批次內容生產

import asyncio
import json
import os
import random

from openai import APIConnectionError, APIStatusError, AsyncOpenAI

client = AsyncOpenAI(base_url="https://www.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"], max_retries=0)
LIMIT = asyncio.Semaphore(8)  # requests in flight at the same time

PROMPT = (
    "Write a product description for an online store in a friendly, concrete tone. "
    "Use only the facts provided. Do not add awards, certifications or numbers that are not listed. "
    "Return 3 short paragraphs."
)


async def write(product, attempts=4):
    async with LIMIT:
        for i in range(attempts):
            try:
                resp = await client.chat.completions.create(
                    model="deepseek-v4.1-flash",
                    messages=[
                        {"role": "system", "content": PROMPT},
                        {"role": "user", "content": json.dumps(product, ensure_ascii=False)},
                    ],
                    max_tokens=600,
                    temperature=0.8,
                )
                return {"sku": product["sku"], "text": resp.choices[0].message.content}
            except APIConnectionError:
                pass  # network problem or timeout: retry
            except APIStatusError as e:
                if e.status_code != 429 and e.status_code < 500:
                    # 4xx means the request itself is wrong (or no balance): fix it, do not retry
                    return {"sku": product["sku"], "error": e.status_code}
            await asyncio.sleep(2 ** i + random.random())  # back off: ~1s, 2s, 4s, 8s
        return {"sku": product["sku"], "error": "gave up after retries"}


async def main(products):
    results = await asyncio.gather(*(write(p) for p in products))
    with open("descriptions.jsonl", "w", encoding="utf-8") as f:
        for r in results:
            f.write(json.dumps(r, ensure_ascii=False) + "\n")


products = [
    {"sku": "A1001", "name": "Ceramic mug", "material": "stoneware", "capacity_ml": 350, "dishwasher_safe": True},
]
asyncio.run(main(products))
# then send about 10% of the results to claude-sonnet-5-5 for a fact and tone check