Sign up (with export icon)

Setup wizard

Show the table of contents

Answer five questions about your infrastructure and copy the docker run command for your CKEditor AI On-Premises deployment.

Note

The wizard covers the settings most deployments need. Required configuration lists every option.

Prerequisites

Copy link

The generated command contains placeholders in square brackets. Collect these values first:

  • License key – from the Customer Portal, or contact us for a trial key.
  • Management secret – a string you generate yourself. It grants access to the Management Panel, so keep it secret and reuse it across restarts. See Secret keys.
  • Database host, user, password, and name – an empty MySQL 8 or PostgreSQL 12 database that the container can reach.
  • In-memory data store host – a Valkey or Redis instance that the container can reach.
  • LLM provider credentials – one set for each provider you select in step 4.
  • File storage credentials – for Amazon S3 or Azure Blob Storage. The filesystem and SQL database options need none.

Step 1: Deployment mode

Copy link

Step 2: Database

Copy link

Step 3: File storage

Copy link

Step 4: LLM provider

Copy link

Select one or more providers. You can add more providers later.

OpenAI, Anthropic, and Google each have a default list of models. They work as soon as you add an API key.

Azure OpenAI, Amazon Bedrock, Google Vertex AI, and Custom have no default models. For these, declare the models in the models option. See Custom models.

Select at least one provider.

Step 5: Optional features

Copy link

Result

Copy link

Copy the command. Replace each placeholder in square brackets with your own value. Deployment explains the steps around this command, and Collaboration Server integration explains the shared database and in-memory data store.

docker run

After you run the command

Copy link

The container starts, but it serves no requests yet. Three steps remain:

  1. Create an Environment and Access Key in the Management Panel.
  2. Create the token endpoint in your application. It issues a JWT for each user. See the Node.js example.
  3. Work through the Quickstart checklist. Its last step sends one request that uses your token endpoint, the access key, the database, and your LLM provider, so it proves that all four work.