###
​### 關掉 Qwen3.5 thinking mode.
### 關掉thinking mode, 可以省掉不少時間和算力
###​​

​import openai

​​base_url="http://127.0.0.1:8080/"
model="Qwen3.5-27B-UD-Q3_K_XL.gguf"
api_key="sk-xxxxxx"

response = client.chat.completions.create(
        model=model,
        messages=[
            {
                "role": "user",
                "content": "Who are you?"
            }
        ],
        extra_body={
            "chat_template_kwargs": {"enable_thinking": False}
        },
        tools = tools,
        tool_choice="auto"
)

​​response_message = response.choices[0].message

​print(response_message)