Giới hạn yêu cầu

{
  "error": {
    "message": "Rate limit exceeded. Please retry later.",
    "type": "rate_limit_exceeded",
    "code": "rate_limit_exceeded",
    "retryable": true,
    "retry_after": 8
  }
}

Retry-After: 8

import random
import time
from openai import RateLimitError

def chat_with_rate_limit_retry(client, model, messages, attempts=4):
    for attempt in range(attempts):
        try:
            return client.with_options(max_retries=0).chat.completions.create(
                model=model,
                messages=messages,
            )
        except RateLimitError as exc:
            if attempt == attempts - 1:
                raise
            header = exc.response.headers.get("Retry-After")
            wait = float(header) if header else min(30, 2 ** attempt + random.random())
            time.sleep(wait)