Chapter 1: REST APIs for ML

FastAPI for ML Serving

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel, Field
import mlflow
import numpy as np

app = FastAPI(title="ML Model API", version="1.0.0")

# Load model at startup
model = None

@app.on_event("startup")
async def load_model():
    global model
    model = mlflow.sklearn.load_model("models:/churn-model/Production")

class PredictionRequest(BaseModel):
    features: list[float] = Field(..., min_length=10, max_length=10)
    customer_id: str

class PredictionResponse(BaseModel):
    customer_id: str
    prediction: int
    probability: float
    model_version: str

@app.post("/predict", response_model=PredictionResponse)
async def predict(request: PredictionRequest):
    try:
        features = np.array(request.features).reshape(1, -1)
        prediction = model.predict(features)[0]
        probability = model.predict_proba(features)[0][1]
        
        return PredictionResponse(
            customer_id=request.customer_id,
            prediction=int(prediction),
            probability=float(probability),
            model_version="2.1.0"
        )
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.get("/health")
async def health():
    return {"status": "healthy", "model_loaded": model is not None}

Key Takeaways

Summary

1. Use Pydantic for request/response validation
2. Load models at startup not per-request
3. Implement health checks for orchestration
4. Use async for better throughput

---

Next: Chapter 2: Model Serving Frameworks