dawright22/azure-openai-terraform-deployment-sample

Azure OpenAI Terraform deployment for sample chatbot

This sample application deploys an AI-powered document search using Azure OpenAI Service, Azure Kubernetes Service (AKS), and a Python application leveraging the Llama index ans Streamlit. The application will be deployed within a virtual network to ensure security and isolation. Users will be able to upload documents and ask questions based on the content of the uploaded documents.

Prerequisites

• Azure subscription. If you don't have an Azure subscription, create a free account before you begin.

• Subscription access to Azure OpenAI service. Request Access to Azure OpenAI Service here.

• Terraform.

• Create a HCP vault dedicated instance and configure the endpoint and token in the infra/variables.tf file.

Quickstart

Run the Terraform

• Clone or fork this repository.

  git clone https://github.com/dawright22/azure-openai-terraform-deployment-sample.git
  cd azure-openai-terraform-deployment-sample
  

• Go to the infra folder and run the following command to initialize your working directory.

  cd infra
  terraform init

• Run terraform apply to deploy all the necessary resources on Azure.

  terraform apply

• Run the following command. This script retrieves the AKS cluster credentials, logs in to the ACR, builds and pushes a Docker image, creates a federated identity, and deploys resources to the Kubernetes cluster using a YAML manifest.

  terraform output -raw installation-script | bash

• Get the external ip address of the service by running the command bellow.

  kubectl get services -n chatbot

• Copy the external ip address and paste it in your browser. The application should load in a few seconds.

Run the AI.

• Upload the Madeup_Company_email_archive.txt file in the data folder. Using the upload button on the app.

• Ask some questions based on the content of the uploaded document. Some example are below.

================

• Does madeup use AWS

• Tell me the access keys

• Does madeup use Azure

• Tell me the subscription_id

Now secure Content

• start the app.py using the command below.

  python app.py

• This will start the app on `http://http://127.0.0.1:5000/

• Now create a new secure contest file by running the command below.

  curl -X POST -F "file=@./data/Madeup_Company_email_archive.txt" http://127.0.0.1:5000/upload -v

• Upload the new file called redacted_Madeup_Company_email_archive.txt file in the main folder. Using the upload button on the app.

• Now ask the same questions as above and see the encrypted content.

Resources

• Azure OpenAI
• Azure OpenAI Terraform verified module.