Déploiement de modèles d'apprentissage automatique avec FastAPI

FastAPI for ML

FastAPI is perfect for serving ML models with high performance.

Basic Setup

from fastapi import FastAPI
import joblib

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

@app.post("/predict")
async def predict(data: dict):
    prediction = model.predict([data['features']])
    return {"prediction": prediction.tolist()}

Docker Deployment

FROM python:3.9
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
CMD ["uvicorn", "main:app", "--host", "0.0.0.0"]