microsoft/sample-app-aoai-chatGPT

Sample code for a simple web chat experience through Azure OpenAI, including Azure OpenAI On Your Data.

What it solves

This project provides a reference implementation of a chat web application that integrates with Azure OpenAI. It allows users to build a chat interface that can either function as a general-purpose AI assistant or a specialized bot that answers questions based on specific proprietary data (RAG).

How it works

The application connects to Azure OpenAI chat models (such as GPT-3.5 or GPT-4) via API. It supports two primary modes of operation:

  1. Basic Chat: A standard conversational interface using the deployed model.
  2. Chat with your data: A Retrieval-Augmented Generation (RAG) setup where the app queries a data source to provide grounded answers. It supports multiple vector and search indices, including Azure AI Search, Azure Cosmos DB (Mongo vCore), Elasticsearch, and Pinecone.

Who it’s for

Developers and architects looking to deploy a production-ready sample app to Azure to understand how to integrate Azure OpenAI with various data sources and authentication methods (like Microsoft Entra ID).

Highlights

  • Multi-source RAG support: Integrates with Azure AI Search, Cosmos DB, Elasticsearch, and Pinecone.
  • Flexible deployment: Supports deployment via Azure Developer CLI, one-click Azure deployment, or manual Azure CLI setup.
  • Enterprise-grade security: Includes options for identity-based authentication using Microsoft Entra ID and integration with Microsoft Defender for Cloud.
  • Customizable parameters: Allows fine-tuning of model behavior via environment variables for temperature, top-p, and strictness.

Related

  • Project
    Azure-Samples/azure-search-openai-demo

    A reference RAG chat application that allows users to interact with their own documents using Azure OpenAI and Azure AI Search.

  • Project
    Azure-Samples/serverless-chat-langchainjs

    A serverless AI chatbot implementation using LangChain.js and Azure, enabling Retrieval-Augmented Generation (RAG) to answer queries based on enterprise documents.

  • Project
    Azure-Samples/rag-postgres-openai-python

    A web-based chat application that uses RAG to answer questions about PostgreSQL database rows using hybrid search and OpenAI function calling.

  • Project
    Azure-Samples/chat-with-your-data-solution-accelerator

    A solution accelerator for building a conversational assistant that indexes unstructured organizational data to provide grounded answers with inline citations.

  • Project
    Azure/GPT-RAG

    An enterprise accelerator for building agentic RAG solutions on Microsoft Foundry, featuring Zero-Trust security and multi-source data retrieval via Foundry IQ.