Docker & Kubernetes — Containerized AI Services

# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
# Dockerfile -- multi-stage build for minimal production image
# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

# dockerfile_content = '''
# Stage 1: Build dependencies
# FROM python:3.11-slim AS builder
# WORKDIR /app
# COPY requirements.txt .
# RUN pip install --user --no-cache-dir -r requirements.txt

# Stage 2: Production image (smaller -- no build tools)
# FROM python:3.11-slim AS production
# WORKDIR /app
# COPY --from=builder /root/.local /root/.local
# ENV PATH=/root/.local/bin:PATH

# Copy application code
# COPY ./app ./app
# COPY ./models ./models   # pre-downloaded model files

# Non-root user for security
# RUN adduser --disabled-password --gecos '' apiuser
# USER apiuser

# Health check
# HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
#   CMD curl -f http://localhost:8000/health || exit 1

# Expose port
# EXPOSE 8000

# Startup command with gunicorn (multi-process for CPU) or uvicorn (single process + async)
# CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "4"]
# '''

# build: docker build -t ai-api:v1.0.0 .
# run:   docker run -p 8000:8000 --gpus all ai-api:v1.0.0
# push:  docker push your-registry/ai-api:v1.0.0

# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
# KUBERNETES DEPLOYMENT MANIFEST
# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
kubernetes_deployment = '''
apiVersion: apps/v1
kind: Deployment
metadata:
  name: ai-api-deployment
  labels:
    app: ai-api
    version: v1.0.0
spec:
  replicas: 3                          # 3 pods for availability
  selector:
    matchLabels:
      app: ai-api
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1                      # create 1 extra pod during update
      maxUnavailable: 0                # never take pod offline (zero-downtime)
  template:
    metadata:
      labels:
        app: ai-api
    spec:
      containers:
      - name: ai-api
        image: your-registry/ai-api:v1.0.0
        ports:
        - containerPort: 8000
        resources:
          requests:
            memory: "2Gi"
            cpu: "500m"
          limits:
            memory: "8Gi"
            cpu: "2000m"
            nvidia.com/gpu: 1           # request 1 GPU per pod
        env:
        - name: OPENAI_API_KEY
          valueFrom:
            secretKeyRef:               # secrets from Kubernetes Secrets (not plain env vars!)
              name: api-secrets
              key: openai-key
        readinessProbe:
          httpGet:
            path: /health
            port: 8000
          initialDelaySeconds: 60       # wait for model loading
          periodSeconds: 10
        livenessProbe:
          httpGet:
            path: /health
            port: 8000
          initialDelaySeconds: 90
          periodSeconds: 30
---
apiVersion: v1
kind: Service
metadata:
  name: ai-api-service
spec:
  selector:
    app: ai-api
  ports:
  - port: 80
    targetPort: 8000
  type: LoadBalancer                    # exposes via cloud load balancer
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: ai-api-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: ai-api-deployment
  minReplicas: 2
  maxReplicas: 20
  metrics:
  - type: Resource
    resource:
      name: cpu
      target:
        type: Utilization
        averageUtilization: 70          # scale up when CPU > 70%
'''

print("Kubernetes deployment manifest ready!")
print("Apply with: kubectl apply -f deployment.yaml")
print("Scale manually: kubectl scale deployment ai-api --replicas=5")
print("Check pods: kubectl get pods -l app=ai-api")
print("Logs: kubectl logs -l app=ai-api --tail=100")