Merge branch 'dev'

.gitignore

@@ -8,3 +8,294 @@ node_modules
 !.env.example
 vite.config.js.timestamp-*
 vite.config.ts.timestamp-*
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
\ No newline at end of file

README.md

@@ -27,7 +27,7 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
 
 - ⚡ **Swift Responsiveness**: Enjoy fast and responsive performance.
 
-- 🚀 **Effortless Setup**: Install seamlessly using Docker for a hassle-free experience.
+- 🚀 **Effortless Setup**: Install seamlessly using Docker or Kubernetes (kubectl, kustomize or helm) for a hassle-free experience.
 
 - 💻 **Code Syntax Highlighting**: Enjoy enhanced code readability with our syntax highlighting feature.
 
@@ -81,29 +81,49 @@ Don't forget to explore our sibling project, [OllamaHub](https://ollamahub.com/)
 
 ### Installing Both Ollama and Ollama Web UI Using Docker Compose
 
-If you don't have Ollama installed yet, you can use the provided Docker Compose file for a hassle-free installation. Simply run the following command:
+If you don't have Ollama installed yet, you can use the provided bash script for a hassle-free installation. Simply run the following command:
 
+For cpu-only container
 ```bash
-docker compose up -d --build
+chmod +x run-compose.sh && ./run-compose.sh
 ```
 
-This command will install both Ollama and Ollama Web UI on your system.
-
-#### Enable GPU
-
-Use the additional Docker Compose file designed to enable GPU support by running the following command:
+For gpu-enabled container (to enable this you must have your gpu driver for docker, it mostly works with nvidia so this is the official install guide: [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html))
+```bash
+chmod +x run-compose.sh && ./run-compose.sh --enable-gpu[count=1]
+```
 
+Note that both the above commands will use the latest production docker image in repository, to be able to build the latest local version you'll need to append the `--build` parameter, for example:
 ```bash
-docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d --build
+./run-compose.sh --build --enable-gpu[count=1]
 ```
 
-#### Expose Ollama API outside the container stack
+### Installing Both Ollama and Ollama Web UI Using Kustomize
+For cpu-only pod
+```bash
+kubectl apply -f ./kubernetes/manifest/base
+```
+For gpu-enabled pod
+```bash
+kubectl apply -k ./kubernetes/manifest
+```
 
-Deploy the service with an additional Docker Compose file designed for API exposure:
+### Installing Both Ollama and Ollama Web UI Using Helm
+Package Helm file first
+```bash
+helm package ./kubernetes/helm/
+```
 
+For cpu-only pod
 ```bash
-docker compose -f docker-compose.yml -f docker-compose.api.yml up -d --build
+helm install ollama-webui ./ollama-webui-*.tgz
 ```
+For gpu-enabled pod
+```bash
+helm install ollama-webui ./ollama-webui-*.tgz --set ollama.resources.limits.nvidia.com/gpu="1"
+```
+
+Check the `kubernetes/helm/values.yaml` file to know which parameters are available for customization
 
 ### Installing Ollama Web UI Only
 

docker-compose.api.yaml

+version: '3.8'
+
+services:
+  ollama:
+    ports:
+      - ${OLLAMA_WEBAPI_PORT-11434}:11434

docker-compose.data.yaml

+version: '3.8'
+
+services:
+  ollama:
+    volumes:
+      - ${OLLAMA_DATA_DIR-./ollama-data}:/root/.ollama
\ No newline at end of file

docker-compose.gpu.yaml

+version: '3.8'
+
+services:
+  ollama:
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: ${OLLAMA_GPU_DRIVER-nvidia}
+              count: ${OLLAMA_GPU_COUNT-1}
+              capabilities:
+                - gpu

docker-compose.yml → docker-compose.yaml

-version: '3.6'
+version: '3.8'
 
 services:
   ollama:
@@ -16,14 +16,14 @@ services:
       args:
         OLLAMA_API_BASE_URL: '/ollama/api'
       dockerfile: Dockerfile
-    image: ollama-webui:latest
+    image: ghcr.io/ollama-webui/ollama-webui:main
     container_name: ollama-webui
     volumes:
       - ollama-webui:/app/backend/data
     depends_on:
       - ollama
     ports:
-      - 3000:8080
+      - ${OLLAMA_WEBUI_PORT-3000}:8080
     environment:
       - "OLLAMA_API_BASE_URL=http://ollama:11434/api"
     extra_hosts:

kubernetes/helm/Chart.yaml

+apiVersion: v2
+name: ollama-webui
+description: "Ollama Web UI: A User-Friendly Web Interface for Chat Interactions 👋"
+version: 1.0.0
+icon: https://raw.githubusercontent.com/ollama-webui/ollama-webui/main/static/favicon.png

kubernetes/helm/templates/ollama-namespace.yaml

+apiVersion: v1
+kind: Namespace
+metadata:
+  name: {{ .Values.namespace }}
\ No newline at end of file

kubernetes/helm/templates/ollama-service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: ollama-service
+  namespace: {{ .Values.namespace }}
+spec:
+  selector:
+    app: ollama
+  ports:
+  - protocol: TCP
+    port: {{ .Values.ollama.servicePort }}
+    targetPort: {{ .Values.ollama.servicePort }}
\ No newline at end of file

kubernetes/helm/templates/ollama-statefulset.yaml

+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: ollama
+  namespace: {{ .Values.namespace }}
+spec:
+  serviceName: "ollama"
+  replicas: {{ .Values.ollama.replicaCount }}
+  selector:
+    matchLabels:
+      app: ollama
+  template:
+    metadata:
+      labels:
+        app: ollama
+    spec:
+      containers:
+      - name: ollama
+        image: {{ .Values.ollama.image }}
+        ports:
+        - containerPort: {{ .Values.ollama.servicePort }}
+        resources:
+          limits:
+            cpu: {{ .Values.ollama.resources.limits.cpu }}
+            memory: {{ .Values.ollama.resources.limits.memory }}
+            nvidia.com/gpu: {{ .Values.ollama.resources.limits.gpu }}
+        volumeMounts:
+        - name: ollama-volume
+          mountPath: /root/.ollama
+        tty: true
+  volumeClaimTemplates:
+  - metadata:
+      name: ollama-volume
+    spec:
+      accessModes: [ "ReadWriteOnce" ]
+      resources:
+        requests:
+          storage: 1Gi
\ No newline at end of file

kubernetes/helm/templates/webui-deployment.yaml

+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: ollama-webui-deployment
+  namespace: {{ .Values.namespace }}
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: ollama-webui
+  template:
+    metadata:
+      labels:
+        app: ollama-webui
+    spec:
+      containers:
+      - name: ollama-webui
+        image: ghcr.io/ollama-webui/ollama-webui:main
+        ports:
+        - containerPort: 8080
+        resources:
+          limits:
+            cpu: "500m"
+            memory: "500Mi"
+        env:
+        - name: OLLAMA_API_BASE_URL
+          value: "http://ollama-service.{{ .Values.namespace }}.svc.cluster.local:{{ .Values.ollama.servicePort }}/api"
+        tty: true
\ No newline at end of file

kubernetes/helm/templates/webui-ingress.yaml

+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: ollama-webui-ingress
+  namespace: {{ .Values.namespace }}
+  #annotations:
+    # Use appropriate annotations for your Ingress controller, e.g., for NGINX:
+    # nginx.ingress.kubernetes.io/rewrite-target: /
+spec:
+  rules:
+  - host: {{ .Values.webui.ingress.host }}
+    http:
+      paths:
+      - path: /
+        pathType: Prefix
+        backend:
+          service:
+            name: ollama-webui-service
+            port:
+              number: {{ .Values.webui.servicePort }}

kubernetes/helm/templates/webui-service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: ollama-webui-service
+  namespace: {{ .Values.namespace }}
+spec:
+  type: NodePort  # Use LoadBalancer if you're on a cloud that supports it
+  selector:
+    app: ollama-webui
+  ports:
+    - protocol: TCP
+      port: {{ .Values.webui.servicePort }}
+      targetPort: {{ .Values.webui.servicePort }}
+      # If using NodePort, you can optionally specify the nodePort:
+      # nodePort: 30000
\ No newline at end of file

kubernetes/helm/values.yaml

+namespace: ollama-namespace
+
+ollama:
+  replicaCount: 1
+  image: ollama/ollama:latest
+  servicePort: 11434
+  resources:
+    limits:
+      cpu: "2000m"
+      memory: "2Gi"
+      nvidia.com/gpu: "0"
+  volumeSize: 1Gi
+
+webui:
+  replicaCount: 1
+  image: ghcr.io/ollama-webui/ollama-webui:main
+  servicePort: 8080
+  resources:
+    limits:
+      cpu: "500m"
+      memory: "500Mi"
+  ingress:
+    host: ollama.minikube.local

kubernetes/manifest/base/ollama-namespace.yaml

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

kubernetes/manifest/base/ollama-service.yaml

+apiVersion: v1
+kind: Service
+metadata:
+  name: ollama-service
+  namespace: ollama-namespace
+spec:
+  selector:
+    app: ollama
+  ports:
+  - protocol: TCP
+    port: 11434
+    targetPort: 11434
\ No newline at end of file

kubernetes/manifest/base/ollama-statefulset.yaml

+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: ollama
+  namespace: ollama-namespace
+spec:
+  serviceName: "ollama"
+  replicas: 1
+  selector:
+    matchLabels:
+      app: ollama
+  template:
+    metadata:
+      labels:
+        app: ollama
+    spec:
+      containers:
+      - name: ollama
+        image: ollama/ollama:latest
+        ports:
+        - containerPort: 11434
+        resources:
+          limits:
+            cpu: "2000m"
+            memory: "2Gi"
+        volumeMounts:
+        - name: ollama-volume
+          mountPath: /root/.ollama
+        tty: true
+  volumeClaimTemplates:
+  - metadata:
+      name: ollama-volume
+    spec:
+      accessModes: [ "ReadWriteOnce" ]
+      resources:
+        requests:
+          storage: 1Gi
\ 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
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: ollama-webui
+  template:
+    metadata:
+      labels:
+        app: ollama-webui
+    spec:
+      containers:
+      - name: ollama-webui
+        image: ghcr.io/ollama-webui/ollama-webui:main
+        ports:
+        - containerPort: 8080
+        resources:
+          limits:
+            cpu: "500m"
+            memory: "500Mi"
+        env:
+        - name: OLLAMA_API_BASE_URL
+          value: "http://ollama-service.ollama-namespace.svc.cluster.local:11434/api"
+        tty: true
\ No newline at end of file

kubernetes/manifest/base/webui-ingress.yaml

+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: ollama-webui-ingress
+  namespace: ollama-namespace
+  #annotations:
+    # Use appropriate annotations for your Ingress controller, e.g., for NGINX:
+    # nginx.ingress.kubernetes.io/rewrite-target: /
+spec:
+  rules:
+  - host: ollama.minikube.local
+    http:
+      paths:
+      - path: /
+        pathType: Prefix
+        backend:
+          service:
+            name: ollama-webui-service
+            port:
+              number: 8080