Alibaba Cloud Model Studio:OpenAI compatible - Chat

The Qwen models from Alibaba Cloud Model Studio support OpenAI-compatible interfaces. You can migrate your existing OpenAI code to Model Studio by updating only the API key, BASE_URL, and model name.

Use the OpenAI SDK

Prerequisites

• Make sure that a Python environment is installed on your computer.

• Install the latest version of the OpenAI SDK.

  # If the following command reports an error, replace pip with pip3.
  pip install -U openai

• Activate Model Studio and create an API key. For more information, see Preparations: Create and export an API key.

• Export the API key as an environment variable to reduce the risk of API key leakage, see Export the API key as an environment variable. You can also set the API key in the code, but this increases the risk of leakage.

• Select a model to use. For more information, see Model availability.

Usage

The following examples show how to use the OpenAI SDK to access Qwen models on Model Studio.

Non-streaming call example

from openai import OpenAI
import os

def get_response():
    client = OpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),  # If you have not configured an environment variable, replace this line with api_key="sk-xxx" using your Model Studio API key.
        # Set the base_url of the DashScope SDK. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1.
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",  
    )
    completion = client.chat.completions.create(
        model="qwen-plus",  # This example uses qwen-plus. You can replace the model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models.
        messages=[{'role': 'system', 'content': 'You are a helpful assistant.'},
                  {'role': 'user', 'content': 'Who are you?'}]
        )
    print(completion.model_dump_json())

if __name__ == '__main__':
    get_response()

Running the code produces the following result:

{
    "id": "chatcmpl-xxx",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null,
            "message": {
                "content": "I am a large-scale pre-trained model from Alibaba Cloud. My name is Qwen.",
                "role": "assistant",
                "function_call": null,
                "tool_calls": null
            }
        }
    ],
    "created": 1716430652,
    "model": "qwen-plus",
    "object": "chat.completion",
    "system_fingerprint": null,
    "usage": {
        "completion_tokens": 18,
        "prompt_tokens": 22,
        "total_tokens": 40
    }
}

Streaming call example

from openai import OpenAI
import os


def get_response():
    client = OpenAI(
        # If you have not configured an environment variable, replace the following line with api_key="sk-xxx" using your Model Studio API key.
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # Set the base_url of the DashScope SDK. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1.
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
        
    )
    completion = client.chat.completions.create(
        model="qwen-plus",  # This example uses qwen-plus. You can replace the model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models.
        messages=[{'role': 'system', 'content': 'You are a helpful assistant.'},
                  {'role': 'user', 'content': 'Who are you?'}],
        stream=True,
        # Use the following setting to display token usage information in the last line of the streaming output.
        stream_options={"include_usage": True}
        )
    for chunk in completion:
        print(chunk.model_dump_json())


if __name__ == '__main__':
    get_response()

Running the code produces the following result:

{"id":"chatcmpl-xxx","choices":[{"delta":{"content":"","function_call":null,"role":"assistant","tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[{"delta":{"content":"I am"},"function_call":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[{"delta":{"content":" a large-scale"},"function_call":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[{"delta":{"content":" language"},"function_call":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[{"delta":{"content":" model from Alibaba Cloud"},"function_call":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[{"delta":{"content":", and my name is Qwen."},"function_call":null,"role":null,"tool_calls":null},"finish_reason":null,"index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[{"delta":{"content":"","function_call":null,"role":null,"tool_calls":null},"finish_reason":"stop","index":0,"logprobs":null}],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":null}
{"id":"chatcmpl-xxx","choices":[],"created":1719286190,"model":"qwen-plus","object":"chat.completion.chunk","system_fingerprint":null,"usage":{"completion_tokens":16,"prompt_tokens":22,"total_tokens":38}}

Function calling example

This section provides an example of how to implement the tool calling feature with an OpenAI-compatible interface using weather and time query tools. The sample code supports multi-round tool calling.

from openai import OpenAI
from datetime import datetime
import json
import os

client = OpenAI(
    # If you have not configured an environment variable, replace the following line with api_key="sk-xxx" using your Model Studio API key.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Set the base_url of the DashScope SDK. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1.
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",  
)

# Define the tool list. The model refers to the name and description of the tools when selecting which tool to use.
tools = [
    # Tool 1: Get the current time.
    {
        "type": "function",
        "function": {
            "name": "get_current_time",
            "description": "Useful for when you want to know the current time.",
            # Because no input parameters are required to get the current time, parameters is an empty dictionary.
            "parameters": {}
        }
    },  
    # Tool 2: Get the weather of a specified city.
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Useful for querying the weather in a specific city.",
            "parameters": {  
                "type": "object",
                "properties": {
                    # A location must be provided to query the weather, so the parameter is set to location.
                    "location": {
                        "type": "string",
                        "description": "A city or county, such as Beijing, Hangzhou, or Yuhang District."
                    }
                }
            },
            "required": [
                "location"
            ]
        }
    }
]

# Simulate the weather query tool. Sample result: "It is rainy in Beijing today."
def get_current_weather(location):
    return f"It is rainy in {location} today. "

# A tool to query the current time. Sample result: "Current time: 2024-04-15 17:15:18."
def get_current_time():
    # Get the current date and time.
    current_datetime = datetime.now()
    # Format the current date and time.
    formatted_time = current_datetime.strftime('%Y-%m-%d %H:%M:%S')
    # Return the formatted current time.
    return f"Current time: {formatted_time}."

# Encapsulate the model response function.
def get_response(messages):
    completion = client.chat.completions.create(
        model="qwen-plus",  # This example uses qwen-plus. You can replace the model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models.
        messages=messages,
        tools=tools
        )
    return completion.model_dump()

def call_with_messages():
    print('\n')
    messages = [
            {
                "content": input('Please enter your query:'),  # Sample questions: "What time is it?" "What time will it be in an hour?" "What is the weather in Beijing?"
                "role": "user"
            }
    ]
    print("-"*60)
    # The first round of model calling.
    i = 1
    first_response = get_response(messages)
    assistant_output = first_response['choices'][0]['message']
    print(f"\nLarge model output in round {i}: {first_response}\n")
    if  assistant_output['content'] is None:
        assistant_output['content'] = ""
    messages.append(assistant_output)
    # If no tool needs to be called, return the final answer directly.
    if assistant_output['tool_calls'] == None:  # If the model determines that no tool needs to be called, print the assistant's reply directly. A second round of model calling is not required.
        print(f"No tool call is needed. I can answer directly: {assistant_output['content']}")
        return
    # If a tool needs to be called, perform multiple rounds of model calling until the model determines that no tool needs to be called.
    while assistant_output['tool_calls'] != None:
        # If the model determines that the weather query tool needs to be called, run the weather query tool.
        if assistant_output['tool_calls'][0]['function']['name'] == 'get_current_weather':
            tool_info = {"name": "get_current_weather", "role":"tool"}
            # Extract the location parameter information.
            location = json.loads(assistant_output['tool_calls'][0]['function']['arguments'])['location']
            tool_info['content'] = get_current_weather(location)
        # If the model determines that the time query tool needs to be called, run the time query tool.
        elif assistant_output['tool_calls'][0]['function']['name'] == 'get_current_time':
            tool_info = {"name": "get_current_time", "role":"tool"}
            tool_info['content'] = get_current_time()
        print(f"Tool output: {tool_info['content']}\n")
        print("-"*60)
        messages.append(tool_info)
        assistant_output = get_response(messages)['choices'][0]['message']
        if  assistant_output['content'] is None:
            assistant_output['content'] = ""
        messages.append(assistant_output)
        i += 1
        print(f"Large model output in round {i}: {assistant_output}\n")
    print(f"Final answer: {assistant_output['content']}")

if __name__ == '__main__':
    call_with_messages()

If you enter What is the weather in Singapore?, the program generates the following output:

Request parameters

The input parameters are aligned with the OpenAI interface parameters. The following parameters are supported:

Response parameters

Use the langchain_openai SDK

Prerequisites

• Make sure that a Python environment is installed on your computer.

• Run the following command to install the langchain_openai SDK.

  # If the following command reports an error, replace pip with pip3.
  pip install -U langchain_openai

• Activate Model Studio and create an API key. For more information, see Preparations: Create and export an API key.

• Export the API key as an environment variable to reduce the risk of API key leakage, see Export the API key as an environment variable. You can also set the API key in the code, but this increases the risk of leakage.

• Select a model to use. For more information, see Model availability.

Usage

The following examples show how to use the langchain_openai SDK to call the Qwen models from Model Studio.

Non-streaming output

Non-streaming output is implemented using the invoke method. The following is the sample code:

from langchain_openai import ChatOpenAI
import os

def get_response():
    llm = ChatOpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),  # If you have not configured an environment variable, replace this line with api_key="sk-xxx" using your Model Studio API key.
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",  # If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1.
        model="qwen-plus"  # This example uses qwen-plus. You can replace the model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models.
        )
    messages = [
        {"role":"system","content":"You are a helpful assistant."},
        {"role":"user","content":"Who are you?"}
    ]
    response = llm.invoke(messages)
    print(response.json())

if __name__ == "__main__":
    get_response()

Running the code produces the following result:

{
    "content": "I am a large language model from Alibaba Cloud. My name is Qwen.",
    "additional_kwargs": {},
    "response_metadata": {
        "token_usage": {
            "completion_tokens": 16,
            "prompt_tokens": 22,
            "total_tokens": 38
        },
        "model_name": "qwen-plus",
        "system_fingerprint": "",
        "finish_reason": "stop",
        "logprobs": null
    },
    "type": "ai",
    "name": null,
    "id": "run-xxx",
    "example": false,
    "tool_calls": [],
    "invalid_tool_calls": []
}

Streaming output

Streaming output is implemented using the stream method. You do not need to set the stream parameter.

from langchain_openai import ChatOpenAI
import os

def get_response():
    llm = ChatOpenAI(
        api_key=os.getenv("DASHSCOPE_API_KEY"),  # If you have not configured an environment variable, replace this line with api_key="sk-xxx" using your Model Studio API key.
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",   # If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1.
        model="qwen-plus",   # This example uses qwen-plus. You can replace the model name as needed. For a list of models, see https://www.alibabacloud.com/help/en/model-studio/getting-started/models.
        stream_usage=True
        )
    messages = [
        {"role":"system","content":"You are a helpful assistant."}, 
        {"role":"user","content":"Who are you?"},
    ]
    response = llm.stream(messages)
    for chunk in response:
        print(chunk.model_dump_json())

if __name__ == "__main__":
    get_response()

Running the code produces the following result:

{"content": "", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "I am", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " a large", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " language model", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " from", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " Alibaba", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": " Cloud", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": ", and my name is Qwen.", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "", "additional_kwargs": {}, "response_metadata": {"finish_reason": "stop"}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null, "tool_call_chunks": []}
{"content": "", "additional_kwargs": {}, "response_metadata": {}, "type": "AIMessageChunk", "name": null, "id": "run-xxx", "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": {"input_tokens": 22, "output_tokens": 16, "total_tokens": 38}, "tool_call_chunks": []}

For information about input parameter settings, see Request parameters. The relevant parameters are defined in the ChatOpenAI object.

Use the HTTP interface

You can call Model Studio using the HTTP interface to receive a response that has the same structure as a response from the OpenAI service.

Prerequisites

• Activate Model Studio and create an API key. For more information, see Preparations: Create and export an API key.

• Export the API key as an environment variable to reduce the risk of API key leakage, see Export the API key as an environment variable. You can also set the API key in the code, but this increases the risk of leakage.

Submit an API request

Singapore: POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
China (Beijing): POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions

Sample request

The following example shows a script that calls the API using the cURL command.

Non-streaming output

# If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions.
curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen-plus",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user", 
            "content": "Who are you?"
        }
    ]
}'

Running the command produces the following result:

{
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "I am a large language model from Alibaba Cloud. My name is Qwen."
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null
        }
    ],
    "object": "chat.completion",
    "usage": {
        "prompt_tokens": 11,
        "completion_tokens": 16,
        "total_tokens": 27
    },
    "created": 1715252778,
    "system_fingerprint": "",
    "model": "qwen-plus",
    "id": "chatcmpl-xxx"
}

Streaming output

If you want to use streaming output, set the stream parameter to true in the request body.

# If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions.
curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen-plus",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user", 
            "content": "Who are you?"
        }
    ],
    "stream":true
}'

Running the command produces the following result:

data: {"choices":[{"delta":{"content":"","role":"assistant"},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"finish_reason":null,"delta":{"content":"I am"},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":" a large-scale"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":" language model"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":" from Alibaba Cloud"},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":", and my name is Qwen."},"finish_reason":null,"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: {"choices":[{"delta":{"content":""},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1715931028,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-3bb05cf5cd819fbca5f0b8d67a025022"}

data: [DONE]

For details about the input parameters, see Request parameters.

Abnormal response example

If an error occurs during the request, the response indicates the cause of the error in the code and message fields.

{
    "error": {
        "message": "Incorrect API key provided. ",
        "type": "invalid_request_error",
        "param": null,
        "code": "invalid_api_key"
    }
}

Status codes