基于阿里通义 Qwen3 混合推理模型才是优化 RAG 和 MCP 的最佳范式 原创

import os
import time
from openai import OpenAI
os.environ["DASHSCOPE_API_KEY"] = "sk-*************************"
client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
)
############################################
# Think
# 记录开始时间
start_time = time.time()
stream = client.chat.completions.create(
    # 模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
    model="qwen3-235b-a22b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "甲和乙从同一地点出发，甲先走2小时，速度5km/h，乙以15km/h追赶，多久追上？"},
    ],
    # Qwen3模型通过enable_thinking参数控制思考过程（开源版默认True，商业版默认False）
    extra_body={"enable_thinking": True},
    stream=True,
)
answer_content = ""
for chunk in stream:
    delta = chunk.choices[0].delta
    if delta.content is not None:
        answer_content += delta.content
print(answer_content)
# 记录结束时间并计算总耗时
end_time = time.time()
print(f"\n\n总耗时：{end_time - start_time:.2f}秒")

from qwen_agent.agents import Assistant
# Define LLM
llm_cfg = {
    'model': 'Qwen3-30B-A3B',
    # Use the endpoint provided by Alibaba Model Studio:
    # 'model_type': 'qwen_dashscope',
    # 'api_key': os.getenv('DASHSCOPE_API_KEY'),
    # Use a custom endpoint compatible with OpenAI API:
    'model_server': 'http://localhost:8000/v1',  # api_base
    'api_key': 'EMPTY',
    # Other parameters:
    # 'generate_cfg': {
    #         # Add: When the response content is `<think>this is the thought</think>this is the answer;
    #         # Do not add: When the response has been separated by reasoning_content and content.
    #         'thought_in_content': True,
    #     },
}
# Define Tools
tools = [
    {'mcpServers': {  # You can specify the MCP configuration file
            'time': {
                'command': 'uvx',
                'args': ['mcp-server-time', '--local-timeznotallow=Asia/Shanghai']
            },
            "fetch": {
                "command": "uvx",
                "args": ["mcp-server-fetch"]
            }
        }
    },
  'code_interpreter',  # Built-in tools
]
# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)
# Streaming generation
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
    pass
print(responses)

from transformers import AutoModelForCausalLM, AutoTokenizer
class QwenChatbot:
    def __init__(self, model_name="Qwen3-30B-A3B/Qwen3-30B-A3B"):
        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
        self.model = AutoModelForCausalLM.from_pretrained(model_name)
        self.history = []
    def generate_response(self, user_input):
        messages = self.history + [{"role": "user", "content": user_input}]
        text = self.tokenizer.apply_chat_template(
            messages,
            tokenize=False,
            add_generation_prompt=True
        )
        inputs = self.tokenizer(text, return_tensors="pt")
        response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
        response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
        # Update history
        self.history.append({"role": "user", "content": user_input})
        self.history.append({"role": "assistant", "content": response})
        return response
# Example Usage
if __name__ == "__main__":
    chatbot = QwenChatbot()
    # First input (without /think or /no_think tags, thinking mode is enabled by default)
    user_input_1 = "How many r's in strawberries?"
    print(f"User: {user_input_1}")
    response_1 = chatbot.generate_response(user_input_1)
    print(f"Bot: {response_1}")
    print("----------------------")
    # Second input with /no_think
    user_input_2 = "Then, how many r's in blueberries? /no_think"
    print(f"User: {user_input_2}")
    response_2 = chatbot.generate_response(user_input_2)
    print(f"Bot: {response_2}") 
    print("----------------------")
    # Third input with /think
    user_input_3 = "Really? /think"
    print(f"User: {user_input_3}")
    response_3 = chatbot.generate_response(user_input_3)
    print(f"Bot: {response_3}")