Merge pull request #897 from open-webui/main

dev

kubernetes/helm/values-minikube.yaml

+ollama:
+  resources:
+    requests:
+      cpu: "2000m"
+      memory: "2Gi"
+    limits:
+      cpu: "4000m"
+      memory: "4Gi"
+      nvidia.com/gpu: "0"
+  service:
+    type: ClusterIP
+  gpu:
+    enabled: false
+
+webui:
+  resources:
+    requests:
+      cpu: "500m"
+      memory: "500Mi"
+    limits:
+      cpu: "1000m"
+      memory: "1Gi"
+  ingress:
+    enabled: true
+    host: open-webui.minikube.local
+  service:
+    type: NodePort

kubernetes/helm/values.yaml

-namespace: ollama-namespace
+nameOverride: ""
 
 ollama:
+  annotations: {}
+  podAnnotations: {}
   replicaCount: 1
-  image: ollama/ollama:latest
-  servicePort: 11434
-  resources:
-    limits:
-      cpu: "2000m"
-      memory: "2Gi"
-      nvidia.com/gpu: "0"
-  volumeSize: 1Gi
+  image:
+    repository: ollama/ollama
+    tag: latest
+    pullPolicy: Always
+  resources: {}
+  persistence:
+    enabled: true
+    size: 30Gi
+    existingClaim: ""
+    accessModes:
+    - ReadWriteOnce
+    storageClass: ""
+    selector: {}
+    annotations: {}
   nodeSelector: {}
-  tolerations: []
+  # -- If using a special runtime container such as nvidia, set it here.
+  runtimeClassName: ""
+  tolerations:
+  - key: nvidia.com/gpu
+    operator: Exists
+    effect: NoSchedule
   service:
     type: ClusterIP
+    annotations: {}
+    port: 80
+    containerPort: 11434
   gpu:
+    # -- Enable additional ENV values to help Ollama discover GPU usage
     enabled: false
 
 webui:
+  annotations: {}
+  podAnnotations: {}
   replicaCount: 1
-  image: ghcr.io/ollama-webui/ollama-webui:main
-  servicePort: 8080
-  resources:
-    limits:
-      cpu: "500m"
-      memory: "500Mi"
+  image:
+    repository: ghcr.io/open-webui/open-webui
+    tag: ""
+    pullPolicy: Always
+  resources: {}
   ingress:
-    enabled: true
-    annotations:
-    # Use appropriate annotations for your Ingress controller, e.g., for NGINX:
+    enabled: false
+    class: ""
+    # -- Use appropriate annotations for your Ingress controller, e.g., for NGINX:
     # nginx.ingress.kubernetes.io/rewrite-target: /
-    host: ollama.minikube.local
-  volumeSize: 1Gi
+    annotations: {}
+    host: ""
+    tls: false
+    existingSecret: ""
+  persistence:
+    enabled: true
+    size: 2Gi
+    existingClaim: ""
+    # -- If using multiple replicas, you must update accessModes to ReadWriteMany
+    accessModes:
+    - ReadWriteOnce
+    storageClass: ""
+    selector: {}
+    annotations: {}
   nodeSelector: {}
   tolerations: []
   service:
-    type: NodePort
\ No newline at end of file
+    type: ClusterIP
+    annotations: {}
+    port: 80
+    containerPort: 8080
+    nodePort: ""

kubernetes/manifest/base/ollama-service.yaml

@@ -2,7 +2,7 @@ apiVersion: v1
 kind: Service
 metadata:
   name: ollama-service
-  namespace: ollama-namespace
+  namespace: open-webui
 spec:
   selector:
     app: ollama

kubernetes/manifest/base/ollama-statefulset.yaml

@@ -2,7 +2,7 @@ apiVersion: apps/v1
 kind: StatefulSet
 metadata:
   name: ollama
-  namespace: ollama-namespace
+  namespace: open-webui
 spec:
   serviceName: "ollama"
   replicas: 1
@@ -20,9 +20,13 @@ spec:
         ports:
         - containerPort: 11434
         resources:
-          limits:
+          requests:
             cpu: "2000m"
             memory: "2Gi"
+          limits:
+            cpu: "4000m"
+            memory: "4Gi"
+            nvidia.com/gpu: "0"
         volumeMounts:
         - name: ollama-volume
           mountPath: /root/.ollama
@@ -34,4 +38,4 @@ spec:
       accessModes: [ "ReadWriteOnce" ]
       resources:
         requests:
-          storage: 1Gi
\ No newline at end of file
+          storage: 30Gi
\ No newline at end of file

kubernetes/manifest/base/ollama-namespace.yaml → kubernetes/manifest/base/open-webui.yaml

 apiVersion: v1
 kind: Namespace
 metadata:
-  name: ollama-namespace
\ No newline at end of file
+  name: open-webui
\ No newline at end of file

kubernetes/manifest/base/webui-deployment.yaml

 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: ollama-webui-deployment
-  namespace: ollama-namespace
+  name: open-webui-deployment
+  namespace: open-webui
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app: ollama-webui
+      app: open-webui
   template:
     metadata:
       labels:
-        app: ollama-webui
+        app: open-webui
     spec:
       containers:
-      - name: ollama-webui
-        image: ghcr.io/ollama-webui/ollama-webui:main
+      - name: open-webui
+        image: ghcr.io/open-webui/open-webui:main
         ports:
         - containerPort: 8080
         resources:
-          limits:
+          requests:
             cpu: "500m"
             memory: "500Mi"
+          limits:
+            cpu: "1000m"
+            memory: "1Gi"
         env:
         - name: OLLAMA_API_BASE_URL
-          value: "http://ollama-service.ollama-namespace.svc.cluster.local:11434/api"
+          value: "http://ollama-service.open-webui.svc.cluster.local:11434/api"
         tty: true
+        volumeMounts:
+        - name: webui-volume
+          mountPath: /app/backend/data
+      volumes:
+      - name: webui-volume
+        persistentVolumeClaim:
+          claimName: ollama-webui-pvc          
\ No newline at end of file

kubernetes/manifest/kustomization.yaml

 resources:
-- base/ollama-namespace.yaml
+- base/open-webui.yaml
 - base/ollama-service.yaml
 - base/ollama-statefulset.yaml
 - base/webui-deployment.yaml
 - base/webui-service.yaml
 - base/webui-ingress.yaml
+- base/webui-pvc.yaml
 
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization