Question

A developer wants to add a chat feature to an internal Python web app. A GPT model is already deployed in an Azure AI Foundry project. The developer needs the app to send user messages to the deployed model and receive responses programmatically, without building any infrastructure from scratch. Which approach best meets this requirement?

Accepted Answer

Use the Azure AI Foundry SDK to connect to the project and call the deployed model's chat completions endpoint from the Python code.

Answer

Fine-tune a new model in the Foundry portal each time a user sends a message.

Answer

Export the model weights from Foundry and host the model on a local server inside the web app.

Answer

Use Azure Content Understanding to process the chat messages and return responses.