Managing the platform in the BMC AMI AI Manager console


This topic describes how to use the BMC AMI AI Manager console to manage your services. By using the console, you can prepare different features and check the deployed status of BMC AMI AI Services, large language models (LLMs), and their details in one place.


Before you begin

Before you sign in to the BMC AMI AI Manager console, you must have installed BMC AMI Services. For more information, see Installing.

You can sign in by using the administrator and z/OS PTP credentials, which are defined in the BMC-AMI-AI-Platform-Services.yml file.

  • Administrator credentials
  •  z/OS FTP credentials

For information about the credentials, contact your application developer.

To sign to the BMC AMI AI Manager console

  1. Log in to the BMC AMI AI Manager console manager URL as follows:
    You can access BMC AMI AI Manager console by using the following steps:
    • If a load balancer or Application Gateway already exists, create a URL in the following format:
      https://domainName/admin, where domainName directs to the load balancer or Application Gateway.
      For example, if the domain name is amiai.bmc.com, then the URL is https://amiai.bmc.com/admin.
    • If you installed BMC AMI AI Services on a stand-alone instance or zCX/zLinux, create a URL in the following format: http://instanceIPaddress:8000/admin. For example, if the IP is 192.168.1.10, then the URL is http://192.168.1.10:8000/admin.
  2. Enter your admin user name and password specified in the playbook file.
  3. Click Sign in.

To select and prepare the BMC feature integration

  1. In a browser, sign in to BMC AMI AI Manager with your credentials. 
  2. From the menu in the left pane, select AI Services Settings > Feature Settings.
    image-2024-10-7_8-39-26.png
    The Feature Settings window lists all the feature integrations available in the deployed BMC AMI AI Services.
  3. From the list in the feature card, select your preferred LLM. 
  4. Click Provision.
    After successful provisioning, a Feature provisioned successfully message is displayed, and the Provision button on the card becomes an Update button. 
  5. Click Update to change the LLM to any other recommended LLM in the list. 

If this procedure fails, the user interface displays an error message with the reason for the failure. For more information, see Troubleshooting.

To view the available LLMs

  1. Sign in to BMC AMI AI Management Console User Interface with your credentials. 
  2. From the menu in the left pane, select AI Services Settings > LLM Settings

The Large language model (LLM) settings window is displayed. It lists all the LLMs available in the deployed BMC AMI AI Services.
image-2024-9-9_13-43-18.png

To view the status of BMC AMI AI Services

  1. Sign in to BMC AMI AI Management Console User Interface with your credentials. 
  2. From the menu in the left pane, click AI Service Health.
  3. Click a service category name to view information about its status.

The AI Service Health window is displayed. It shows the health status of each service category.
image-2024-9-9_14-58-8.png

The following table describes the service categories: 

Service category

Description

BMC AMI AI Platform Services

Status of the discovery service, gateway service, and security service

BMC AMI AI Integration Services

Status of the integration services available

Large Language Models

Status of the deployed LLMs

Each service displays a summary of the category. 

A green check mark confirms that all the services in that category are up and running.
image-2024-9-10_10-7-9.png

You can expand a service menu to see the service details, which include the following details:

  • Name of the service
  • Status of the service (Active/Inactive)
  • Host name of the container running the service
  • Port number of the service

If a service is inactive, the service category status icon displays the number of services that are down.
image-2024-9-10_10-34-13.png





 

Tip: For faster searching, add an asterisk to the end of your partial query. Example: cert*