This repository provides a solution accelerator for deploying a private, secure chat application within an Azure tenant, leveraging Azure OpenAI Service. It's designed for organizations seeking to build internal chatbots that can converse with their proprietary data and integrate with enterprise services, offering enhanced privacy and control over network traffic and authentication.

How It Works

The solution enables users to deploy a chat interface that connects to Azure OpenAI Service for natural language processing. It supports chatting over custom data sources and integrates with enterprise systems. Key features include private deployment within an Azure subscription, network isolation, and enterprise-grade authentication, with recent updates focusing on Managed Identity for keyless security and support for private endpoints and ESLZ compliant deployments.

Quick Start & Requirements

• Installation: Use the Azure Developer CLI (azd). Run azd init -t microsoft/azurechat to initialize, then azd up to provision and deploy.
• Prerequisites: Azure subscription, Azure Developer CLI, and an identity provider setup (e.g., Entra ID).
• Resources: Deployment creates Azure resources.
• Documentation: Deploy to Azure documentation

Highlighted Details

• Managed Identity-based security for keyless authentication.
• Helper scripts (appreg_setup.ps1, appreg_setup.sh) for Entra ID App Registration.
• Support for private endpoints and ESLZ compliant deployments.
• Integration capabilities with internal services (e.g., ServiceNow).

Maintenance & Community

This is a Microsoft-maintained project. Contributions are welcome, subject to a Contributor License Agreement (CLA). The project adheres to the Microsoft Open Source Code of Conduct.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README. Compatibility for commercial use or closed-source linking would require clarification on licensing terms.

Limitations & Caveats

The README mentions that the Azure Portal deployment option only creates Azure resources, requiring separate application deployment steps via GitHub Actions. An identity provider must be configured for application security.