RAG chat app with Azure OpenAI and Azure AI Search (Python)

This solution creates a ChatGPT-like frontend experience over your own documents using RAG (Retrieval Augmented Generation). It uses Azure OpenAI Service to access GPT models, and Azure AI Search for data indexing and retrieval.

This solution's backend is written in Python. There are also JavaScript, .NET, and Java samples based on this one. Learn more about developing AI apps using Azure AI Services.

Important Security Notice

This template, the application code and configuration it contains, has been built to showcase Microsoft Azure specific services and tools. We strongly advise our customers not to make this code part of their production environments without implementing or enabling additional security features. See our productionizing guide for tips, and consult the Azure OpenAI Landing Zone reference architecture for more best practices.

Table of Contents

• Features
• Azure account requirements
• Cost estimation
• Getting Started
• GitHub Codespaces
• VS Code Dev Containers
• Local environment
• Deploying
• Deploying again
• Running the development server
• Using the app
• Clean up
• Guidance
• Resources

📺 Watch a video overview of the app.

This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data using the Retrieval Augmented Generation pattern. It uses Azure OpenAI Service to access a GPT model (gpt-5.4-mini), and Azure AI Search for data indexing and retrieval.

The repo includes sample data so it's ready to try end to end. In this sample application we use a fictitious company called Zava, and the experience allows its employees to ask questions about the benefits, internal policies, as well as job descriptions and roles.

Features

• Chat (multi-turn) interface
• Renders citations and thought process for each answer
• Includes settings directly in the UI to tweak the behavior and experiment with options
• Integrates Azure AI Search for indexing and retrieval of documents, with support for many document formats as well as cloud data ingestion
• Optional usage of multimodal models to reason over image-heavy documents
• Optional addition of speech input/output for accessibility
• Optional automation of user login and data access via Microsoft Entra
• Performance tracing and monitoring with Application Insights

Architecture Diagram

Azure account requirements

IMPORTANT: In order to deploy and run this example, you'll need:

• Azure account. If you're new to Azure, get an Azure account for free and you'll get some free Azure credits to get started. See guide to deploying with the free trial.
• Azure account permissions:
• Your Azure account must have Microsoft.Authorization/roleAssignments/write permissions, such as Role Based Access Control Administrator, User Access Administrator, or Owner. If you don't have subscription-level permissions, you must be granted RBAC for an existing resource group and deploy to that existing group.
• Your Azure account also needs Microsoft.Resources/deployments/write permissions on the subscription level.

Cost estimation

Pricing varies per region and usage, so it isn't possible to predict exact costs for your usage. However, you can try the Azure pricing calculator for the resources below.

• Azure Container Apps: Default host for app deployment as of 10/28/2024. See more details in the ACA deployment guide. Consumption plan with 1 CPU core, 2 GB RAM, minimum of 0 replicas. Pricing with Pay-as-You-Go. Pricing
• Azure Container Registry: Basic tier. Pricing
• Azure App Service: Only provisioned if you deploy to Azure App Service following the App Service deployment guide. Basic Tier with 1 CPU core, 1.75 GB RAM. Pricing per hour. Pricing
• Azure OpenAI: Standard tier, GPT and Ada models. Pricing per 1K tokens used, and at least 1K tokens are used per question. Pricing
• Azure AI Document Intelligence: SO (Standard) tier using pre-built layout. Pricing per document page, sample documents have 261 pages total. Pricing
• Azure AI Search: Basic tier, 1 replica, free level of semantic search. Pricing per hour. Pricing
• Azure Blob Storage: Standard tier with ZRS (Zone-redundant storage). Pricing per storage and read operations. Pricing
• Azure Cosmos DB: Only provisioned if you enabled chat history with Cosmos DB. Serverless tier. Pricing per request unit and storage. Pricing
• Azure AI Vision: Only provisioned if you enabled multimodal approach. Pricing per 1K transactions. Pricing
• Azure AI Content Understanding: Only provisioned if you enabled media description. Pricing per 1K images. Pricing
• Azure Monitor: Pay-as-you-go tier. Costs based on data ingested. Pricing

To reduce costs, you can switch to free SKUs for various services, but those SKUs have limitations. See this guide on deploying with minimal costs for more details.

⚠️ To avoid unnecessary costs, remember to take down your app if it's no longer in use, either by deleting the resource group in the Portal or running azd down.

Getting Started

You have a few options for setting up this project. The easiest way to get started is GitHub Codespaces, since it will setup all the tools for you, but you can also set it up locally if desired.

GitHub Codespaces

You can run this repo virtually by using GitHub Codespaces, which will open a web-based VS Code in your browser:

Once the codespace opens (this may take several minutes), open a terminal window.

VS Code Dev Containers

A related option is VS Code Dev Containers, which will open the project in your local VS Code using the Dev Containers extension:

1. Start Docker Desktop (install it if not already installed)

2. Open the project:

3. In the VS Code window that opens, once the project files show up (this may take several minutes), open a terminal window.

Local environment

1. Install the required tools:

   • Azure Developer CLI
   • Python 3.10, 3.11, 3.12, 3.13, or 3.14
   • Important: Python and the pip package manager must be in the path in Windows for the setup scripts to work.
   • Important: Ensure you can run python --version from console. On Ubuntu, you might need to run sudo apt install python-is-python3 to link python to python3.
   • Node.js 20+
   • Git
   • Powershell 7+ (pwsh) - For Windows users only.
   • Important: Ensure you can run pwsh.exe from a PowerShell terminal. If this fails, you likely need to upgrade PowerShell.

2. Create a new folder and switch to it in the terminal.

3. Run this command to download the project code:

   shell azd init -t azure-search-openai-demo

   Note that this command will initialize a git repository, so you do not need to clone this repository.

Deploying

The steps below will provision Azure resources and deploy the application code to Azure Container Apps. To deploy to Azure App Service instead, follow the app service deployment guide.

1. Login to your Azure account:

   shell azd auth login

   For GitHub Codespaces users, if the previous command fails, try:

shell azd auth login --use-device-code

1. Create a new azd environment:

   shell azd env new

   Enter a name that will be used for the resource group. This will create a new folder in the .azure folder, and set it as the active environment for any calls to azd going forward. 1. (Optional) This is the point where you can customize the deployment by setting environment variables, in order to use existing resources, enable optional features (such as auth or vision), or deploy low-cost options, or deploy with the Azure free trial. 1. Run azd up - This will provision Azure resources and deploy this sample to those resources, including building the search index based on the files found in the ./data folder. - Important: Beware that the resources created by this command will incur immediate costs, primarily from the AI Search resource. These resources may accrue costs even if you interrupt the command before it is fully executed. You can run azd down or delete the resources manually to avoid unnecessary spending. - You will be prompted to select two locations, one for the majority of resources and one for the OpenAI resource, which is currently a short list. That location list is based on the OpenAI model availability table and may become outdated as availability changes. 1. After the application has been successfully deployed you will see a URL printed to the console. Click that URL to interact with the application in your browser. It will look like the following:

NOTE: It may take 5-10 minutes after you see 'SUCCESS' for the application to be fully deployed. If you see a "Python Developer" welcome screen or an error page, then wait a bit and refresh the page.

Deploying again

If you've only changed the backend/frontend code in the app folder, then you d