Deploying MaxAI NBC Model

Create Amazon EFS Access Points for AION NBC

To create EFS Access Point for AION NBC, follow the steps below:

1. Log in to the AWS Management Console.
2. Navigate to EFS via the search bar.
3. Select Access Points from the left navigation menu.
4. Click Create Access Point.
5. Provide the following details:

   Field	Value
   File system	Use the default or an existing EFS
   Name (optional)	cdp-aion-nfc
   Root directory path	/app/AION/model/nfc
   User ID	0
   Group ID	0
   Secondary group IDs	Leave blank
   Owner User ID	0
   Owner Group ID	0
   Access point permissions	0775

6. Click Create Access Point.

Deploy NFC Model via Devtron

To deploy the NFC model, follow the steps below:

1. Open Devtron dashboard, and navigate to the Chart Store and select Generic Helm Chart.
2. Click Configure & Deploy.
3. Under the Configuration section, paste and modify the following YAML template according to your environment.
4. NFC Helm Configuration Template is provided below.

   data:
     - apiVersion: v1
       kind: PersistentVolume
       metadata:
         name: aion-nbc-prod-pv
       spec:
         capacity:
           storage: 50Gi
         accessModes:
           - ReadWriteMany
         persistentVolumeReclaimPolicy: Retain
         storageClassName: efs-sc
         csi:
           driver: efs.csi.aws.com
           volumeHandle: <AWS Access Point Id>::<AWS File System ID>
   
     - apiVersion: v1
       kind: PersistentVolumeClaim
       metadata:
         name: aion-nbc-prod-pvc
       spec:
         accessModes:
           - ReadWriteMany
         resources:
           requests:
             storage: 50Gi
         storageClassName: efs-sc
     - apiVersion: v1
       kind: ConfigMap
       metadata:
         name: aion-cdp-nbc-prod-config
       data:
         config.ini: |
           [AUTH]
           client_id=test
           client_secret=test
     - apiVersion: apps/v1
       kind: Deployment
       metadata:
         name: cdp-aion-nbc-prod-deployment
       spec:
         replicas: 2
         selector:
           matchLabels:
             app: cdp-aion-nbc-prod
         template:
           metadata:
             labels:
               app: cdp-aion-nbc-prod
           spec:
             containers:
               - name: cdp-aion-nbc-prod-container
                 image: { provide image repository: image tag}
                 imagePullPolicy: Always
                 ports:
                   - containerPort: 8000
                 volumeMounts:
                   - mountPath: /app/AION/config
                     name: aion-nbc-prod-volume
                   - mountPath: /app/AION/model
                     name: aion-nbc-prod-pvc-volume
                 resources:
                   requests:
                     memory: "4000Mi"
                     cpu: "2"
                   limits:
                     memory: "14000Mi"
                     cpu: "3"  
             volumes:
               - name: aion-nbc-prod-volume
                 configMap:
                   name: aion-cdp-nbc-prod-config
               - name: aion-nbc-prod-pvc-volume
                 persistentVolumeClaim:
                   claimName: aion-nbc-prod-pvc
   
   
     - apiVersion: v1
       kind: Service
       metadata:
         name: cdp-aion-nbc-prod-service
       spec:
         ports:
           - name: http
             port: 8000
             protocol: TCP
             targetPort: 8000
         selector:
           app: cdp-aion-nbc-prod
    
     - apiVersion: networking.k8s.io/v1
       kind: Ingress
       metadata:
         annotations: <Add annotation related to environment>        
         labels:
           app.kubernetes.io/instance: cdp-aion-nbc-prod
         name: cdp-aion-nbc-prod
       spec:
         ingressClassName: alb
         rules:
           - host: <HOST_DETAILS>
             http:
               paths:
                 - backend:
                     service:
                       name: cdp-aion-nbc-prod-service
                       port:
                         number: 8000
                   path: /*
                   pathType: ImplementationSpecific
   
     - apiVersion: keda.sh/v1alpha1
       kind: ScaledObject
       metadata:
         name: cdp-nbc-prod-scaledobject
         namespace: default
       spec:
         scaleTargetRef:
           name: cdp-nbc-deployment
         pollingInterval: 30
         cooldownPeriod: 300
         minReplicaCount: 1
         maxReplicaCount: 2
         idleReplicaCount: 0
         restoreToOriginalReplicaCount: true
         advanced:
           horizontalPodAutoscalerConfig:
             behavior:
               scaleDown:
                 stabilizationWindowSeconds: 300
                 policies:
                   - type: Percent
                     value: 100
                     periodSeconds: 60
         triggers:
           - type: prometheus
             metadata:
               serverAddress: <PROMETHEUS_SERVER_URL>
               metricName: cpuusage
               query: sum(rate(container_cpu_usage_seconds_total{pod=~"aion-cdp-nbc.*",container_name!="POD"}[5m]))*100
               threshold: "80"
           - type: prometheus
             metadata:
               serverAddress: <PROMETHEUS_SERVER_URL>
               metricName: memoryusage
               query: avg(container_memory_usage_bytes{pod=~"aion-cdp-nbc.*"}) / sum(kube_pod_container_resource_limits{pod=~"aion-cdp-nbc.*",resource="memory"}) * 100
               threshold: "80"

   Note: Replace placeholders such as <IMAGE_REPOSITORY>, <IMAGE_TAG>, <AWS_ACCESS_POINT_ID>, <HOST_DETAILS>, <PROMETHEUS_SERVER_URL> and <EFS_FILE_SYSTEM_ID> with your actual values.

Post-Deployment Verification