Updating Service Configurations¶

Function¶

This API is used to update configurations of a model service. It can also be used to start or stop a service.

URI¶

PUT /v1/{project_id}/services/{service_id}

Table 1 describes the required parameters.

**Table 1** Parameters¶
Parameter	Mandatory	Type	Description
project_id	Yes	String	Project ID. For details about how to obtain the project ID, see Obtaining a Project ID.
service_id	Yes	String	Service ID

Request Body¶

Table 2 describes the request parameters.

**Table 2** Parameters¶
Parameter	Mandatory	Type	Description
description	No	String	Service description, which contains a maximum of 100 characters. If this parameter is not set, the service description is not updated.
status	No	String	Service status. The value can be running or stopped. If this parameter is not set, the service status is not changed. status and config cannot be modified at the same time. If both parameters exist, modify only the status parameter.
config	No	config array corresponding to infer_type	Service configuration. If this parameter is not set, the service is not updated. The model service is modified and the update_time parameter is returned only for requests with config updated. If infer_type is set to real-time, see Table 3. If infer_type is set to batch, see Table 4.
schedule	No	schedule array	Service scheduling configuration, which can be configured only for real-time services. By default, this parameter is not used. Services run for a long time. For details, see Table 5.
additional_properties	No	Map<String, Object>	Additional service attribute, which facilitates service management

**Table 3** **config** parameters of **real-time**¶
Parameter	Mandatory	Type	Description
model_id	Yes	String	Model ID
weight	Yes	Integer	Traffic weight allocated to a model. This parameter is mandatory only when infer_type is set to real-time. The sum of the weights must be 100.
specification	Yes	String	Resource specifications. Select specifications based on service requirements.
custom_spec	No	Object	Custom specifications. Set this parameter when you use a dedicated resource pool. For details, see Table 6.
instance_count	Yes	Integer	Number of instances for deploying a model. The value must be greater than 0.
envs	No	Map<String, String>	(Optional) Environment variable key-value pair required for running a model. By default, this parameter is left blank. To ensure data security, do not enter sensitive information, such as plaintext passwords, in environment variables.
cluster_id	No	string	ID of a dedicated resource pool. By default, this parameter is left blank, indicating that no dedicated resource pool is used.

**Table 4** **config** parameters of **batch**¶
Parameter	Mandatory	Type	Description
model_id	Yes	String	Model ID
specification	Yes	String	Resource flavor.
instance_count	Yes	Integer	Number of instances for deploying a model.
envs	No	Map<String, String>	(Optional) Environment variable key-value pair required for running a model. By default, this parameter is left blank. To ensure data security, do not enter sensitive information, such as plaintext passwords, in environment variables.
src_type	No	String	Data source type. This parameter can be set to ManifestFile. By default, this parameter is left blank, indicating that only files in the src_path directory are read. If this parameter is set to ManifestFile, src_path must be a specific manifest file path. You can specify multiple data paths in the manifest file.
src_path	Yes	String	OBS path of the input data of a batch job
dest_path	Yes	String	OBS path of the output data of a batch job
req_uri	Yes	String	Inference API called in a batch job, which is a REST API in the model image. Select an API URI from the model config.json file for inference. If a ModelArts built-in inference image is used, the value of this parameter is /.
mapping_type	Yes	String	Mapping type of the input data. The value can be file or csv. If you select file, each inference request corresponds to a file in the input data path. When this mode is used, req_uri of this model can have only one input parameter and the type of this parameter is file. If you select csv, each inference request corresponds to a row of data in the CSV file. When this mode is used, the files in the input data path can only be in CSV format and mapping_rule must be configured to map the index of each parameter in the inference request body to the CSV file.
mapping_rule	No	Map	Mapping between input parameters and CSV data. This parameter is mandatory only when mapping_type is set to csv. Mapping rule: The mapping rule comes from the input parameter (input_params) in the model configuration file config.json. When type is set to string, number, integer, or boolean, you are required to configure the index parameter. For details, see . The index must be a positive integer starting from 0. If the index value does not comply with the rule, this parameter will be ignored in the request. After the mapping rule is configured, the CSV data must be separated by commas (,).

**Table 5** **schedule** parameters¶
Parameter	Mandatory	Type	Description
type	Yes	String	Scheduling type. Only the value stop is supported.
time_unit	Yes	String	Scheduling time unit. Possible values are DAYS, HOURS, and MINUTES.
duration	Yes	Integer	Value that maps to the time unit. For example, if the task stops after two hours, set time_unit to HOURS and duration to 2.

**Table 6** **custom_spec** parameters¶
Parameter	Mandatory	Type	Description
cpu	Yes	Float	Number of required CPUs
memory	Yes	Integer	Required memory capacity, in MB
gpu_p4	No	Float	Number of GPUs, which can be decimals. This parameter is optional. By default, it is not used.

Response Body¶

None

Samples¶

The following shows how to update a real-time service.

Sample request

PUT    https://endpoint/v1/{project_id}/services/{service_id}
{
    "description": "",
    "status": "running",
    "config": [{
        "model_id": "xxxx",
        "weight": "100",
        "specification": "modelarts.vm.cpu.2u",
        "instance_count": 1
    }]
}

Sample response
```
{}
```

Status Code¶

For details about the status code, see Table 1.

Error Codes¶

See Error Codes.

last updated: 2024-05-18 01:56