監控與記錄

使用 FastAPI 將 AI 佈署到生產環境

Matt Eckerle

Software and Data Engineering Leader

為什麼要監控與記錄？

無法在正式環境除錯
監控程式需簡易健檢
長期記錄關鍵指標

監控與記錄軟體

設定自訂記錄

載入 uvicorn 錯誤記錄器

在應用啟動時加入自訂記錄

在端點加入自訂記錄

from fastapi import FastAPI
import logging

logger = logging.getLogger(
    'uvicorn.error'
)

app = FastAPI()
logger.info("App is running!")


@app.get('/')
async def main():
    logger.debug('GET /')
    return 'ok'

載入模型時寫入記錄

from fastapi import FastAPI
import logging
import joblib 

logger = logging.getLogger('uvicorn.error')


model = joblib.load('penguin_classifier.pkl')
logger.info("Penguin classifier loaded successfully.")

app = FastAPI()

用中介層記錄處理時間

from fastapi import FastAPI, Request
import logging
import time
logger = logging.getLogger('uvicorn.error')
app = FastAPI()

@app.middleware("http")
async def log_process_time(request: Request, call_next):
    start_time = time.perf_counter()
    response = await call_next(request)
    process_time = time.perf_counter() - start_time
    logger.info(f"Process time was {process_time} seconds.")
    return response

¹ https://fastapi.tiangolo.com/tutorial/middleware/

設定記錄層級

Python 記錄層級

uvicorn main:app --log-level debug

監控

from fastapi import FastAPI

app = FastAPI()

@app.get("/health")
async def get_health():
    return {"status": "OK"}

「I'm ok!」

與監控分享模型參數

from fastapi import FastAPI
import joblib

model = joblib.load(
    'penguin_classifier.pkl'
)
app = FastAPI()

@app.get("/health")
async def get_health():
    params = model.get_params()
    return {"status": "OK",
            "params": params}

「I'm ok!」
「Here are some fun facts about me!」

一起來練習吧！

使用 FastAPI 將 AI 佈署到生產環境