Deploying BMC AMI AI Services on your on-premises x86 Linux distribution (Ubuntu and RHEL)

The following infrastructure is required for optimal performance with BMC AMI AI Services:

Task 1: To acquire the required infrastructure

Acquire the infrastructure from the recommended table and make sure that you have installed the Ubuntu 24.04 LTS operating system. We recommend creating infrastructure for the Mixtral8x7B configuration type because it provides optimal system performance and accuracy.

You can acquire one of the configurations from the list. Then note the IP or domain name for the application installation.

Task 2: To download the required scripts from EPD

1. Make sure that you have completed the steps in Downloading-the-installation-files and obtain the BMC-AMI-AI-x86.zip file.
2. Extract the contents from the BMC-AMI-AI-x86.zip file and save the extracted files in a folder of your choice for future use. 

Task 3: To configure BMC AMI AI Services for installation

Update the configuration in the Ansible scripts, based on the services that you need:

• BMC AMI AI Platform Services configuration
• BMC AMI Code Insights Explain configuration
• BMC AMI Ops Insights Root Cause Explain configuration
• BMC AMI AI Model configuration

BMC AMI AI Platform Services configuration

You can find the BMC-AMI-AI-Platform-Services.yml Ansible file in the extracted folder. This script installs BMC AMI AI Platform services.

You must configure the following fields before running the Ansible script:

For licensing purposes, you must configure the following fields for BMC AMI Common Enterprise Services (CES). During integration provisioning, the CES details are provided to store BMC AMI AI Services access information. The CES details are also used with BMC AMI DevX Workbench applications to access BMC AMI AI Services. If you are using Code Insights Explain, you must configure the CES fields.

If you have the mainframe machine's host name or IP address, enter it in the zos_host field to authenticate users. All authenticated users can access the BMC AMI AI Manager console.

If you don't have the host name or IP address, specify the administrator user name in the admin_user_id field. The default is admin. If you have set zos_host, reset the values set for the admin user in the admin_user_id field. All users are admin users.

In the admin_password field, set an admin user password encoded in base64. The default value is base64 encoding of amiaiadmin: YW1pYWlhZG1pbg== 

To configure other properties, see Configuring-the-BMC-AMI-Platform-service.

To access the BMC AMI AI Services console, user credentials are required.

BMC AMI AI Code Insights Explain configuration

You can find the BMC-AMI-AI-Devx-Service.yml Ansible file in the extracted folder. This script installs BMC AMI AI Code Insights Explain.

You must configure the following fields before running the Ansible script:

BMC AMI Ops Insights Root Cause Explain configuration

You can find the BMC-AMI-AI-OI-Service.yml Ansible file in the extracted folder. This script installs BMC AMI Ops Insights Root Cause Explain.

You must configure the following fields before running the Ansible script:

BMC AMI AI Model configuration

You can find the BMC-AMI-AI-GPU-Service.yml Ansible file in the extracted folder.

You must configure the following fields before running the Ansible script:

Task 4: To copy the script and files to the machine

Copy the folder to the acquired instance, as follows:

1. Locate the folder where you stored the following files:
   • BMC-AMI-AI-Platform-Services.yml
   • BMC-AMI-AI-Devx-Service.yml
   • BMC-AMI-AI-OI-Service.yml
   • BMC-AMI-AI-GPU-Service.yml
   • BMC-AMI-AI-Platform.sh
   • BMC-AMI-AI-Devx.sh
   • BMC-AMI-AI-OI.sh
   • BMC-AMI-AI-GPU.sh
2. Move all the files listed to the x86 Linux distribution. You can use any SCP client to copy all files.
3. If SSL is enabled, create a certificates folder in the directory where scripts and Ansible are present and copy the SSL certificate and private key to the certificates folder.

Task 5: To deploy BMC AMI AI Services

1. Connect to the newly acquired x86 Linux distribution instance via SSH. Make sure that the login credentials have admin access.
2. Install Python and its dependency on-premises x86 machine, as follows:

   1. Verify whether Python is already installed by entering the python3 command. If Python is not installed, then run the following commands: 

      sudo apt update
      sudo apt install python3

   2. Install pip by using the following commands: 

      sudo apt update
      sudo apt-get -y install python3-pip
3. Deploy the application. BMC AMI AI Services deployment consists of the following steps:
   1. BMC AMI Platform services deployment

      1. Run the following commands to deploy AMI AI Platform Services: 

         chmod +x BMC-AMI-AI-Platform.sh
         sed -i -e 's/\r$//' BMC-AMI-AI-Platform.sh
         ./BMC-AMI-AI-Platform.sh
      2. When prompted, enter your EPD portal's user name and password.
   2. Integration deployment

      • For BMC AMI AI Code Insights Explain, run the following command:

        chmod +x BMC-AMI-AI-Devx.sh
        sed -i -e 's/\r$//' BMC-AMI-AI-Devx.sh
        ./BMC-AMI-AI-Devx.sh

      • For BMC AMI Ops Insights Root Cause Explain, run the following command:

        chmod +x BMC-AMI-AI-OI.sh
        sed -i -e 's/\r$//' BMC-AMI-AI-OI.sh
        ./BMC-AMI-AI-OI.sh
   3. Model Deployment

      1. Run one of the following commands, based on your selected configuration. Do not run all the commands. 

         Configuration type	Command
         Recommended	chmod +x BMC-AMI-AI-GPU.sh sed -i -e 's/\r$//' BMC-AMI-AI-GPU.sh ./BMC-AMI-AI-GPU.sh After running this command, enter Mixtral,or Granite, or  Llama3 in the selection prompt window.

      2. When prompted, enter your EPD portal's user name and password.

Task 6: To verify the deployment of BMC AMI AI Services

See Verifying-the-installation.