Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

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

Number of Required Servers

POC Requirements

Purpose

AWS

On Premise

Gateway (Linux)

t3a.large ($0.0752 + tax)

4 cores, 8 GB RAM

Dashboard / Ingestor (Windows)

t3a.large ($0.1028 + tax)

4 cores, 8 GB RAM

...

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

Load Balancer

EC2 Application Load Balancer

...

 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.

    Configure to use Databases located on Gateway server.

    How to create an Azure integration with BusinessGPT

  4. How to install GPT Gateway

  5. How to install BG Dashboard

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.