azure-search-openai-demo

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to pow

What is azure-search-openai-demo?

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

Overview of azure-search-openai-demo

What it is

A sample application for the Retrieval-Augmented Generation (RAG) pattern running in Azure. It uses Azure AI Search for document retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences over your own data. The backend is written in Python, with JavaScript, .NET, and Java variants available. The repository includes sample data about a fictitious company called Zava, covering benefits, internal policies, and job descriptions.

Key features

  • Chat (multi-turn) interface with rendered citations and thought process for each answer - Settings in the UI to tweak behavior and experiment with options - Integrates Azure AI Search for indexing and retrieval of documents, supporting many document formats and 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

Use cases

  • Creating a ChatGPT-like frontend over your own documents using RAG - Enabling employees to ask questions about benefits, internal policies, job descriptions, and roles - Any scenario requiring question answering over a custom knowledge base with citation support

Getting started

You can run this project using GitHub Codespaces, VS Code Dev Containers, or a local environment. For local setup: 1. Install Azure Developer CLI, Python 3.10–3.14, Node.js 20+, Git, and PowerShell 7+ (Windows). 2. Create a new folder and run: shell azd init -t azure-search-openai-demo 3. Login to Azure: shell azd auth login 4. Create a new environment: shell azd env new 5. Run azd up to provision resources and deploy. See the repository README for full details on GitHub Codespaces and Dev Containers.

License and pricing

The project is licensed under the MIT License. It is open source. Running the sample incurs Azure service costs; the README includes a cost estimation section with pricing details for each resource (e.g., Azure Container Apps, Azure OpenAI, Azure AI Search).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/azure-samplesazure-search-openai-demo.svg)](https://yunodb.com/tools/azure-samplesazure-search-openai-demo?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/azure-samplesazure-search-openai-demo?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/azure-samplesazure-search-openai-demo.svg" alt="Featured on YunoDB" height="20"></a>