Best Practices

FROM python:3.11-slim

WORKDIR /app

# Install dependencies first (cached layer)
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY app/ ./app/
COPY models/ ./models/

EXPOSE 8000

CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "4"]

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

@app.get("/health/ready")
async def readiness():
    if not ml_models.get("classifier"):
        raise HTTPException(503, "Model not loaded")
    return {"status": "ready", "models": list(ml_models.keys())}

import logging, time
from fastapi import Request

@app.middleware("http")
async def log_requests(request: Request, call_next):
    start = time.time()
    response = await call_next(request)
    duration = time.time() - start
    logging.info(
        f"{request.method} {request.url.path} "
        f"status={response.status_code} "
        f"duration={duration:.3f}s"
    )
    return response

from fastapi.testclient import TestClient
from app.main import app

client = TestClient(app)

def test_health():
    response = client.get("/health")
    assert response.status_code == 200

def test_predict():
    response = client.post(
        "/predict",
        json={"text": "test input"},
        headers={"X-API-Key": "test-key"}
    )
    assert response.status_code == 200
    assert "prediction" in response.json()