# Integration with CKEditor AI On-Premises

This page covers running Collaboration Server On-Premises together with [CKEditor AI On-Premises](../../ckeditor-ai-onpremises/overview.md): the prerequisites, the configuration that connects the two, what changes once they are connected, and the token that authorizes both. Read it if you add CKEditor AI to a Collaboration Server you already run.

CKEditor AI On-Premises can share its data layer with Collaboration Server On-Premises. Both services then use the same SQL database and Redis instance, so you do not set up separate ones for AI.

> **Warning**
>
> This integration requires Collaboration Server On-Premises **5.0.0 or newer**.

Collaboration Server On-Premises and CKEditor AI On-Premises are released at the same time. Update them together and keep them on the same version.

<a id="prerequisites">

## Prerequisites

Before integrating, make sure you have a working CKEditor AI On-Premises deployment. See [Deployment](../../ckeditor-ai-onpremises/deployment.md) or [Collaboration Server integration](../../ckeditor-ai-onpremises/collaboration-server-integration.md) for the AI-side setup.

<a id="configuration">

## Configuration

Set `AI_API_BASE_URL` to the address of CKEditor AI On-Premises. Collaboration Server uses this address to reach the AI service, including from the [Management Panel](../management.md):

```bash
docker run --init -p 8000:8000 \
	-e LICENSE_KEY=[your license key] \
	-e DATABASE_DRIVER=[mysql|postgres] \
	-e DATABASE_HOST=[your database host] \
	-e DATABASE_USER=[your database user] \
	-e DATABASE_PASSWORD=[your database password] \
	-e DATABASE_DATABASE=[your database name] \
	-e REDIS_HOST=[your Redis host] \
	-e ENVIRONMENTS_MANAGEMENT_SECRET_KEY=[your secret] \
	-e AI_API_BASE_URL=[CKEditor AI On-Premises address, for example http://ckeditor-ai:8000] \
	docker.cke-cs.com/cs:[version]
```

> **Note**
>
> The value of `AI_API_BASE_URL` is the scheme, host, and port of an address that Collaboration Server can reach. In Docker Compose, that is the AI service name and its container port.

> **Note**
>
> For CKEditor AI On-Premises, also use the same `DATABASE_*` and `REDIS_*` values as this Collaboration Server. On a mismatch, the AI service does not find the Collaboration Server tables, and it sets up a data layer of its own. See [Collaboration Server integration](../../ckeditor-ai-onpremises/collaboration-server-integration.md).

<a id="what-changes-when-integrated">

## What changes when integrated

* **Shared environments** – the environments and access keys work for both services, whichever Management Panel you create them in.
* **Two management panels** – both panels let you manage environments and browse insight logs. You configure collaboration features in the Collaboration Server [Management Panel](../management.md) and AI features in the CKEditor AI Management Panel.
* **Shared data layer** – both services read and write the same SQL database and Redis instance. You do not create a separate database for AI.

<a id="token-endpoint-for-collaboration-and-ai">

## Token endpoint for collaboration and AI

One token covers both services. Put the collaboration roles in `auth.collaboration` and the AI permissions in `auth.ai.permissions` in the same payload:

```json
{
	"aud": "your-environment-id",
	"sub": "user-123",
	"auth": {
		"collaboration": {
			"*": {
				"role": "writer"
			}
		},
		"ai": {
			"permissions": [
				"ai:conversations:*",
				"ai:models:agent",
				"ai:actions:system:*",
				"ai:reviews:system:*"
			]
		}
	}
}
```

See [Example token payload for collaboration and AI](../../../developer-resources/security/token-endpoint.md#example-token-payload-for-collaboration-and-ai) on the Token endpoint page.

<a id="next-steps">

## Next steps

* [Quick start](quickstart.md) – Set up Collaboration Server On-Premises on your local machine.
* [Environmental variables](configuration/environmental-variables.md) – See the full list of Collaboration Server options, including `AI_API_BASE_URL`.
* [Token endpoint](../../../developer-resources/security/token-endpoint.md) – Build the endpoint that signs tokens for collaboration and AI.

---

Full index of the Cloud Services documentation: [llms.txt](../../../../llms.txt)