LLM 애플리케이션 최적화를 위한 강력한 Python 데코레이터 5가지

from functools import lru_cache
import time

@lru_cache(maxsize=100)
def summarize_text(text: str) -> str:
    print("Sending text to LLM...")
    time.sleep(1) # A simulation of network delay
    return f"Summary of {len(text)} characters."

print(summarize_text("The quick brown fox.")) # Takes one second
print(summarize_text("The quick brown fox.")) # Instant

from diskcache import Cache

cache = Cache(".local_llm_cache")

@cache.memoize(expire=86400) # Cached for 24 hours
def fetch_llm_response(prompt: str) -> str:
    print("Calling expensive LLM API...")
    # Replace this by an actual LLM API call
    time.sleep(2) # API latency simulation
    return f"Response to: {prompt}"

from tenacity import retry, wait_exponential, stop_after_attempt, retry_if_exception_type

@retry(
    wait=wait_exponential(multiplier=2, min=2, max=10),
    stop=stop_after_attempt(4),
    retry=retry_if_exception_type(RateLimitError)
)
def call_flaky_llm_api(prompt: str):
    print("Attempting to call API...")
    # ...(중략)
    return "Success!"

from magentic import prompt
from pydantic import BaseModel

class CapitalInfo(BaseModel):
    capital: str
    population: int

@prompt("What is the capital and population of {country}?")
def get_capital_info(country: str) -> CapitalInfo:
    ... # No function body needed here!