An Azure-based reference accelerator where multiple specialized AI agents plan and execute user-specified organizational tasks, built on Microsoft Agent Framework and Azure AI Foundry.
Azure-Samples/openai-chat-app-quickstart
A Python chat web app that calls Azure OpenAI with managed identity, provisioned and deployed to Azure Container Apps via azd.
- Stars
- 254
- Forks
- 140
- Open issues
- 24
- Last commit
- 7 days ago
What is it?
This template is a small Python chat application that generates responses to user messages with Azure OpenAI. The backend is a Quart app using the openai package, and the browser frontend streams replies from the server as JSON Lines over a ReadableStream.
The project also ships Bicep files that provision the Azure resources it needs: Azure OpenAI, Azure Container Apps, Azure Container Registry, Log Analytics, and the RBAC roles. By default the app authenticates to Azure OpenAI with managed identity instead of API keys. Running `azd up` provisions everything and deploys the app, and `azd deploy` redeploys after code changes.
For local development, you copy the sample environment file, fill in the endpoint and tenant ID from your deployed resources, and run the Quart server on port 50505. Codespaces and Dev Containers configurations are included for a ready-made environment.
Key features
- 01Python Quart backend that generates chat replies with the openai package
- 02Browser frontend that streams responses over JSON Lines
- 03Bicep templates provisioning Azure OpenAI, Container Apps, and Container Registry
- 04Managed identity authentication to Azure OpenAI by default
- 05Deployment with a single azd command
- 06Codespaces and Dev Containers setup included
Use cases
- Starting a chat front end on Azure OpenAI without storing API keys
- Learning how to deploy a Python AI app to Azure Container Apps
- Prototyping a simple chatbot that can be redeployed quickly with azd
Quick start
- 1
Download the project code with azd
azd init -t openai-chat-app-quickstart - 2
Log in to Azure
azd auth login - 3
Provision and deploy all resources to Azure
azd up
Things to know
- Requires an Azure subscription and approved access to Azure OpenAI Service.
- Running it costs money on Azure, and the README advises deleting resources when they are no longer needed.
In collections
Topics
FAQ
- What is openai-chat-app-quickstart?
- A Python chat web app that calls Azure OpenAI with managed identity, provisioned and deployed to Azure Container Apps via azd. This template is a small Python chat application that generates responses to user messages with Azure OpenAI. The backend is a Quart app using the openai package, and the browser frontend streams replies from the server as JSON Lines over a ReadableStream.
- Is openai-chat-app-quickstart free to use? What license does it have?
- openai-chat-app-quickstart is open source under the MIT license. Check the license terms before using it in commercial products.
- Is openai-chat-app-quickstart still maintained?
- Actively maintained. The last commit to openai-chat-app-quickstart was on Nov 1, 2026.
- What can I use openai-chat-app-quickstart for?
- Starting a chat front end on Azure OpenAI without storing API keys Learning how to deploy a Python AI app to Azure Container Apps Prototyping a simple chatbot that can be redeployed quickly with azd
- How do I install openai-chat-app-quickstart?
- Download the project code with azd: azd init -t openai-chat-app-quickstart Log in to Azure: azd auth login Provision and deploy all resources to Azure: azd up
- Where can I get openai-chat-app-quickstart?
- The source code and installation instructions are on GitHub: https://github.com/Azure-Samples/openai-chat-app-quickstart
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Azure-based solution accelerator that mines conversational and document data with generative AI, offering chat exploration and auto-generated insight dashboards.
An Azure-hosted RAG accelerator that grounds a chat assistant in your own documents, returning answers with inline citations to sources.
A RAG chat app that answers natural-language questions about rows in a PostgreSQL table, using pgvector search and OpenAI models, deployable to Azure.
Scripts and tools to evaluate RAG chat apps using the Azure AI Evaluate SDK and OpenAI-based graders.
Azure solution accelerator for a central AI API gateway built on Azure API Management, governing and observing LLM access across teams.