pip install -r requirements.txt
uvicorn src.serving_app:create_app --factory --reload --port 8000

FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY src/ src/
COPY configs/ configs/
EXPOSE 8000
CMD ["uvicorn", "src.serving_app:create_app", "--factory", "--host", "0.0.0.0", "--port", "8000"]

docker build -t model-server .
docker run -p 8000:8000 -v $(pwd)/models:/app/models model-server

apiVersion: apps/v1
kind: Deployment
metadata:
  name: model-server
spec:
  replicas: 3
  selector:
    matchLabels:
      app: model-server
  template:
    metadata:
      labels:
        app: model-server
    spec:
      containers:
        - name: server
          image: your-registry.docs.example.com/model-server:latest
          ports:
            - containerPort: 8000
          livenessProbe:
            httpGet:
              path: /health
              port: 8000
            initialDelaySeconds: 10
            periodSeconds: 15
          readinessProbe:
            httpGet:
              path: /ready
              port: 8000
            initialDelaySeconds: 5
            periodSeconds: 10
          resources:
            requests:
              memory: "512Mi"
              cpu: "500m"
            limits:
              memory: "2Gi"
              cpu: "2"

curl -X POST http://localhost:8000/predict \
  -H "Content-Type: application/json" \
  -d '{"features": {"age": 35, "income": 55000, "region": "north"}}'

curl -X POST http://localhost:8000/predict/batch \
  -H "Content-Type: application/json" \
  -d '{"instances": [{"age": 35, "income": 55000}, {"age": 42, "income": 72000}]}'

curl -X POST http://localhost:8000/predict \
  -H "Content-Type: application/json" \
  -H "X-Model-Version: canary_model" \
  -d '{"features": {"age": 35, "income": 55000}}'