# Install the Control Plane

## System and Network Requirements <a href="#system-and-network-requirements" id="system-and-network-requirements"></a>

Before installing the NVIDIA Run:ai control plane, validate that the [system requirements](/multi-tenant/getting-started/installation/cp-system-requirements.md) and [network requirements ](/multi-tenant/getting-started/installation/network-requirements.md)are met.

## Permissions

As part of the installation, you will be required to install the NVIDIA Run:ai control plane [Helm chart](https://helm.sh/). The Helm charts require Kubernetes administrator permissions. You can review the exact objects that are created by the charts using the `--dry-run` on both helm charts.

## Installation

{% hint style="info" %}
**Note**

* To customize the installation based on your environment, see [Advanced control plane configurations](/multi-tenant/infrastructure-setup/advanced-setup/control-plane-config.md).
* PostgreSQL and Keycloakx are installed with default usernames and passwords. To change the default credentials, see [Additional third-party configurations](/multi-tenant/infrastructure-setup/advanced-setup/control-plane-config.md#additional-third-party-configurations).
  {% endhint %}

1. Create a `values.yaml` file using the appropriate example below based on your [metrics backend](/multi-tenant/getting-started/installation/metrics-store-requirements.md#supported-backend):

{% tabs %}
{% tab title="YAML with Grafana Labs" %}

```yaml
global:
  domain: <RUNAI_DOMAIN> # example: "runai.hostorg.com"
  multiTenancy: 
    enabled: true
  management:
    user: <ADMIN-USER>
    password: <ADMIN-PASSWORD>
metricsService:
  config:
   datasourceUrl: <METRIC_STORE_READ_URL> # example: https://prometheus-prod-13-prod-us-east-0.grafana.net/api/prom
tenantsManager:
  config:
    defaultMetricStore:
      read:
        auth:
          basic:
            password: <METRIC_STORE_READ_PASSWORD>
            username: "1434499"
        url: <METRIC_STORE_READ_URL> # example: https://prometheus-prod-13-prod-us-east-0.grafana.net/api/prom
      useXscopeHeader: true
      write:
        auth:
          basic:
            password: <METRIC_STORE_WRITE_PASSWORD>
            username: "1434499"
        url: <METRIC_STORE_WRITE_URL> # example: https://prometheus-prod-56-prod-us-east-2.grafana.net/api/prom
thanos:
  enabled: false
authorization:
  config:
    isCSPEnv: true
```

{% endtab %}

{% tab title="YAML with Mimir" %}

```yaml
global:
  domain: <RUNAI_DOMAIN> # example: "runai.hostorg.com"
  multiTenancy:
    enabled: true
  management:
    user: <ADMIN-USER>
    password: <ADMIN-PASSWORD>
metricsService:
  config:
   datasourceUrl: <METRIC_STORE_READ_URL> # example: http://mimir-query-frontend.monitoring.svc:8080/prometheus
tenantsManager:
  config:
    defaultMetricStore:
      read:
        auth:
          basic:
            password: ''
            username: ''
        url: <METRIC_STORE_READ_URL> # example: http://mimir-query-frontend.monitoring.svc:8080/prometheus
      useXscopeHeader: true
      write:
        auth:
          basic:
            password: ''
            username: ''
        url: <<REPLACE ME WITH MIMIR ENDPOINT>> # example: http://mimir-distributor.monitoring.svc:8080/api/v1/push
thanos:
  enabled: false
authorization:
  config:
    isCSPEnv: true
```

{% endtab %}
{% endtabs %}

2. Run the following commands to install the NVIDIA Run:ai control plane using your configured `values.yaml` file:

```bash
helm repo add runai https://helm.ngc.nvidia.com/nvidia/runai --force-update \
  --username='$oauthtoken' \
  --password=<NGC_API_KEY>
helm repo update
helm upgrade -i runai-backend -n runai-backend runai/control-plane \ 
    -f /path/to/your/values.yaml 
```

{% hint style="info" %}
**Note**

* To install a specific version, add `--version <VERSION>` to the install command. You can find all available versions by using the `helm search repo runai/control-plane --versions` command.
* Use the `--dry-run` flag to gain an understanding of what is being installed before the actual installation.
  {% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://run-ai-docs.nvidia.com/multi-tenant/getting-started/installation/install-control-plane.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.