00.前言
近期，Qwen 发布了 QwQ-32B - 一个在许多基准测试中性能可与 DeepSeek-R1 相媲美的推理模型。QwQ在推理模型中集成了调用工具的能力，使其能够在使用工具的同时进行批判性思考，并根据反馈调整推理过程。这样的能力使得QwQ能够很好在Agentic System中使用。本文介绍如何通过vLLM和SgLang结合QwQ-32B，搭建OpenAI格式的聊天API，并与外部函数结合来拓展模型的更多功能。
tools是OpenAI的Chat Completion API中的一个可选参数，可用于提供函数调用规范（function specifications）。这样做的目的是使模型能够生成符合所提供的规范的函数参数格式。同时，API 实际上不会执行任何函数调用。开发人员需要使用模型输出来执行函数调用。
vLLM和SgLang均支持OpenAI-API的tool参数。通过tool参数以及其中的函数调用规范，QwQ将能决定何时调用什么样的函数，以及怎么调用函数。
注：本文测试用例参考OpenAI cookbook：https://cookbook.openai.com/examples/how_to_call_functions_with_chat_models
本文主要包含以下两个个部分：
- 模型部署：使用vLLM，SgLang和QwQ，通过设置参数，部署支持Function call的聊天API接口。
- 生成函数参数：指定一组函数并使用 API 生成函数参数。
01.模型部署
模型文件下载
modelscope download --model=Qwen/QwQ-32B --local_dir ./QwQ-32B
环境安装
pip install vllm pip install "sglang[all]>=0.4.3.post2"
vLLM部署命令
vllm serve /ModelPath/QwQ-32B \ --port 8000 \ --reasoning-parser deepseek_r1 \ --max_model_len 4096 \ --enable-auto-tool-choice \ --tool-call-parser hermes
sglang部署命令
python -m sglang.launch_server --model-path /ModelPath/QwQ-32B --port 3001 --host 0.0.0.0 --tool-call-parser qwen25
模型调用
使用OpenAI的API格式调用本地部署的QwQ模型
单轮对话
from openai import OpenAI # 设置 OpenAI 的 API 密钥和 API 基础 URL 使用 vLLM 的 API 服务器。 openai_api_key = "EMPTY" openai_api_base = "http://localhost:8000/v1" client = OpenAI( api_key=openai_api_key, base_url=openai_api_base, ) # 使用流式输出（stream=True） chat_response = client.chat.completions.create( model="path/to/QwQ-32B", messages=[{"role": "user", "content": "你好"}], stream=True # 启用流式响应 ) # 处理流式输出 contents = [] for e in chat_response: # print(e.choices[0].delta.content,end="") contents.append(e.choices[0].delta.content) print("".join(contents))
添加图片注释，不超过 140 字（可选）
多轮对话
from openai import OpenAI import os # 初始化OpenAI客户端 client = OpenAI( api_key = "empty", base_url="http://localhost:8000/v1" ) reasoning_content = "" # 定义完整思考过程 answer_content = "" # 定义完整回复 is_answering = False # 判断是否结束思考过程并开始回复 messages = [] conversation_idx = 1 while True: print("="*20+f"第{conversation_idx}轮对话"+"="*20) conversation_idx += 1 user_msg = {"role": "user", "content": input("请输入你的消息：")} messages.append(user_msg) # 创建聊天完成请求 completion = client.chat.completions.create( model="path/to/QwQ-32B",# 此处以 qwq-32b 为例，可按需更换模型名称 messages=messages, stream=True ) print("\n" + "=" * 20 + "思考过程" + "=" * 20 + "\n") for chunk in completion: # 如果chunk.choices为空，则打印usage if not chunk.choices: print("\nUsage:") print(chunk.usage) else: delta = chunk.choices[0].delta # 打印思考过程 if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None: print(delta.reasoning_content, end='', flush=True) reasoning_content += delta.reasoning_content else: # 开始回复 if delta.content != "" and is_answering is False: print("\n" + "=" * 20 + "完整回复" + "=" * 20 + "\n") is_answering = True # 打印回复过程 print(delta.content, end='', flush=True) answer_content += delta.content messages.append({"role": "assistant", "content": answer_content}) print("\n") # print("=" * 20 + "完整思考过程" + "=" * 20 + "\n") # print(reasoning_content) # print("=" * 20 + "完整回复" + "=" * 20 + "\n") # print(answer_content)
添加图片注释，不超过 140 字（可选）
02.使用工具
首先，定义模型调用函数
from openai import OpenAI # 设置 OpenAI 的 API 密钥和 API 基础 URL 使用 vLLM 的 API 服务器。 openai_api_key = "EMPTY" openai_api_base = "http://localhost:8000/v1" MODEL = "path/to/QwQ-32B" client = OpenAI( api_key=openai_api_key, base_url=openai_api_base, ) def chat_completion_request(messages, tools=None, tool_choice=None, model=MODEL): try: response = client.chat.completions.create( model=model, messages=messages, tools=tools, tool_choice="auto", ) return response except Exception as e: print("Unable to generate ChatCompletion response") print(f"Exception: {e}") raise
然后，我们定义一些实用工具，用于调用聊天完成 API 以及维护和跟踪对话状态。
def pretty_print_conversation(messages): role_to_color = { "system": "red", "user": "green", "assistant": "blue", "function": "magenta", } for message in messages: if message["role"] == "system": print(colored(f"system: {message['content']}\n", role_to_color[message["role"]])) elif message["role"] == "user": print(colored(f"user: {message['content']}\n", role_to_color[message["role"]])) elif message["role"] == "assistant" and message.get("function_call"): print(colored(f"assistant: {message['function_call']}\n", role_to_color[message["role"]])) elif message["role"] == "assistant" and not message.get("function_call"): print(colored(f"assistant: {message['content']}\n", role_to_color[message["role"]])) elif message["role"] == "function": print(colored(f"function ({message['name']}): {message['content']}\n", role_to_color[message["role"]]))
03.工具定义
这里假设了一个天气 API，并设置了一些函数规范和它进行交互。将这些函数规范传递给 Chat API，以便模型可以生成符合规范的函数参数。
tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "format": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location.", }, }, "required": ["location", "format"], }, } }, { "type": "function", "function": { "name": "get_n_day_weather_forecast", "description": "Get an N-day weather forecast", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "format": { "type": "string", "enum": ["celsius", "fahrenheit"], "description": "The temperature unit to use. Infer this from the users location.", }, "num_days": { "type": "integer", "description": "The number of days to forecast", } }, "required": ["location", "format", "num_days"] }, } }, ]
如果我们向模型询问当前的天气情况，它将会反问，希望获取到进一步的更多的参数信息。
messages = [] messages.append({"role": "user", "content": "hi ，can you tell me what's the weather like today"}) chat_response = chat_completion_request( messages, tools=tools ) print(chat_response) assistant_message = chat_response.choices[0].message messages.append(assistant_message) assistant_message
一旦我们通过对话提供缺失的参数信息，模型就会为我们生成适当的函数参数。
messages.append({"role": "user", "content": "I'm in Glasgow, Scotland."}) chat_response = chat_completion_request( messages, tools=tools ) assistant_message = chat_response.choices[0].message messages.append(assistant_message) assistant_message
通过不同的提示词，我们可以让它反问不同的问题以获取函数参数信息。
messages = [] messages.append({"role": "user", "content": "can you tell me, what is the weather going to be like in Glasgow, Scotland in next x days"}) chat_response = chat_completion_request( messages, tools=tools ) assistant_message = chat_response.choices[0].message messages.append(assistant_message) assistant_message messages.append({"role": "user", "content": "5 days"}) chat_response = chat_completion_request( messages, tools=tools ) chat_response.choices[0]
并行函数调用
支持一次提问中，并行调用多次函数
messages = [] messages.append({"role": "user", "content": "what is the weather going to be like in San Francisco and Glasgow over the next 4 days"}) chat_response = chat_completion_request( messages, tools=tools, model=MODEL ) assistant_message = chat_response.choices[0].message.tool_calls assistant_message
点击阅读原文 ，跳转模型合集
