[Python] is this right way to make multiple calls to llama 3.1 model?

def safe_invoke(llm, messages, retries=5, backoff_base=1.5):
for attempt in range(retries):
try:
return llm.invoke(messages)
except Exception as e:
if "429" in str(e):
sleep_time = backoff_base * (2 ** attempt) + random.uniform(0, 1)
print(f"[Rate Limit] Sleeping for {sleep_time:.2f} seconds (attempt {attempt + 1})...")
time.sleep(sleep_time)
else:
raise e
raise Exception("Max retries exceeded due to rate limiting.")

Continue reading...