OnlineRequestSettings Class
- java.
lang. Object - com.
azure. resourcemanager. machinelearning. models. OnlineRequestSettings
- com.
Implements
public final class OnlineRequestSettings
implements JsonSerializable<OnlineRequestSettings>
Online deployment scoring requests configuration.
Constructor Summary
| Constructor | Description |
|---|---|
| OnlineRequestSettings() |
Creates an instance of Online |
Method Summary
| Modifier and Type | Method and Description |
|---|---|
|
static
Online |
fromJson(JsonReader jsonReader)
Reads an instance of Online |
| Integer |
maxConcurrentRequestsPerInstance()
Get the max |
| Duration |
maxQueueWait()
Get the max |
| Duration |
requestTimeout()
Get the request |
|
Json |
toJson(JsonWriter jsonWriter) |
| void |
validate()
Validates the instance. |
|
Online |
withMaxConcurrentRequestsPerInstance(Integer maxConcurrentRequestsPerInstance)
Set the max |
|
Online |
withMaxQueueWait(Duration maxQueueWait)
Set the max |
|
Online |
withRequestTimeout(Duration requestTimeout)
Set the request |
Methods inherited from java.lang.Object
Constructor Details
OnlineRequestSettings
public OnlineRequestSettings()
Creates an instance of OnlineRequestSettings class.
Method Details
fromJson
public static OnlineRequestSettings fromJson(JsonReader jsonReader)
Reads an instance of OnlineRequestSettings from the JsonReader.
Parameters:
Returns:
Throws:
maxConcurrentRequestsPerInstance
public Integer maxConcurrentRequestsPerInstance()
Get the maxConcurrentRequestsPerInstance property: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1.
Returns:
maxQueueWait
public Duration maxQueueWait()
Get the maxQueueWait property: (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).
Returns:
requestTimeout
public Duration requestTimeout()
Get the requestTimeout property: The scoring timeout in ISO 8601 format. Defaults to 5000ms.
Returns:
toJson
validate
public void validate()
Validates the instance.
withMaxConcurrentRequestsPerInstance
public OnlineRequestSettings withMaxConcurrentRequestsPerInstance(Integer maxConcurrentRequestsPerInstance)
Set the maxConcurrentRequestsPerInstance property: The number of maximum concurrent requests per node allowed per deployment. Defaults to 1.
Parameters:
Returns:
withMaxQueueWait
public OnlineRequestSettings withMaxQueueWait(Duration maxQueueWait)
Set the maxQueueWait property: (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).
Parameters:
Returns:
withRequestTimeout
public OnlineRequestSettings withRequestTimeout(Duration requestTimeout)
Set the requestTimeout property: The scoring timeout in ISO 8601 format. Defaults to 5000ms.
Parameters:
Returns: