For deployments using Open AI or AWS Bedrock APIs and not local LLMs.

Number of Required Servers

POC Requirements

1x Linux Instance ( Gateway)

100 GB SSD disk

1x Windows Instance (Dashboard/ Ingestor)

t3a.large- 80GB SSD disk

1x Microsoft SQL Server Express. May be co-located.

SSL certificate (optional)

Customer may provide an SSL certificate to secure access to the dashboard website.

Network Access

Ensure that the BGPT dashboard server has network access to any privately hosted services containing data that needs to be ingested. E.g. Data Center confluence.

 SSL certificate (optional)

Customer may provide an SSL certificate to secure access to the dashboard website.

Load Balancer

EC2 Application Load Balancer

Required if using more than one server for each component.

 Minimum Required Permissions for AGAT

AGAT Remote Access Recommendations

During Deployment

Continuous RDP/ SSH / all ports access to servers from AGAT offices static IP address

Optional - IAM access to deploy instances and set up security configuration

After Deployment

Temporary access for support from AGAT offices static IP address

Installation Process

1. Create AWS instances or On Prem VMs. See above for details.

2. Install Gateway docker container using Docker Compose Files provided.

   1. Configure Open AI keys on docker.env file.

3. Install Windows Dashboard and Ingestor.

   1. Configure to use Databases located on Gateway server.

Notes

1. Username and password authentication works out of the box. SSO authentication using Azure or Google requires the customer to create and application registration with Azure/Google and to enter the App ID + Secret key in the Business GPT interface.