benchmark/get_response_api.py

import os
from openai import OpenAI

def get_streaming_response(message="Who are you",enable_thinking=True):
    client = OpenAI(
        api_key="sk-de60fca86cd34af3a4ff9b0e893139f5",  # 替换为你的API Key
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
    )

    completion = client.chat.completions.create(
        model="qwen3-8b",
        messages=[
            {'role': 'system', 'content': 'You are a helpful assistant.'},
            {'role': 'user', 'content': message}
        ],
        extra_body={
            "enable_thinking": enable_thinking,
        },
        temperature=0,
        top_p=0.9,
        stream=True,
        stream_options={"include_usage": True}
    )

    reasoning_content = ""
    answer_content = ""
    is_answering = False

    for chunk in completion:
        if not chunk.choices:
            continue

        delta = chunk.choices[0].delta

        if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
            reasoning_content += delta.reasoning_content

        if hasattr(delta, "content") and delta.content:
            is_answering = True
            answer_content += delta.content

    return f"<think>{reasoning_content}</think>{answer_content}"


def get_response_template(message,model="meta-llama/Meta-Llama-3-8B-Instruct",client=OpenAI(
        api_key="EMPTY",
        base_url="http://127.0.0.1:8422/v1",
    )):
    
    prompt= message
    chat_response = client.chat.completions.create(
    model=model,
    messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": prompt},
        ],
    temperature = 0.8,
    )
    print("Chat response:", chat_response.choices[0].message.content)
    return chat_response.choices[0].message.content