Installing Automation.AI in On-Premises Systems

Automation.AI is an AI-platform- agnostic, stand-alone component that can communicate with multiple Large Language Models (LLMs), thus allowing you to incorporate state-of-the-art AI technology to help you design automated processes, write scripts, analyze and explain the automation output, troubleshoot issues and suggest potential solutions to those issues. The LLMs supported are Gemini, OpenAI, and Ollama.

You can install it in Automic Automation Kubernetes Edition and on-premises systems, regardless if they have been installed manually or, for testing environments, using the ONE Installer.

Important!

This page includes the following:

Install Automation.AI with the ONE Installer

You can use the ONE Installer to install systems for proof of concepts, testing purposes, and non-production environments only. For more information, see ONE Installer - Single-Box Installation.

When using it, the Automation.AI component is installed automatically. Since the ONE Installer takes care of the port assignment for the environment being installed, you only need to make sure that your system can connect to the relevant LLM, which you can define before the installation using the application.properties file. You can also use environment variables to define those settings. For more information, see On-Premises: Preparing for the Automation.AI Installation.

Once the system has been installed, make sure you define the JWP port used for the communication to the Automation.AI component using the AUTOMATION_AI_ENDPOINT key of the UC_SYSTEM_SETTINGS variable. For more information, see AUTOMATION_AI_ENDPOINT.

Install Automation.AI Manually

Before installing the Automation.AI component, make sure that you have defined the server port and the LLM that you want to use in the application.properties file. You can also use environment variables to define those settings. For more information, see On-Premises: Preparing for the Automation.AI Installation.

To trigger the manual installation, use the automation-ai-launcher.jar file delivered with the offering an run it using the following command:

java -jar automation-ai-launcher.jar

You can also add the Automation.AI component to the ServiceManager. For more information, see ServiceManager - Dialog Program.

Once the system has been installed, make sure you define the port used for the communication to the Automation.AI component by the JWP using the AUTOMATION_AI_ENDPOINT key of the UC_SYSTEM_SETTINGS variable. For more information, see AUTOMATION_AI_ENDPOINT.

See also: