Configure AI preferences

AI preferences allow you to configure the large language model (LLM), provider, connection details, access permissions, and MCP server in UC. These preferences determine how AI features are configured and made available to users and databases. This section provides information about how you can configure the AI preferences in UC.

Enable AI Assistance

The Enable AI Assistance banner appears only when none of the available databases are AI enabled. You can enable AI for a database by configuring an AI model. Click Enable in the banner to configure or edit the AI preferences. If at least one database in the system is AI enabled, this banner is not displayed.

Configure or edit AI preferences

You can configure or edit the AI preferences in UC to make AI features available to users.

1. Log in to UC.

2. Choose AI preferences under Settings in the home page. The AI preferences page opens and displays the following information:

   • Host - The host name.
   • Model - The large language model (LLM) that is used.
   • Creator - The MC role who created the LLM.
   • Enabled for - The database for which the LLM is enabled.
   • Status - The current status of the LLM.

3. Hover over ⋮ and select Edit. The following model details display:

   • Model provider
   • Model name
   • URL of the service hosting the model
   • Region
   • Secret access key
   • API key
   • Who should have access
   • Which databases can access this
   • MCP status

4. From the Model provider list, choose the AI model provider that creates, trains, maintains, and hosts AI models. You can choose from Anthropic, Google Gemini, and Amazon Bedrock.

5. From the Model name list, choose the specific LLM to use for inference.

6. In the URL of the service hosting the model field, enter the root network address used to send requests to an AI service's API. Use the endpoint URL provided in your selected AI provider's documentation or API configuration page.

7. In the Region field, choose the appropriate service region.

   Note

      This is applicable only if your provider is Amazon Bedrock.
   

8. In the Secret access key field, enter the credential (secret key) required for secure authentication.

9. In the API key field, enter the key used to authenticate API requests.

   Note

      If your provider is Amazon Bedrock, enter the **Access Key Id**. Enter the **API key** only if you are using a provider other than Amazon Bedrock.
   

10. In the Who should have access area, choose the required users depending on the role played by the user in the organization. For more information, see Configuration roles in MC.

11. In the Which databases can access this area, choose the databases that can access the LLM.

12. Click MCP status to view the MCP client configuration. For more information, see Configure the MCP client.

13. Click Save.

Add a model

You can add a model from the AI preferences.

1. Login to UC.
2. Choose AI preferences under Settings in the home page. The AI preferences page opens.
3. Click +Add new model. Follow steps 4-13 in Configure or edit AI preferences.