Penanganan Kesalahan dan Batas Laju

Mengapa Kesalahan API Terjadi

Ikhtisar Jenis Kesalahan OpenAI

Menangkap Kesalahan dengan Try-Except

import openai

client = openai.OpenAI()

try:
    response = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': 'Hello!'}]
    )
    print(response.choices[0].message.content)
except openai.AuthenticationError as e:
    print('Bad API key. Check OPENAI_API_KEY environment variable.')
    raise  # do not retry
except openai.RateLimitError as e:
    print('Rate limited. Back off and retry.')
except openai.APIConnectionError as e:
    print('Network error:', e)
except openai.APIStatusError as e:
    print('Server error', e.status_code, e.message)

Memahami Batas Laju

Exponential Backoff: Strategi Percobaan Ulang yang Tepat

import time
import random
import openai

client = openai.OpenAI()

def call_with_backoff(messages, max_retries=5):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model='gpt-4o-mini',
                messages=messages
            )
        except openai.RateLimitError:
            if attempt == max_retries - 1:
                raise
            wait = (2 ** attempt) + random.uniform(0, 1)
            print(f'Rate limited. Waiting {wait:.1f}s (attempt {attempt+1})')
            time.sleep(wait)
        except (openai.APIConnectionError, openai.APIStatusError):
            if attempt == max_retries - 1:
                raise
            time.sleep(2 ** attempt)

Menggunakan Pustaka tenacity

from tenacity import retry, wait_random_exponential, stop_after_attempt
import openai

client = openai.OpenAI()

@retry(
    wait=wait_random_exponential(min=1, max=60),
    stop=stop_after_attempt(6)
)
def completion_with_backoff(**kwargs):
    return client.chat.completions.create(**kwargs)

response = completion_with_backoff(
    model='gpt-4o-mini',
    messages=[{'role': 'user', 'content': 'Tell me a joke.'}]
)
print(response.choices[0].message.content)

Konfigurasi Timeout

import openai

# Set a default timeout for all requests from this client
client = openai.OpenAI(timeout=30.0)

# Or override per request
try:
    response = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': 'Summarize the French Revolution.'}],
        timeout=60.0
    )
except openai.APITimeoutError:
    print('Request timed out. Try a shorter prompt or increase timeout.')

Menangani Kesalahan Autentikasi

import os
import openai

api_key = os.environ.get('OPENAI_API_KEY')
if not api_key:
    raise EnvironmentError(
        'OPENAI_API_KEY not set. Export it before running.'
    )

client = openai.OpenAI(api_key=api_key)

try:
    response = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': 'Hello'}]
    )
except openai.AuthenticationError:
    # Do NOT retry - the key itself is invalid
    raise RuntimeError('Invalid API key. Check OPENAI_API_KEY.')

Kuota vs Batas Laju

Mencatat Kesalahan untuk Penelusuran

import logging
import openai

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

client = openai.OpenAI()

def safe_completion(model, messages):
    try:
        response = client.chat.completions.create(
            model=model, messages=messages
        )
        return response
    except openai.RateLimitError as e:
        logger.warning(
            'Rate limit hit',
            extra={'model': model, 'error': str(e)}
        )
        raise
    except openai.APIStatusError as e:
        logger.error(
            'API server error',
            extra={
                'status_code': e.status_code,
                'request_id': e.request_id,
                'model': model
            }
        )
        raise

Penanganan Kesalahan dalam Aplikasi Produksi

Pemeriksaan Singkat

Rangkuman Pelajaran