k8s-manifest.yml

---
# chatbot-rag-app deploys "create-index" to install ELSER and load values.
# Then, it starts "api-frontend" to serve the application.
apiVersion: apps/v1
kind: Deployment
metadata:
  name: chatbot-rag-app
spec:
  replicas: 1
  selector:
    matchLabels:
      app: chatbot-rag-app
  template:
    metadata:
      labels:
        app: chatbot-rag-app
    spec:
      # For `LLM_TYPE=vertex`: create a volume for application_default_credentials.json
      volumes:
        - name: gcloud-credentials
          secret:
            secretName: gcloud-credentials
            optional: true  # only read when `LLM_TYPE=vertex`
      initContainers:
        - name: create-index
          image: &image ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app:latest
          command: &command [ "opentelemetry-instrument" ] # match image
          args: [ "flask", "create-index" ]
          # This recreates your configmap based on your .env file:
          # kubectl create configmap chatbot-rag-app-env --from-env-file=.env
          envFrom: &envFrom
            - configMapRef:
                name: chatbot-rag-app-env
      containers:
        - name: api-frontend
          image: *image
          command: *command
          args: [ "python", "api/app.py" ]
          ports:
            - containerPort: 4000
          envFrom: *envFrom
          # For `LLM_TYPE=vertex`: mount credentials to the path read by the google-cloud-sdk
          volumeMounts:
            - name: gcloud-credentials
              mountPath: /root/.config/gcloud
              readOnly: true
---
apiVersion: v1
kind: Service
metadata:
  name: api
spec:
  selector:
    app: chatbot-rag-app
  ports:
    - protocol: TCP
      port: 4000
      targetPort: 4000