apiVersion: v1
kind: Namespace
metadata:
  name: local-ai
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: local-ai
  namespace: local-ai
  labels:
    app: local-ai
spec:
  selector:
    matchLabels:
      app: local-ai
  replicas: 1
  template:
    metadata:
      labels:
        app: local-ai
      name: local-ai
    spec:
      containers:
        - name: local-ai
          image: quay.io/go-skynet/local-ai:latest
          env:
          - name: THREADS
            value: "14"
          - name: CONTEXT_SIZE
            value: "512"
          - name: MODELS_PATH
            value: /models
          volumeMounts:
          - mountPath: /models
            name: models
      volumes:
      - name: models
        persistentVolumeClaim:
          claimName: models
---
apiVersion: v1
kind: Service
metadata:
  name: local-ai
  namespace: local-ai
  # If using AWS, you'll need to override the default 60s load balancer idle timeout
  # annotations:
  #   service.beta.kubernetes.io/aws-load-balancer-connection-idle-timeout: "1200"
spec:
  selector:
    app: local-ai
  type: LoadBalancer
  ports:
    - protocol: TCP
      port: 8080
      targetPort: 8080