Use the Automation Anywhere retrieval-augmented generation (RAG) capability to create Grounded by Enterprise
Knowledge Model connections to generate accurate and contextually relevant
information referenced from Enterprise Knowledge bases. By grounding LLMs in specific,
relevant information, RAG ensures that AI-generated responses are accurate, up-to-date, and
aligned with an organization's unique needs.
About this task
Note: Automation Anywhere Grounded by Enterprise Knowledge Model connections is now available in Automation 360 in Cloud and On-Premises.
Before you begin
The Automation Admin requires these roles and permissions to create and manage
Model connections for their business organization.
- Role: AAE_Basic, Automation Admin custom role
- Permission: Attended Bot Runner
- Settings: AI Data Management must be enabled
by the Automation Admin and the check box selected for Allow
users to disable logs on AI Skills option.
See Roles and permissions for the Automation Admin custom role
permissions.
Procedure
-
In your Control Room environment, navigate to .
-
In the Create Model connection screen configure these
Connection settings:
-
Model connection name: Provide a name for easy
identification of the Model connection.
-
Description (optional): Add a meaningful short
description defining the connection.
-
Choose a vendor: Choose a foundational model
vendor from the supported list of vendors. For creating a Grounded by
Enterprise Knowledge Model connection with Automation Anywhere, select Automation Anywhere
from the drop-down list.
-
Choose a type: Choose Grounded by Enterprise Knowledge for using the RAG capability.
For a complete list of supported models for each foundational model
vendor, see
General FAQs.
-
Click Next to proceed to the
Authentication details section.
-
Enter the Authentication details. For more information,
see Automation Anywhere.
-
Click Test connection to make sure all connection
details have been defined correctly and check if the connection is working.
This is a desktop operation using a
Bot Agent. Use
Bot Agent 22.60.10 and later for successful testing.
- If the connection works as expected, the system will process the
request and you will get a system generated success message.
- If the connection does not work as expected, you will get a
system-generated message stating the reason for the connection
failure. For example, if you have not downloaded the supported
foundational model package to your workspace, you would get an error
message. You would have to download the package and then retest the
Model connection.
- If the Model connection testing is unsuccessful or if you leave the task
incomplete, the Model connection will not get saved
and you will have to restart the process of creating the Model connection.
-
Click Next to proceed to the Invite
roles section to begin assigning custom roles to users.
The Automation Admin would create custom roles and assign the Model connections to the role, which can then be assigned to
users. Only users assigned to this custom role can use this Model connection.
-
Assign the Model connection to the custom role (using RBAC) so
users assigned to the role can access it.
-
Click Create model connection to complete creating the
Model connection.
After successfully creating the Model connection, the Pro Developer
would use it to create an AI Skill.