Hacker News Reader

The pre-built pipeline components look interesting.

I wish Cloud AI offered an API for the kind of results that I get when I use Google Lens. None of the ML offerings seem to come even close with labels.

View on HN

Their Cloud Vision API [1] might be what you're looking for.

[1] https://cloud.google.com/vision

Yeah that's the one I was talking about. It gives some labels about stuff in the image and it works well. But Google Lens is on a different level -- you can send it a picture of a breed or a snake and it will return species and subspecies. Can't find anything like that in the GCP offering.

What sort of results do you get back from Cloud Vision API? The Google Lens example you mentioned is what I assumed it would do.

Nothing near that specific unfortunately. Not much more than "snake" (and occasionally wildly inaccurate species). At least with the ~20 or so photos that I just tested with.

Looks like you're not the only one who's interested: https://support.google.com/photos/thread/17424160?hl=en

Ah, thanks for pointing that out. Added my upvote. Cheers!

Also take a look at:

https://chooch.ai/

Reply on news.ycombinator.com