Community

Open WebUI

DescriptionInstall

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.

Prerequisites

Deploy k0rdent v1.4.0: QuickStart

Deploy Ingress-nginx to expose application web UI

Install template to k0rdent

helm upgrade --install open-webui oci://ghcr.io/k0rdent/catalog/charts/kgst --set "chart=open-webui:8.10.0" -n kcm-system

Verify service template

kubectl get servicetemplates -A
# NAMESPACE    NAME                            VALID
# kcm-system   open-webui-8-10-0               true

Deploy service template

Configuration without GPU

Tested on worker instanceType: t3.xlarge and rootVolumeSize: 32:

apiVersion: k0rdent.mirantis.com/v1beta1
kind: ClusterDeployment
metadata:
  name: aws-example
spec:
  template: aws-standalone-cp-1-0-14
  credential: aws-credential
  config:
    ...
    worker:
      instanceType: t3.xlarge
      rootVolumeSize: 32
    workersNumber: 1

Tested service configuration:

apiVersion: k0rdent.mirantis.com/v1beta1
kind: MultiClusterService
metadata:
  name: open-webui
spec:
  clusterSelector:
    matchLabels:
      group: demo
  serviceSpec:
    services:
    - template: open-webui-8-10-0
      name: open-webui
      namespace: open-webui
      values: |
        open-webui:
          ollama:
            ollama:
              models:
                pull: [smollm:135m]
                run: [smollm:135m]
          ingress:
            enabled: true
            class: "nginx"
            host: 'openwebui.example.com'

Configuration with GPU

This setup requires corresponding cluster setup, see NVIDIA GPU Operator

apiVersion: k0rdent.mirantis.com/v1beta1
kind: MultiClusterService
metadata:
  name: open-webui
spec:
  clusterSelector:
    matchLabels:
      group: demo
  serviceSpec:
    services:
    - template: open-webui-8-10-0
      name: open-webui
      namespace: open-webui
      values: |
        open-webui:
          ollama:
            ollama:
              gpu:
                enabled: true
                type: 'nvidia'
                number: 1
              models:
                pull: [llama3.2:3b]
                run: [llama3.2:3b]
          ingress:
            enabled: true
            class: "nginx"
            host: 'openwebui.example.com'

• Official docs