OpenAI API error handling with rate limit backoff

# pip install tenacity
from openai import AsyncOpenAI, RateLimitError, APITimeoutError, APIConnectionError
from tenacity import (
    retry, stop_after_attempt, wait_exponential,
    retry_if_exception_type, before_sleep_log
)
import logging

client = AsyncOpenAI()
log = logging.getLogger(__name__)

@retry(
    retry=retry_if_exception_type((RateLimitError, APITimeoutError, APIConnectionError)),
    wait=wait_exponential(multiplier=1, min=2, max=60),
    stop=stop_after_attempt(5),
    before_sleep=before_sleep_log(log, logging.WARNING),
)
async def generate_embedding_with_retry(text: str) -> list[float]:
    response = await client.embeddings.create(
        model='text-embedding-3-small',
        input=text,
    )
    return response.data[0].embedding

# Handle non-retryable errors separately:
async def safe_embed(text: str) -> list[float] | None:
    try:
        return await generate_embedding_with_retry(text)
    except RateLimitError as e:
        log.error('Rate limit exhausted after retries', error=str(e))
        return None
    except Exception as e:
        log.error('Unexpected embedding error', error=str(e))
        return None