Querying the Details of a Service

You can use the API to query details about a service object.

Sample Code

In the ModelArts notebook instance, 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: Query details about the service created in Deploying a Real-Time Service.

  from modelarts.session import Session
  from modelarts.model import Predictor
  session = Session()
  predictor_instance = Predictor(session, service_id="input your service_id")
  predictor_info = predictor_instance.get_service_info()
  

• Method 2: Query details about the service object returned in Querying the List of Service Objects.

  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_info = predictor_instance.get_service_info()
  

Parameter Description

Table 1 get_service_info response 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.
vpc_id	String	ID of the VPC to which a service instance belongs. This parameter is returned when the network configuration is customized.
subnet_network_id	String	ID of the subnet where a service instance resides. This parameter is returned when the network configuration is customized.
security_group_id	String	Security group to which a service instance belongs. This parameter is returned when the network configuration is customized.
status	String	Service status. The value can be running, deploying, concerning, failed, stopped, or finished.
error_msg	String	Error message. When status is failed, the deployment failure cause is returned.
config	config array corresponding to infer_type	config array corresponding to infer_type Service configurations (If a service is shared, only model_id, model_name, and model_version are returned.)
access_address	String	Access address of an inference request. This parameter is returned when infer_type is set to real-time.
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
progress	Integer	Deployment progress. This parameter is returned when status is deploying.

Table 2 config parameters corresponding to real-time

Parameter	Type	Description
model_id	String	Model ID. You can obtain the value by calling the API described in Obtaining the Model List or from the ModelArts management console.
model_name	String	Model name
model_version	String	Model version
source_type	String	Model source. This parameter is returned when a model is created by an ExeML project. The value is auto.
status	String	Running status of a model instance. Possible values are as follows: ready: ready (All instances have been started.) concerning: partially ready (Some instances are started but some are not.) notReady: not ready (All instances are not started.)
weight	Integer	Traffic weight allocated to a model
specification	String	Resource flavor. The value can be modelarts.vm.cpu.2u, modelarts.vm.gpu.p4, or modelarts.vm.ai1.a310.
envs	Map<String, String>	Environment variable key-value pair required for running a model
instance_count	Integer	Number of instances deployed in a model
scaling	Boolean	Whether auto scaling is enabled

Table 3 config parameters corresponding to batch

Parameter	Type	Description
model_id	String	Model ID. You can obtain the value by calling the API described in Obtaining the Model List or from the ModelArts management console.
model_name	String	Model name
model_version	String	Model version
specification	String	Resource flavor. The value can be modelarts.vm.cpu.2u or modelarts.vm.gpu.p4.
envs	Map<String, String>	Environment variable key-value pair required for running a model
instance_count	Integer	Number of instances deployed in a model
src_path	String	OBS path of the input data of a batch job
dest_path	String	OBS path of the output data of a batch job
req_uri	String	Inference path of a batch job
mapping_type	String	Mapping type of the input data. The value can be file or csv.
mapping_rule	Map	Mapping between input parameters and CSV data. This parameter is returned only when mapping_type is set to csv.

last updated: 2024-12-11 13:55 UTC - commit: afb4a7dfa15e256dc933e946d9e874db041cb35c