If you read my previous post on Google's Gemini AI launch, you may have seen my test prompts asking it to identify the kind of cat shown in a picture. I decided to turn this into a proper web application as a real example of the API in action.
By using `capture='camera'` on an input tag, you directly get access to the device camera. There are more advanced ways of doing this, but for quick and simple, it works fine. Even better, on desktop, it simply acts as a file selector.
[
add
]
[
|
|
...
]