限流说明

import asyncio
import os

from openai import AsyncOpenAI

client = AsyncOpenAI(base_url="https://open.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"], max_retries=4)
limit = asyncio.Semaphore(8)  # 同时在跑的请求数，按自己的业务调整


async def summarize(text):
    async with limit:
        resp = await client.chat.completions.create(
            model="deepseek-v4.1-flash",
            messages=[{"role": "user", "content": f"用一句话总结：{text}"}],
        )
        return resp.choices[0].message.content


async def main(texts):
    return await asyncio.gather(*(summarize(t) for t in texts))

import OpenAI from 'openai'

const client = new OpenAI({ baseURL: 'https://open.tutujin.com/v1', apiKey: process.env.TUTUJIN_API_KEY, maxRetries: 4 })

// 用固定数量的 worker 处理队列，limit 就是并发上限
async function mapWithConcurrency(items, limit, fn) {
  const results = new Array(items.length)
  let next = 0
  async function worker() {
    while (next < items.length) {
      const i = next++
      results[i] = await fn(items[i])
    }
  }
  await Promise.all(Array.from({ length: limit }, worker))
  return results
}

const summaries = await mapWithConcurrency(texts, 8, async (text) => {
  const resp = await client.chat.completions.create({
    model: 'deepseek-v4.1-flash',
    messages: [{ role: 'user', content: `用一句话总结：${text}` }],
  })
  return resp.choices[0].message.content
})