Setting up GroundX On-Prem on AWS

A Simple Guide to Installing GroundX On-Prem onto AWS

In this tutorial we’ll deploy GroundX On-Prem onto AWS, and then use that On-Prem instance to implement Retrieval Augmented Generation (RAG) in a manner that can be isolated from all external dependencies. isolated RAG might be useful in a variety of use cases, especially those where RAG functionality is required within highly secure environments.

GroundX On-Prem is offered in a variety of forms:

  1. As a free and open source repo (github)
  2. As a paid product with more advanced capabilities than the free version
  3. As a service with white glove support

We’ll be using the free and open source version.

⚠️ Warning ⚠️

The resources created by following this guide will incur cost via AWS. It is recommended to follow all instructions accurately and completely. Taredown instructions are provided which, when followed, will properly discard all created resources. Experience with AWS is recommended.

Prerequisites

Please ensure you have the following software tools installed before proceeding:

  • bash shell (version 4.0 or later recommended. AWS Cloud Shell has insufficient resources.)
  • terraform (Setup Docs)
  • AWS CLI (Setup Docs)
  • kubectl (Setup Docs)

1) Defining the Infrastructure

Naturally, a good first step is to clone this repo. If you haven’t yet, run

$git clone https://github.com/eyelevelai/eyelevel-iac.git

Then run

$cd eyelevel-iac/
>cp environment/aws/env.tfvars.example environment/aws/env.tfvars

env.tfvars is the configuration file terraform will use when defining the resources. The content of env.tfvars can be modified to update this configuration as necessary. By copying env.tfvars.example to env.tfvars you will be using the default configuration.

Once that’s been set up, you can trigger terraform to set up the requisite resources via the following command:

$environment/aws/setup-eks

You will be prompted for an AWS region to set up your cluster, and will also be asked to double check that you’re happy with the state of the configuration file.

Once this command has executed all infrasturcual resources will have been created, and you can proceed to deploying GroundX.

2) Deploying GroundX

Not that the compute resources necessary to deploy GroundX have been constructed, we can deploy GroundX onto those resources.

First, run

$cp operator/env.tfvars.example operator/env.tfvars

This copies an example config file for the GroundX application, similarly to what was done in step 1. Now, however, some configuration is required.

For security reasons, you MUST modify the following within operator/env.tfvars:

  • admin.api_key: Set this to a random UUID. You can generate one by running bin/uuid. This will be the API key associated with the admin account and will be used for inter-service communications.
  • admin.username: Set this to a random UUID. You can generate one by running bin/uuid. This will be the user ID associated with the admin account and will be used for inter-service communications.
  • admin.email: Set this to the email address you want associated with the admin account.

once operator/env.tfvars has been properly configured, run

$operator/setup

This will deploy GroundX On-Prem onto the kubernetes cluster defined in Step 1.

3) Setting Up A Client To Talk TO GroundX On-Prem

Once the setup is complete, run kubectl -n eyelevel get svc to get the API endpoint. It will be the external IP associated with the GroundX load balancer.

For instance, the “external IP” might resemble the following:

EXTERNAL-IP
b941a120ecd91455fa7b8682be2a9e41-1427794132.us-east-2.elb.amazonaws.com

That endpoint, in conjunction with the admin.api_key defined when configuring operator/env.tfvars, can be used to configure the GroundX SDKs to communicate with your On-Prem instance of GroundX.

1from groundx import GroundX
2
3external_ip = "b941a120ecd91455fa7b8682be2a9e41-1427794132.us-east-2.elb.amazonaws.com"
4api_key="xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
5
6client = GroundX(api_key=api_key, base_url=f"http://{external_ip}/api")

A GroundX client which points to an On-Prem instance of GroundX behaves similarly to a traditional client which points to the hosted version of GroundX. See the API Documentation for more tutorials and documentation about specific endpoints and their usage.