Server-side Python SDK

Prerequisites

Activate the service and obtain and configure an API key. To prevent security risks from code leaks, configure the API key as an environment variable instead of hard coding it in your code.

To grant temporary access permissions to third-party applications or users, or want to strictly control risky operations such as accessing or deleting sensitive data, you can use a temporary authentication token.Compared to a long-term API key, a temporary authentication token is valid for only a short period (60 seconds) and offers higher security. It is suitable for temporary call scenarios and can effectively reduce the risk of API key leaks.Usage: In your code, replace the API key used for authentication with the obtained temporary authentication token.

Install the latest version of the DashScope SDK (The DashScope SDK version must be 1.24.1 or later, and the Python version must be 3.9 or later).

API description

TingWu.py

You can call the service using the call method of TingWu.py:

def call(
          model: str,
          user_defined_input: Dict[str, Any],
          parameters: Dict[str, Any] = None,
          api_key: str = None,
          **kwargs
  ) -> DashScopeAPIResponse:
"""Calls the generation model service.

    Args:
          model (str): The requested model, such as qwen3.5-flash.
          api_key (str, optional): The API key. If this parameter is not specified,
              the SDK obtains the API key by following the default rule.
          user_defined_input: The custom input.
          parameters: The custom parameters.
          **kwargs:
              base_address: The base address.
              Additional parameters for the request.

    Raises:
          InvalidInput: The history and auto_history parameters are mutually exclusive.

    Returns:
          Union[GenerationResponse,
                Generator[GenerationResponse, None, None]]: If
          stream is set to True, a Generator is returned. Otherwise, a GenerationResponse is returned.
"""

Using Automotive Service Insights as an example, the key parameters are described as follows. For more information about the parameters, see the Automotive Service Insights API Reference or the Customer Portrait for Car Purchase API Reference:

model
Name
Type
Required
Description
Example
model
string
Yes
Defines the business type.

For more information about the parameters, see the API reference.
tingwu-automotive-service-insights

Name	Type	Required	Description	Example
model	string	Yes	Defines the business type. For more information about the parameters, see the API reference.	tingwu-automotive-service-insights

user_defined_input

Name	Type	Required	Description	Example
fileUrl	string	Select one of the three	The OSS URL of the file to be analyzed.	https://.oss-cn-hangzhou.aliyuncs.com/%E8%AF%95%E9%A9%BE%E6%A1%88%E4%BE%8Bsmall.wav?OSSAccessKeyId=YOUR_ACCESS_KEY_ID&Expires=&Signature=YOUR_SIGNATURE
text	string		The text to be analyzed.	Each line must be in the following format:${Speaker name}: ${Speaker content}For example: `Zhang3: I want to buy an SUV. Li4: What price range are you looking for?`
dataId	string		The ID of the task that has been uploaded and parsed.
appId	string	Yes	Application ID.
task	string	Yes	Task type: createTask: Creates a task. getTask: Obtains the task result.	createTask

parameters (For more information, see the API reference.)

Sample code

from dashscope.multimodal.tingwu.tingwu import TingWu
import os

# Create a TingWu instance.
tingwu = TingWu()
resp = TingWu.call(
    model='tingwu-automotive-service-insights',
    user_defined_input={"task": "createTask", "text": "Zhang*:I want to buy an SUV\nLi*:What price range are you looking for?", "appId": "123456"},
    api_key="your_api_key",
    base_address="https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
    parameters={"serviceInsights": {"insightsContents": [
        {"title": "Store Arrival Welcome - Greeting", "content": "The sales representative actively greets the customer upon arrival.", "score": "20"},
        {"title": "Store Departure Farewell - Customer Information Retention", "content": "The sales representative asks the customer to leave their contact information, such as WeChat, phone number, or business card.", "score": "30"},
        {"title": "Store Arrival Welcome - Beverage Offer",
         "content": "The sales representative proactively asks the customer if they would like a beverage (such as coffee, orange juice, water, or tea), snacks, or fruit.", "score": "50"}]}}
)
print(resp)

Response

Using Automotive Service Insights as an example, the main response parameters are described as follows. For more information, see the Automotive Service Insights API Reference or the Customer Portrait for Car Purchase API Reference:

Name	Type	Description	Example
output	object
output.dataId	string	Task ID.
output.status	string	0: Succeeded 1: In progress 2: Failed	0
usage	object
code	string	Error code.	InvalidParameter
message	string	Error message.	Agent Input text format error.
request_id	string	Request ID.	f97ee37d-0f9c-9b93-b6bf-bd263a232bf9

Sample response:

{
    "output": {
        "dataId": "dj***"
    },
    "usage": {},
    "request_id": "8313c0bc-ff3f-98e8-b87a-0118f6fe3049"
}

​Prerequisites

​API description

​TingWu.py

​Sample code

​Response

Prerequisites

API description

TingWu.py

Sample code

Response