get-started-app-chat-scaling-with-azure-container-apps.md

title	description	ms.date	ms.topic	ms.subservice	ms.custom	ms.collection
Scale Azure OpenAI for Python chat sample using RAG	Learn how to add load balancing to your application to extend the chat app beyond the Azure OpenAI token and model quota limits.	05/13/2024	get-started	intelligent-apps	devx-track-python, devx-track-python-ai, build-2024-intelligent-apps	ce-skilling-ai-copilot

Scale Azure OpenAI for Python chat using RAG with Azure Container Apps

[!INCLUDE aca-load-balancer-intro]

Prerequisites

• Azure subscription. Create one for free

• Access granted to Azure OpenAI in the desired Azure subscription.

  Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at https://aka.ms/oai/access.

• Dev containers are available for both samples, with all dependencies required to complete this article. You can run the dev containers in GitHub Codespaces (in a browser) or locally using Visual Studio Code.

  Codespaces (recommended)

  • GitHub account

  Visual Studio Code

  • Docker Desktop - start Docker Desktop if it's not already running
  • Visual Studio Code
  • Dev Container Extension

  ---

[!INCLUDE scaling-load-balancer-aca-procedure.md]

[!INCLUDE py-deployment-procedure]

[!INCLUDE logs]

[!INCLUDE capacity.md]

[!INCLUDE py-aca-cleanup]

Sample code

Samples used in this article include:

• Python chat app with RAG
• Load Balancer with Azure Container Apps

Next step

• Use Azure Load Testing to load test your chat app with