Question

A field-service company wants a lightweight app where technicians upload a photo of a wiring diagram and ask a typed question such as "Which terminal connects to the ground wire?" The app must reason over the image and the text together and return a written answer. Which model capability should you deploy in Azure AI Foundry to power this app?

Accepted Answer

A multimodal model that accepts both image and text inputs in the same prompt

Answer

A text-only chat completion model with a large context window

Answer

An image-generation model that produces new images from text prompts

Answer

A speech-to-text model that transcribes spoken audio into text