Call a model in a sub-workspace - Alibaba Cloud Model Studio

This topic describes how to call a model in the specified workspace.

Important

Typically, you do not need to specify the workspace ID when you call a model in the model center by using the API key of your Alibaba Cloud account. You must specify the workspace ID only when you call a model in a workspace by using the API key of a Resource Access Management (RAM) user.

Note: You cannot access the default workspace by using the API key of a RAM user. The models and applications in the default workspace can be called only by using the API key of the Alibaba Cloud account.

Prerequisites

The Alibaba Cloud Model Studio service is activated. For more information, see Activate Alibaba Cloud Model Studio.

An API key is created. For more information, see Obtain an API key.
A sub-workspace is created.
The RAM user is authorized to access the sub-workspace.
The sub-workspace is authorized to call models.

Call examples

SDK sample code

The following sample code shows how to call the Retrieval-Augmented Generation (RAG) application for answering questions by using an enterprise knowledge base.

Note

To ensure that the code runs as expected, you must replace YOUR_API_KEY and YOUR_WORKSPACE in the code with your API key and workspace ID.

python sdk version: dashscope>=1.17.0

java sdk version: >=2.12.0

Specify the API key

export DASHSCOPE_API_KEY=YOUR_API_KEY

Sample code

The following sample code shows how to call a model in a sub-workspace.

Python

from http import HTTPStatus
import dashscope


def call_with_messages():
    messages = [{'role': 'system', 'content': 'You are a helpful assistant.'},
                {'role': 'user', 'content': 'Who are you'}]

    response = dashscope.Generation.call(
        dashscope.Generation.Models.qwen_turbo,
        messages=messages,
        result_format='message',  # set the result to be "message" format.
        workspace='YOUR_WORKSPACE'
    )
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
            response.request_id, response.status_code,
            response.code, response.message
        ))


if __name__ == '__main__':
    dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'
    call_with_messages()

Java

import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.MessageManager;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;

public class Main {
    public static void callWithMessage()
            throws NoApiKeyException, ApiException, InputRequiredException {
        Generation gen = new Generation("http", "https://dashscope-intl.aliyuncs.com/api/v1");
        MessageManager msgManager = new MessageManager(10);
        Message systemMsg =
                Message.builder().role(Role.SYSTEM.getValue()).content("You are a helpful assistant.").build();
        Message userMsg = Message.builder().role(Role.USER.getValue()).content("Who are you").build();
        msgManager.add(systemMsg);
        msgManager.add(userMsg);
        GenerationParam param =
                GenerationParam.builder().model(Generation.Models.QWEN_TURBO).messages(msgManager.get())
                        .resultFormat(GenerationParam.ResultFormat.MESSAGE)
                        .workspace("YOUR_WORKSPACE")
                        .build();
        GenerationResult result = gen.call(param);
        System.out.println(result);
    }


    public static void main(String[] args){
        try {
            callWithMessage();
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

Sample request (SSE disabled)

The following sample code shows how to call a model in a sub-workspace by using a cURL command. In this example, Server-Sent Events (SSE) is disabled.

Note

To ensure that the code runs as expected, you must replace YOUR_API_KEY and YOUR_WORKSPACE in the code with your API key and workspace ID.

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \
--header 'X-DashScope-WorkSpace: {YOUR_WORKSPACE}' \
--data '{
    "model": "qwen-turbo",
    "input":{
        "messages":[      
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Who are you"
            }
        ]
    },
    "parameters": {
    }
}'

Sample request (SSE enabled)

The following sample code shows how to call a model in a sub-workspace by using a cURL command. In this example, SSE is enabled.

Note

To ensure that the code runs as expected, you must replace YOUR_API_KEY and YOUR_WORKSPACE in the code with your API key and workspace ID.

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text-generation/generation' \
--header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \
--header 'X-DashScope-WorkSpace: {YOUR_WORKSPACE}' \
--header 'X-DashScope-SSE: enable' \
--data '{
    "model": "qwen-turbo",
    "input":{
        "messages":[      
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
                "content": "Who are you"
            }
        ]
    },
    "parameters": {
    }
}'