and you'd need AI to tell you whats in the pictures because lots of restaurant sites just have photos of their menu and some designer with no web knowledge put their phone number, address, and hours in an image designed in Photoshop

You're in for bad luck. Some time ago I tried some photos of pasta dishes with Gemini and it could not guess the recipe name.

I've found Gemini to be pretty terrible at vision tasks compared to the competition. Try GPT-4o or Claude-3.5-Sonnet instead.