
type: string ,
info: 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: string ,
resourceGroupName: string ,
workspaceName: string ,
endpointName: string ,
deploymentName: string ,
api-version: string ,
body:
{
identity:
{
principalId: string ,
tenantId: string ,
type: enum ,
userAssignedIdentities: object ,
}
,
kind: string ,
properties:
{
appInsightsEnabled: boolean ,
dataCollector:
{
collections: object ,
requestLogging:
{
captureHeaders:
[
string ,
]
,
}
,
rollingRate: enum ,
}
,
egressPublicNetworkAccess: enum ,
endpointComputeType: enum ,
instanceType: string ,
livenessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
model: string ,
modelMountPath: string ,
provisioningState: enum ,
readinessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
startupProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
requestSettings:
{
maxConcurrentRequestsPerInstance: integer ,
maxQueueWait: string ,
requestTimeout: string ,
}
,
scaleSettings:
{
scaleType: enum ,
}
,
}
,
sku:
{
name: string ,
tier: enum ,
size: string ,
family: string ,
capacity: integer ,
}
,
}
,
}

⚐ Response (200)

{
identity:
{
principalId: string ,
tenantId: string ,
type: enum ,
userAssignedIdentities: object ,
}
,
kind: string ,
properties:
{
appInsightsEnabled: boolean ,
dataCollector:
{
collections: object ,
requestLogging:
{
captureHeaders:
[
string ,
]
,
}
,
rollingRate: enum ,
}
,
egressPublicNetworkAccess: enum ,
endpointComputeType: enum ,
instanceType: string ,
livenessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
model: string ,
modelMountPath: string ,
provisioningState: enum ,
readinessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
startupProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
requestSettings:
{
maxConcurrentRequestsPerInstance: integer ,
maxQueueWait: string ,
requestTimeout: string ,
}
,
scaleSettings:
{
scaleType: enum ,
}
,
}
,
sku:
{
name: string ,
tier: enum ,
size: string ,
family: string ,
capacity: integer ,
}
,
}

⚐ Response (201)

{
$headers:
{
x-ms-async-operation-timeout: string ,
azure-asyncoperation: string ,
}
,
$schema:
{
identity:
{
principalId: string ,
tenantId: string ,
type: enum ,
userAssignedIdentities: object ,
}
,
kind: string ,
properties:
{
appInsightsEnabled: boolean ,
dataCollector:
{
collections: object ,
requestLogging:
{
captureHeaders:
[
string ,
]
,
}
,
rollingRate: enum ,
}
,
egressPublicNetworkAccess: enum ,
endpointComputeType: enum ,
instanceType: string ,
livenessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
model: string ,
modelMountPath: string ,
provisioningState: enum ,
readinessProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
startupProbe:
{
failureThreshold: integer ,
initialDelay: string ,
period: string ,
successThreshold: integer ,
timeout: string ,
}
,
requestSettings:
{
maxConcurrentRequestsPerInstance: integer ,
maxQueueWait: string ,
requestTimeout: string ,
}
,
scaleSettings:
{
scaleType: enum ,
}
,
}
,
sku:
{
name: string ,
tier: enum ,
size: string ,
family: string ,
capacity: integer ,
}
,
}
,
}

⚐ Response (default)

{
error:
{
code: string ,
message: string ,
target: string ,
details:
[
string ,
]
,
additionalInfo:
[
{
type: string ,
info: object ,
}
,
]
,
}
,
}