Serverless Inference 오류 처리 모범 사례는 무엇인가요?

import openai

try:
    response = client.chat.completions.create(
        model="meta-llama/Llama-3.1-8B-Instruct",
        messages=messages
    )
except Exception as e:
    print(f"Error: {e}")
    # 적절하게 오류를 처리하세요

import time
from typing import Optional

def call_inference_with_retry(
    client, 
    messages, 
    model: str,
    max_retries: int = 3,
    base_delay: float = 1.0
) -> Optional[str]:
    for attempt in range(max_retries):
        try:
            response = client.chat.completions.create(
                model=model,
                messages=messages
            )
            return response.choices[0].message.content
        except Exception as e:
            if attempt == max_retries - 1:
                raise
            
            # 지수 백오프로 지연 시간 계산
            delay = base_delay * (2 ** attempt)
            print(f"Attempt {attempt + 1} failed, retrying in {delay}s...")
            time.sleep(delay)
    
    return None

def handle_inference_error(error):
    error_str = str(error)
    
    if "401" in error_str:
        # 인증 실패
        raise ValueError("Check your API key and project configuration")
    elif "402" in error_str:
        # 크레딧 부족
        raise ValueError("Insufficient credits")
    elif "429" in error_str:
        # 요청 속도 제한 초과
        return "retry"
    elif "500" in error_str or "503" in error_str:
        # 서버 오류
        return "retry"
    else:
        # 알 수 없는 오류
        raise

# 더 긴 응답을 위한 설정
client = openai.OpenAI(
    base_url='https://api.inference.wandb.ai/v1',
    api_key="your-api-key",
    timeout=60.0  # 60초 타임아웃
)