@Marvin I want to run the prefect dashboard separately from the prefect server, how can I accomplish in a helm installation?

There doesn't seem to be a direct guide on running the Prefect dashboard separately from the Prefect server using Helm, but I found some resources that could help you create a custom solution. Based on the available information, here's a general approach: 1. Setup Prefect Helm Repository: First, ensure your Helm client is configured to use the Prefect Helm repository:

bash
   helm repo add prefect <https://prefecthq.github.io/prefect-helm>
   helm repo update

2. Create Separate Deployments: Typically, Prefect server and UI run together by default. To run the UI separately, you might need to customize Helm charts or create separate deployments for each service. 3. Customizing Helm Chart for UI: You can customize the Helm values file (

values.yaml

) specifically for the Prefect UI service. This involves disabling the server component and focusing on the UI. Here's an example

values.yaml

configuration to only deploy the Prefect UI:

yaml
   server:
     enabled: false

   ui:
     enabled: true
     serviceType: LoadBalancer

4. Deploy UI: Use Helm to deploy the Prefect UI with your custom values:

bash
   helm install prefect-ui prefect/prefect-server -f values.yaml

5. Deploy Server Separately: Similarly, you can create a

values.yaml

for the Prefect server to only deploy the server component:

yaml
   server:
     enabled: true

   ui:
     enabled: false

Deploy the server with:

bash
   helm install prefect-server prefect/prefect-server -f values.yaml

For detailed customization and settings, you might need to refer to the Prefect Helm Chart documentation or inspect the Helm chart templates. If you encounter any specific issues or need more precise configurations, you can also check Prefect GitHub issues for similar use cases or open a new issue for tailored assistance.