Updated on 2024-06-12 GMT+08:00

Obtaining Service Logs

You can use the API to obtain the logs of a service object.

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.

  • Method 1: Obtain the logs of a service based on the service object created in Deploying a Real-Time Service.
    1
    2
    3
    4
    5
    6
    7
    from modelarts.session import Session
    from modelarts.model import Predictor
    
    session = Session()
    predictor_instance = Predictor(session, service_id="your_service_id")
    predictor_log = predictor_instance.get_service_logs() 
    print(predictor_log)
    
  • Method 2: Obtain the logs of a service based on the service object returned in Obtaining Service Objects.
    1
    2
    3
    4
    5
    6
    7
    8
    from modelarts.session import Session
    from modelarts.model import Predictor
    
    session = Session()
    predictor_object_list = Predictor.get_service_object_list(session)
    predictor_instance = predictor_object_list[0]                
    predictor_log = predictor_instance.get_service_logs()
    print(predictor_log)
    

Parameters

Table 1 get_service_logs response parameters

Parameter

Type

Description

service_id

String

Service ID

service_name

String

Service name

logs

log array

Service update logs

Table 2 log parameters

Parameter

Type

Description

update_time

Long

Time when a service is updated, in milliseconds calculated from 1970.1.1 0:0:0 UTC

result

String

Update result. The value can be SUCCESS, FAIL, or RUNNING.

config

config array

Updated service configurations. This parameter is returned when infer_type is set to real-time.

Table 3 config parameters

Parameter

Type

Description

model_id

String

Model ID

model_name

String

Model name

model_version

String

Model version

weight

Integer

Traffic weight allocated to a model

specification

String

Resource flavor

instance_count

Integer

Number of instances deployed in a model

envs

Map<String, String>

Environment variable key-value pair required for running a model

Table 4 result parameters

Parameter

Type

Description

node_name

String

Name of an edge node

operation

String

Operation type. The value can be deploy or delete.

result

Boolean

Operation result. true indicates a successful operation, and false indicates a failed operation.