Merge pull request #101 from okamototk/tika-support

feat: add Apache Tika dependency

.github/workflows/helm-release.yml

@@ -28,6 +28,7 @@ jobs:
         run: |
           helm repo add ollama https://otwld.github.io/ollama-helm/
           helm repo add open-webui https://helm.openwebui.com/
+          helm repo add tika https://apache.jfrog.io/artifactory/tika/
 
       - name: Run chart-releaser
         uses: helm/chart-releaser-action@v1.6.0

charts/open-webui/Chart.lock

@@ -1,9 +1,12 @@
 dependencies:
 - name: ollama
   repository: https://otwld.github.io/ollama-helm/
-  version: 0.59.0
+  version: 0.64.0
 - name: pipelines
   repository: https://helm.openwebui.com
   version: 0.0.4
-digest: sha256:bfba828139ce6280e2fc9020cb933b8760e89ff1bbc66bee443d292af7ac1db1
-generated: "2024-09-22T12:16:31.226566428-06:00"
+- name: tika
+  repository: https://apache.jfrog.io/artifactory/tika
+  version: 2.9.0
+digest: sha256:91c12b702598527a8b602af6f229f975abc8bd7cf95c31324bc013bb919ff14e
+generated: "2024-11-07T14:14:55.798831-07:00"

charts/open-webui/Chart.yaml

@@ -1,7 +1,7 @@
 apiVersion: v2
 name: open-webui
-version: 3.2.0
-appVersion: "0.3.24"
+version: 3.6.0
+appVersion: "0.3.35"
 
 home: https://www.openwebui.com/
 icon: https://raw.githubusercontent.com/open-webui/open-webui/main/static/favicon.png
@@ -36,3 +36,7 @@ dependencies:
       - child: service
         parent: pipelines.service
     condition: pipelines.enabled
+  - name: tika
+    repository: https://apache.jfrog.io/artifactory/tika
+    version: ">=2.9.0"
+    condition: tika.enabled

charts/open-webui/README.md

@@ -1,6 +1,6 @@
 # open-webui
 
-![Version: 3.2.0](https://img.shields.io/badge/Version-3.2.0-informational?style=flat-square) ![AppVersion: 0.3.24](https://img.shields.io/badge/AppVersion-0.3.24-informational?style=flat-square)
+![Version: 3.6.0](https://img.shields.io/badge/Version-3.6.0-informational?style=flat-square) ![AppVersion: 0.3.35](https://img.shields.io/badge/AppVersion-0.3.35-informational?style=flat-square)
 
 Open WebUI: A User-Friendly Web Interface for Chat Interactions 👋
 
@@ -32,6 +32,7 @@ helm upgrade --install open-webui open-webui/open-webui
 
 | Repository | Name | Version |
 |------------|------|---------|
+| https://apache.jfrog.io/artifactory/tika | tika | >=2.9.0 |
 | https://helm.openwebui.com | pipelines | >=0.0.1 |
 | https://otwld.github.io/ollama-helm/ | ollama | >=0.24.0 |
 
@@ -43,7 +44,7 @@ helm upgrade --install open-webui open-webui/open-webui
 | annotations | object | `{}` |  |
 | clusterDomain | string | `"cluster.local"` | Value of cluster domain |
 | containerSecurityContext | object | `{}` | Configure container security context ref: <https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-containe> |
-| extraEnvVars | list | `[{"name":"OPENAI_API_KEY","value":"0p3n-w3bu!"}]` | Env vars added to the configmap and mounted to the Open WebUI deployment. Most up-to-date environment variables can be found here: https://docs.openwebui.com/getting-started/env-configuration/ |
+| extraEnvVars | list | `[{"name":"OPENAI_API_KEY","value":"0p3n-w3bu!"}]` | Env vars added to the Open WebUI deployment. Most up-to-date environment variables can be found here: https://docs.openwebui.com/getting-started/env-configuration/ |
 | extraEnvVars[0] | object | `{"name":"OPENAI_API_KEY","value":"0p3n-w3bu!"}` | Default API key value for Pipelines. Should be updated in a production deployment, or be changed to the required API key if not using Pipelines |
 | image | object | `{"pullPolicy":"IfNotPresent","repository":"ghcr.io/open-webui/open-webui","tag":""}` | Open WebUI image tags can be found here: https://github.com/open-webui/open-webui/pkgs/container/open-webui |
 | imagePullSecrets | list | `[]` | Configure imagePullSecrets to use private registry ref: <https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry> |
@@ -66,6 +67,7 @@ helm upgrade --install open-webui open-webui/open-webui
 | persistence.selector | object | `{}` |  |
 | persistence.size | string | `"2Gi"` |  |
 | persistence.storageClass | string | `""` |  |
+| persistence.subPath | string | `""` | Subdirectory of Open WebUI PVC to mount. Useful if root directory is not empty. |
 | pipelines.enabled | bool | `true` | Automatically install Pipelines chart to extend Open WebUI functionality using Pipelines: https://github.com/open-webui/pipelines |
 | pipelines.extraEnvVars | list | `[]` | This section can be used to pass required environment variables to your pipelines (e.g. Langfuse hostname) |
 | podAnnotations | object | `{}` |  |
@@ -73,8 +75,11 @@ helm upgrade --install open-webui open-webui/open-webui
 | replicaCount | int | `1` |  |
 | resources | object | `{}` |  |
 | service | object | `{"annotations":{},"containerPort":8080,"labels":{},"loadBalancerClass":"","nodePort":"","port":80,"type":"ClusterIP"}` | Service values to expose Open WebUI pods to cluster |
+| tika.enabled | bool | `false` | Automatically install Apache Tika to extend Open WebUI |
 | tolerations | list | `[]` | Tolerations for pod assignment |
 | topologySpreadConstraints | list | `[]` | Topology Spread Constraints for pod assignment |
+| volumeMounts | object | `{"container":[],"initContainer":[]}` | Configure container volume mounts ref: <https://kubernetes.io/docs/tasks/configure-pod-container/configure-volume-storage/> |
+| volumes | list | `[]` | Configure pod volumes ref: <https://kubernetes.io/docs/tasks/configure-pod-container/configure-volume-storage/> |
 
 ----------------------------------------------
 

charts/open-webui/templates/configmap.yaml

@@ -1,22 +0,0 @@
-{{- if or .Values.extraEnvVars .Values.ollama.enabled }}
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: {{ include "open-webui.name" . }}-env
-  labels:
-    {{- include "open-webui.labels" . | nindent 4 }}
-data:
-  {{- if .Values.ollama.enabled }}
-  OLLAMA_BASE_URLS: {{ include "ollamaBaseUrls" . | quote }}
-  {{- else }}
-  ENABLE_OLLAMA_API: "False"
-  {{- end }}
-  {{- if .Values.pipelines.enabled }}
-  OPENAI_API_BASE_URL: {{ include "pipelines.serviceEndpoint" . }}
-  {{- else if .Values.openaiBaseApiUrl }}
-  OPENAI_API_BASE_URL: {{ .Values.openaiBaseApiUrl | quote }}
-  {{- end }}
-  {{- range .Values.extraEnvVars }}
-  {{ .name }}: {{ .value | quote }}
-  {{- end }}
-{{- end }}

charts/open-webui/templates/workload-manager.yaml

@@ -47,6 +47,12 @@ spec:
         volumeMounts:
         - name: data
           mountPath: /tmp/app-data
+          {{- if .Values.persistence.subPath }}
+          subPath: {{ .Values.persistence.subPath }}
+          {{- end }}
+        {{- with .Values.volumeMounts.initContainer }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
       enableServiceLinks: false
       automountServiceAccountToken: false
       {{- with .Values.podSecurityContext }}
@@ -72,10 +78,34 @@ spec:
         volumeMounts:
         - name: data
           mountPath: /app/backend/data
-        {{- if or .Values.extraEnvVars .Values.ollama.enabled }}
-        envFrom:
-        - configMapRef:
-            name: {{ include "open-webui.name" . }}-env
+          {{- if .Values.persistence.subPath }}
+          subPath: {{ .Values.persistence.subPath }}
+          {{- end }}
+        {{- with .Values.volumeMounts.container }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+        env:
+        {{- if or .Values.ollamaUrls .Values.ollama.enabled }}
+        - name: "OLLAMA_BASE_URLS"
+          value: {{ include "ollamaBaseUrls" . | quote }}
+        {{- else }}
+        - name: "ENABLE_OLLAMA_API"
+          value: "False"
+        {{- end }}
+        - name: "OPENAI_API_BASE_URL"
+        {{- if .Values.pipelines.enabled }}
+          value: {{ include "pipelines.serviceEndpoint" . }}
+        {{- else if .Values.openaiBaseApiUrl }}
+          value: {{ .Values.openaiBaseApiUrl | quote }}
+        {{- end }}
+        {{- if .Values.extraEnvVars }}
+          {{- toYaml .Values.extraEnvVars | nindent 8 }}
+        {{- end }}
+        {{- if .Values.tika.enabled }}
+        - name: "CONTENT_EXTRACTION_ENGINE"
+          value: "Tika"
+        - name: "TIKA_SERVER_URL"
+          value: http://{{ .Chart.Name }}-tika:9998
         {{- end }}
         tty: true
       {{- with .Values.nodeSelector }}
@@ -107,3 +137,6 @@ spec:
         persistentVolumeClaim:
           claimName: {{ include "open-webui.name" . }}
       {{- end }}
+      {{- with .Values.volumes }}
+      {{- toYaml . | nindent 6 }}
+      {{- end }}

charts/open-webui/values.yaml

@@ -24,6 +24,10 @@ pipelines:
   # -- This section can be used to pass required environment variables to your pipelines (e.g. Langfuse hostname)
   extraEnvVars: []
 
+tika:
+  # -- Automatically install Apache Tika to extend Open WebUI
+  enabled: false
+
 # -- A list of Ollama API endpoints. These can be added in lieu of automatically installing the Ollama Helm chart, or in addition to it.
 ollamaUrls: []
 
@@ -60,6 +64,8 @@ persistence:
   size: 2Gi
   # -- Use existingClaim if you want to re-use an existing Open WebUI PVC instead of creating a new one
   existingClaim: ""
+  # -- Subdirectory of Open WebUI PVC to mount. Useful if root directory is not empty.
+  subPath: ""
   # -- If using multiple replicas, you must update accessModes to ReadWriteMany
   accessModes:
     - ReadWriteOnce
@@ -92,8 +98,8 @@ service:
 # -- OpenAI base API URL to use. Defaults to the Pipelines service endpoint when Pipelines are enabled, and "https://api.openai.com/v1" if Pipelines are not enabled and this value is blank
 openaiBaseApiUrl: ""
 
-# -- Env vars added to the configmap and mounted to the Open WebUI deployment. Most up-to-date environment variables can be found here: https://docs.openwebui.com/getting-started/env-configuration/
-extraEnvVars: 
+# -- Env vars added to the Open WebUI deployment. Most up-to-date environment variables can be found here: https://docs.openwebui.com/getting-started/env-configuration/
+extraEnvVars:
   # -- Default API key value for Pipelines. Should be updated in a production deployment, or be changed to the required API key if not using Pipelines
   - name: OPENAI_API_KEY
     value: "0p3n-w3bu!"
@@ -109,6 +115,25 @@ extraEnvVars:
   # - name: OLLAMA_DEBUG
   #   value: "1"
 
+# -- Configure container volume mounts
+# ref: <https://kubernetes.io/docs/tasks/configure-pod-container/configure-volume-storage/>
+volumeMounts:
+  initContainer: []
+  # - name: ""
+  #   mountPath: ""
+  container: []
+  # - name: ""
+  #   mountPath: ""
+
+# -- Configure pod volumes
+# ref: <https://kubernetes.io/docs/tasks/configure-pod-container/configure-volume-storage/>
+volumes: []
+# - name: ""
+#   configMap:
+#     name: ""
+# - name: ""
+#   emptyDir: {}
+
 # -- Configure pod security context
 # ref: <https://kubernetes.io/docs/tasks/configure-pod-container/security-context/#set-the-security-context-for-a-containe>
 podSecurityContext:

charts/pipelines/values.yaml

@@ -61,6 +61,11 @@ extraEnvVars:
   # -- Example pipeline to pull and load on deployment startup, see current pipelines here: https://github.com/open-webui/pipelines/blob/main/examples
   - name: PIPELINES_URLS
     value: "https://github.com/open-webui/pipelines/blob/main/examples/filters/detoxify_filter_pipeline.py"
+  # - name: PIPELINES_API_KEY
+  #   valueFrom:
+  #     secretKeyRef: 
+  #       name: pipelines-keys
+  #       key: pipelines-api-key
   # -- Langfuse example, including values used in Langfuse filter to connect
   # - name: PIPELINES_URLS
   #   value: "https://github.com/open-webui/pipelines/blob/main/examples/filters/langfuse_filter_pipeline.py"