Obtaining Services

Obtain the service list of a user.

Sample Code

In ModelArts notebook, you do not need to enter authentication parameters for session authentication. For details about session authentication of other development environments, see Session Authentication.

Scenario 1: Obtain all services of a user.

      
           from modelarts.session import Session 
from modelarts.model import Predictor 

session = Session() 
predictor_list = Predictor.get_service_list(session)
print(predictor_list)

Scenario 2: Obtain the services of a user based on search criteria.

      
           from modelarts.session import Session 
from modelarts.model import Predictor 

session = Session()
predictor_list = Predictor.get_service_list(session, service_name="digit", order="asc", offset="0", infer_type="real-time")
print(predictor_list)

Parameters

**Table 1** Query parameters
Parameter	Mandatory	Type	Description
session	Yes	Object	Session object. For details about the initialization method, see Session Authentication.
service_id	No	String	Service ID. By default, the service ID is not filtered.
service_name	No	String	Service name. By default, the service name is not filtered.
infer_type	No	String	Inference mode. The value can be real-time or batch. By default, this parameter is left blank.
offset	No	Integer	Start page of the paging list. Default value: 0
limit	No	Integer	Maximum number of records returned on each page. Default value: 1000
service_status	No	String	Service status. By default, the service status is not filtered. The service list can be queried based on the service status. Possible values are as follows: running: The service is running properly and is being billed. deploying: The service is being deployed or scheduling resources are being deployed. concerning: An alarm is generated, indicating that the backend instance is abnormal and may be billed. For example, in the case of multiple instances, some instances are normal, but some are not. A normal instance is billed but is in the concerning status. failed: The service fails to be deployed. For details about the failure cause, see the event and log. stopped: The service has been stopped. finished: This status is displayed only for the batch service, indicating that the service running is completed.
sort_by	No	String	Sorting mode. The value can be publish_at or service_name. Default value: publish_at
order	No	String	Sorting order. The value can be asc or desc, indicating the ascending or descending order. Default value: desc
model_id	No	String	Model ID. By default, the model ID is not filtered.

**Table 2** **get_service_list** response parameters
Parameter	Type	Description
total_count	Integer	Total number of services that meet the search criteria when no paging is implemented
count	Integer	Number of services in the query result. If offset and limit are not set, the values of count and total are the same.
services	service array	Collection of the queried services

**Table 3** **service** parameters
Parameter	Type	Description
service_id	String	Service ID
service_name	String	Service name
description	String	Service description
tenant	String	Tenant to whom a service belongs
project	String	Project to which a service belongs
owner	String	User to whom a service belongs
publish_at	Number	Latest service publishing time, in milliseconds calculated from 1970.1.1 0:0:0 UTC
infer_type	String	Inference mode. The value can be real-time or batch.
status	String	Service status. The value can be running, deploying, concerning, failed, stopped, or finished.
progress	Integer	Deployment progress. This parameter is returned when status is deploying.
invocation_times	Number	Total number of service calls
failed_times	Number	Number of failed service calls
is_shared	Boolean	Whether a service is subscribed
shared_count	Number	Number of subscriptions