Update installation.md

Fixed a lag issue with Helm in the installation documentation.
This commit is contained in:
Samzong Lu 2024-05-20 17:41:47 +08:00 committed by GitHub
parent d32f799842
commit 50315ecdf8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -16,22 +16,22 @@ kubectl apply -k ./kubernetes/manifest
### Installing Both Ollama and Open WebUI Using Helm ### Installing Both Ollama and Open WebUI Using Helm
Package Helm file first :::info
The helm install method has been migrated to the new github repo,
and the latest installation method is referred to. [https://github.com/open-webui/helm-charts](https://github.com/open-webui/helm-charts)
:::
Confirm that'Helm 'has been deployed on your execution environment.
For more installation instructions, please refer to [https://helm.sh/docs/intro/install/](https://helm.sh/docs/intro/install/)
```bash ```bash
helm package ./kubernetes/helm/ helm repo add open-webui https://helm.openwebui.com/
helm repo update
kubectl create namespace open-webui
helm upgrade --install open-webui open-webui/open-webui --namespace open-webui
``` ```
For cpu-only pod Check the [kubernetes/helm/values.yaml](https://github.com/open-webui/helm-charts/tree/main/charts/open-webui) file to know more values are available for customization
```bash
helm install open-webui ./open-webui-*.tgz
```
For gpu-enabled pod
```bash
helm install open-webui ./open-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