异步调用大模型

但又更多 prompt 时，可以异步调用大模型，加快效率，普通写法：

20 条 prompt：

import requests
import time
from openai import OpenAI

client = OpenAI(
    api_key="",
    base_url="https://open.bigmodel.cn/api/paas/v4/"
)

def call_large_model(prompt):
    completion = client.chat.completions.create(
        model="glm-4-plus",
        messages=[
            {"role": "system", "content": "你是一个聪明且富有创造力的小说作家"},
            {"role": "user",
             "content": prompt}
        ],
        top_p=0.7,
        temperature=0.9
    )
    return completion.choices[0].message

def main_sync():
    prompts = [f"说出数字，不用说其他内容 {i}" for i in range(20)]
    start_time = time.time()
    for prompt in prompts:
        size = call_large_model(prompt)
        print(f"{size}")
    print(f"Sync execution took {time.time() - start_time:.2f} seconds")

if __name__ == "__main__":
    main_sync()

异步写法：

import aiohttp
import asyncio
import time

API_KEY = ""
BASE_URL = "https://open.bigmodel.cn/api/paas/v4"

async def call_large_model(prompt, session):
    url = f"{BASE_URL}/chat/completions"
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    messages = [
        {"role": "system", "content": "你是一个聪明且富有创造力的小说作家"},
        {"role": "user", "content": prompt}
    ]
    payload = {
        "model": "glm-4-plus",
        "messages": messages,
        "top_p": 0.7,
        "temperature": 0.9
    }
    async with session.post(url, json=payload, headers=headers) as response:
        completion = await response.json()
        return completion['choices'][0]['message']

async def main_async():
    prompts = [f"说出数字，不用说其他内容 {i}" for i in range(20)]
    start_time = time.time()
    async with aiohttp.ClientSession() as session:
        tasks = [call_large_model(prompt, session) for prompt in prompts]
        results = await asyncio.gather(*tasks)
        for result in results:
            print(f"{result}")
    print(f"Async execution took {time.time() - start_time:.2f} seconds")

if __name__ == "__main__":
    asyncio.run(main_async())

 

opanai异步：

import asyncio
import time
from openai import AsyncOpenAI

# 创建异步客户端
client = AsyncOpenAI(
    base_url=',
    api_key=,  # ModelScope Token
)

# 设置额外参数
extra_body = {
    "enable_thinking": False,
    # "thinking_budget": 4096
}


async def process_request(user_query: str):
    """处理单个请求的异步函数"""
    response = await client.chat.completions.create(
        model='Qwen/Qwen3-235B-A22B',
        messages=[
            {
                'role': 'user',
                'content': user_query
            }
        ],
        stream=False,
        extra_body=extra_body
    )
    return response.choices[0].message.tool_calls


async def process_batch_requests(queries: list):
    """批量处理请求的异步函数"""
    tasks = [process_request(query) for query in queries]
    results = await asyncio.gather(*tasks)
    return results


# 使用示例
if __name__ == "__main__":
    queries = [
        "9.9和9.11谁大",
        "10.1和10.10哪个更大",
        "比较5.5和5.55的大小"
    ]

    # 运行异步批量处理
    start = time.time()
    results = asyncio.run(process_batch_requests(queries))

    # 打印所有结果
    for i, tool_calls in enumerate(results):
        print(f"查询 {queries[i]} 的结果:")
        print(tool_calls)
        print("-" * 50)

    end = time.time()
    print(f"处理完成，耗时 {end - start:.2f} 秒")