Giới hạn tốc độ

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

Retry-After: 60  # Seconds to wait before retrying

import time
from openai import OpenAI, RateLimitError

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.tokenlab.sh/v1"
)

def make_request_with_backoff(messages, max_retries=5):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model="gpt-4o",
                messages=messages
            )
        except RateLimitError as e:
            if attempt == max_retries - 1:
                raise

            wait_time = 2 ** attempt  # 1, 2, 4, 8, 16 seconds
            print(f"Rate limited. Waiting {wait_time}s...")
            time.sleep(wait_time)

import asyncio
from collections import deque

class RateLimitedClient:
    def __init__(self, requests_per_minute=1000):
        self.rpm = requests_per_minute
        self.interval = 60 / requests_per_minute
        self.last_request = 0

    async def request(self, messages):
        # Wait if needed to respect rate limit
        now = asyncio.get_event_loop().time()
        wait_time = max(0, self.last_request + self.interval - now)
        if wait_time > 0:
            await asyncio.sleep(wait_time)

        self.last_request = asyncio.get_event_loop().time()
        return await self.client.chat.completions.create(
            model="gpt-4o",
            messages=messages
        )

def process_batch(items, batch_size=50, delay=1):
    results = []
    for i in range(0, len(items), batch_size):
        batch = items[i:i + batch_size]
        for item in batch:
            result = client.chat.completions.create(
                model="gpt-4o",
                messages=[{"role": "user", "content": item}]
            )
            results.append(result)
        time.sleep(delay)  # Pause between batches
    return results