Configure SQL AI Assistant using Cloudera AI Workbench

This topic describes how to deploy and configure the SQL AI Assistant using the Cloudera AI Workbench. With the added support for Cloudera AI Workbench, you can securely deploy and run your own models within a virtual private cloud. This self-contained integration offers enhanced control and privacy within your environment.

In this task, you specify the token value in the Hue Advanced Configuration Snippet field in Cloudera Manager. The credentials are saved in a configuration file in the plain text format.

To know more about creating and deploying models using Cloudera AI, see Create and deploy the model.

Upon succesuccessful completion of model deployment, log in to the CDP Management Console as an Administrator.
Go to Environments and select your environment.
Go to the Data Lake tab and click on the CM URL to open Cloudera Manager.
Go to Clusters > Hue service > Configuration and select add the following lines in the Hue Service Advanced Configuration Snippet (Safety Valve) for hue_safety_valve.ini field:
```
[desktop]
 [[ai_interface]]
    service='cml'
    model='llama'
    model_ref='[***Place model access key here***]'
    base_url='https://[***RESOURCE***].cloudera.site/model'
    
```
Click Save Changes.

You see

Assistant on the Hue SQL editor, where the SQL AI Assistant utilizes the model hosted in the Cloudera AI Workbench.