refactor: migrate open-webui to interface layer and remove legacy ai-agents manifests

ai-agents/manifests.yaml

@@ -1,200 +0,0 @@
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: ollama
-  namespace: ai-agents
-spec:
-  progressDeadlineSeconds: 600
-  replicas: 1
-  revisionHistoryLimit: 10
-  selector:
-    matchLabels:
-      app: ollama
-  strategy:
-    rollingUpdate:
-      maxSurge: 25%
-      maxUnavailable: 25%
-    type: RollingUpdate
-  template:
-    metadata:
-      creationTimestamp: null
-      labels:
-        app: ollama
-    spec:
-      containers:
-      - image: ollama/ollama:latest
-        imagePullPolicy: Always
-        name: ollama
-        ports:
-        - containerPort: 11434
-          protocol: TCP
-        resources:
-          requests:
-            cpu: '2'
-            memory: 4Gi
-        terminationMessagePath: /dev/termination-log
-        terminationMessagePolicy: File
-        volumeMounts:
-        - mountPath: /root/.ollama
-          name: ollama-data
-      dnsPolicy: ClusterFirst
-      restartPolicy: Always
-      schedulerName: default-scheduler
-      securityContext: {}
-      terminationGracePeriodSeconds: 30
-      volumes:
-      - name: ollama-data
-        persistentVolumeClaim:
-          claimName: ollama-pvc
-
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: open-webui
-  namespace: ai-agents
-spec:
-  progressDeadlineSeconds: 600
-  replicas: 1
-  revisionHistoryLimit: 10
-  selector:
-    matchLabels:
-      app: open-webui
-  strategy:
-    rollingUpdate:
-      maxSurge: 25%
-      maxUnavailable: 25%
-    type: RollingUpdate
-  template:
-    metadata:
-      creationTimestamp: null
-      labels:
-        app: open-webui
-    spec:
-      containers:
-      - env:
-        - name: OLLAMA_BASE_URL
-          value: http://ollama.ai-agents.svc.cluster.local:11434
-        image: ghcr.io/open-webui/open-webui:main
-        imagePullPolicy: IfNotPresent
-        name: open-webui
-        ports:
-        - containerPort: 8080
-          protocol: TCP
-        resources: {}
-        terminationMessagePath: /dev/termination-log
-        terminationMessagePolicy: File
-        volumeMounts:
-        - mountPath: /app/backend/data
-          name: open-webui-data
-      dnsPolicy: ClusterFirst
-      restartPolicy: Always
-      schedulerName: default-scheduler
-      securityContext: {}
-      terminationGracePeriodSeconds: 30
-      volumes:
-      - name: open-webui-data
-        persistentVolumeClaim:
-          claimName: open-webui-pvc
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: ollama
-  namespace: ai-agents
-spec:
-  internalTrafficPolicy: Cluster
-  ipFamilies:
-  - IPv4
-  ipFamilyPolicy: SingleStack
-  ports:
-  - port: 11434
-    protocol: TCP
-    targetPort: 11434
-  selector:
-    app: ollama
-  sessionAffinity: None
-  type: ClusterIP
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: open-webui
-  namespace: ai-agents
-spec:
-  allocateLoadBalancerNodePorts: true
-  externalTrafficPolicy: Cluster
-  internalTrafficPolicy: Cluster
-  ipFamilies:
-  - IPv4
-  ipFamilyPolicy: SingleStack
-  ports:
-  - nodePort: 31583
-    port: 80
-    protocol: TCP
-    targetPort: 8080
-  selector:
-    app: open-webui
-  sessionAffinity: None
-  type: LoadBalancer
-
----
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  finalizers:
-  - kubernetes.io/pvc-protection
-  name: ollama-pvc
-  namespace: ai-agents
-spec:
-  accessModes:
-  - ReadWriteOnce
-  resources:
-    requests:
-      storage: 20Gi
-  storageClassName: longhorn
-  volumeMode: Filesystem
-
----
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  finalizers:
-  - kubernetes.io/pvc-protection
-  name: open-webui-pvc
-  namespace: ai-agents
-spec:
-  accessModes:
-  - ReadWriteOnce
-  resources:
-    requests:
-      storage: 5Gi
-  storageClassName: longhorn
-  volumeMode: Filesystem
-
----
-apiVersion: networking.k8s.io/v1
-kind: Ingress
-metadata:
-  name: applaud-ingress
-  namespace: ai-agents
-  annotations:
-    k8s.apisix.apache.org/enable-websocket: "true"
-spec:
-  ingressClassName: apisix
-  rules:
-  - host: ai.applaude.net
-    http:
-      paths:
-      - backend:
-          service:
-            name: open-webui
-            port:
-              number: 80
-        path: /
-        pathType: Prefix
-
-

interface/k8s/kustomization.yaml

@@ -1,4 +1,4 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
-  - placeholder.yaml
+  - open-webui/

interface/k8s/open-webui/deployment.yaml

@@ -0,0 +1,60 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: open-webui
+  namespace: interface
+  labels:
+    app.kubernetes.io/name: open-webui
+spec:
+  replicas: 1
+  revisionHistoryLimit: 3
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: open-webui
+  strategy:
+    type: Recreate # Better for single PVCs
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: open-webui
+    spec:
+      containers:
+      - name: open-webui
+        # Pinning to a specific version is recommended, but keeping main if user prefers.
+        # Alternatively, using a recent stable tag like v0.3.32
+        image: ghcr.io/open-webui/open-webui:main
+        imagePullPolicy: IfNotPresent
+        env:
+        - name: OLLAMA_BASE_URL
+          value: "http://litellm.ai-core.svc.cluster.local:4000" # Pointing to LiteLLM router!
+        - name: WEBUI_AUTH
+          value: "False" # Based on default, keeping it simple or whatever they had
+        ports:
+        - containerPort: 8080
+          protocol: TCP
+        resources:
+          requests:
+            cpu: 250m
+            memory: 512Mi
+          limits:
+            cpu: 2000m
+            memory: 2Gi
+        livenessProbe:
+          httpGet:
+            path: /health
+            port: 8080
+          initialDelaySeconds: 30
+          periodSeconds: 15
+        readinessProbe:
+          httpGet:
+            path: /health
+            port: 8080
+          initialDelaySeconds: 10
+          periodSeconds: 5
+        volumeMounts:
+        - mountPath: /app/backend/data
+          name: open-webui-data
+      volumes:
+      - name: open-webui-data
+        persistentVolumeClaim:
+          claimName: open-webui-pvc

interface/k8s/open-webui/ingress.yaml

@@ -0,0 +1,20 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: open-webui-ingress
+  namespace: interface
+  annotations:
+    k8s.apisix.apache.org/enable-websocket: "true"
+spec:
+  ingressClassName: apisix
+  rules:
+  - host: ai.applaude.net
+    http:
+      paths:
+      - backend:
+          service:
+            name: open-webui
+            port:
+              number: 80
+        path: /
+        pathType: Prefix

interface/k8s/open-webui/kustomization.yaml

@@ -0,0 +1,7 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - deployment.yaml
+  - service.yaml
+  - pvc.yaml
+  - ingress.yaml

interface/k8s/open-webui/pvc.yaml

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: open-webui-pvc
+  namespace: interface
+  labels:
+    app.kubernetes.io/name: open-webui
+spec:
+  accessModes:
+  - ReadWriteOnce
+  resources:
+    requests:
+      storage: 5Gi
+  storageClassName: longhorn

interface/k8s/open-webui/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: open-webui
+  namespace: interface
+  labels:
+    app.kubernetes.io/name: open-webui
+spec:
+  ports:
+  - port: 80
+    targetPort: 8080
+    protocol: TCP
+  selector:
+    app.kubernetes.io/name: open-webui
+  type: ClusterIP # We use Ingress now instead of LoadBalancer with NodePort

interface/k8s/placeholder.yaml

@@ -1,7 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: interface-gitops-placeholder
-  namespace: interface
-data:
-  note: "Replace with Slack bot and HQ dashboard workloads when ready."