5. Deployment with FastAPI

1. Pickle

Saving your Python object to a file.

python
import joblib
joblib.dump(model, "model.pkl")

2. API

Serving predictions via HTTP.

python
from fastapi import FastAPI
import joblib

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

@app.post("/predict")
def predict(features: list):
    return model.predict([features]).tolist()

Report an issue or suggest an improvement

Mark as Completed

Previous Next Lesson