Overview

Activate GenAI with Azure — A smart and scalable document retrieval solution

Description

Activate GenAI with Azure is a new delivery that leverages the power of artificial intelligence and cloud computing to provide a smart and scalable document search retrieval solution. The solution uses Azure OpenAI, Cognitive Search, Container Apps, Application Insights, and Azure API Management to create a chat interface that can answer user queries with relevant documents, suggested follow-up questions, and citations. The solution also allows users to upload custom data files and perform vector search using semantic or hybrid methods. Additionally, the solution supports extensibility through plugins, charge back functionality, security features such as authentication and authorization, monitoring capabilities, and scalability options.

Pre-requisites

To use this solution, you will need the following:

  • An Azure subscription
  • A User, Service Principal or Managed Identity with the following permissions:
    • Contributor role on the Azure subscription
  • Azure CLI v2.53.0 or later
  • Terraform v1.6.0 or later

High-level Architecture

The following diagram shows the high-level architecture of the Activate GenAI with Azure solution:

High-level Architecture

Objectives

By the end of this delivery, you will be able to:

  • Configure and deploy the Activate GenAI with Azure solution
  • Use the chat interface to query documents and get relevant results
  • Upload custom data files and perform vector search
  • Extend the solution with plugins
  • Manage the charge back functionality
  • Secure and monitor the solution
  • Scale and integrate the solution with other services

Delivery Guidance

This delivery consists of the following steps:

Day 1:

  1. Scoping and planning.
  2. Prepare the environment.
  3. Adapt deployment scripts according to the customer’s requirements.

Day 2:

  1. Deploy the Activate GenAI with Azure solution: Create and configure the Azure resources.
  2. Test and use the chat interface to query documents.
  3. Upload custom data files and perform vector search.

Day 3:

  1. Customize the solution’s look and feel.
  2. Extend the solution with prompt engineering and plugins.
  3. Show how the solution scales and integrates with other services.
  4. Show how the security and monitoring works.
  5. Plan the next steps.

Closing

By the end of the Activate GenAI with Azure delivery, stakeholders will have a powerful and innovative solution that can help them improve their document retrieval efficiency, enhance their user experience, increase their productivity, share their knowledge, gain data insights and analytics, and comply with security standards.ss


Last modified March 1, 2024: Add files via upload (f2a7d32)