Hey everyone, I'm launching Dotient on Product Hunt this week and wanted to share what I've been building before the big day.
Dotient is a desktop app that lets you search your files by what they look like, not what you happened to name them two years ago. Everything runs completely offline, nothing leaves your machine. It also has a live graph view of your files, deep PDF search, and canvas workspaces for organizing everything.
I built it solo out of pure frustration with Windows File Explorer and the lack of any tool that actually understands your files without making you do all the work manually.
Would love to hear any questions or feedback before launch. Happy to talk through anything.
Congrats on the launch! Did I feel correctly that the Signals system is the part that truly separates this from off-the-shelf CLIP search with a nice UI? Letting users push the embedding space toward what they mean is a sharp call!
Dotient
@artstavenka1 Absolutely, signals are sort of the 'dark horse' of the app. They are absolutely necessary to fill in the gaps of unique/personal files so you are still able to search for them. They are also a great way to differentiate images. You can easily differentiate a blue jay from a cardinal, or a rope tornado from a wedge tornado.
Hey, how are we handling privacy in this? Like, what data actually leaves my device or workspace when I run Dotient on something sensitive?
Dotient
@romejerome Great Question Jerome! The answer is absolutely nothing. Nothing leaves your device. Everything is stored in the SQLite DB that is on your device. There is no server besides the small API that simply checks if your license key is valid or not, that is the only time something ever communicates outside of your device.
I love your website! Is the expected usage to train a signal before every unique search? If i had a bunch of group photos and I'm looking to search by name, I'd have to create a signal for each person by clicking a bunch of pictures they're in and not in?
Dotient
@noice30sugar Correct, if you were to label a specific person with a name then it would probably be best to select a few images they are in, maybe lower the threshold a bit just to see all the options. Then if there are certain images that just won't go away and have nothing to do with the person, create a negative signal to eliminate those images. Once the signal is just right, you really shouldn't have to do any more adjusting. Any new image you import of that person, the signal will include it.
Dotient
@daniellebe Time saved is sort of an unmeasurable statistic as some people are more organized than others. If your system already works for you then you should probably keep doing that. However if your a person like me that really doesn't spend enough time organizing, this is the perfect app. But yeah I see your point, organizing in it of itself takes time, so that is definitely another place time is saved.
BlockSurvey
Hey, I purchased and downloaded it. But upon opening the file it show it is corrupted. Can you help?
Dotient
@wilsonbright Hey Wilson, I saw your email. If you are simply on macOS then 90% of the time the issue can be solved with the instructions on this link: https://dotient.com/download/macos
Solid
Dotient
@tkeith In the future there will be ways to sync devices over a wifi connection, but nothing over some external server. That would go completely against Dotient's morals.
very cool! and beautifully designed!
is it only for images? any chance to support videos later? and documents files?
Dotient
@feiou_su It is not only for images, however images are one of the few things that are semantically supported. PDF's being the other file type. Videos will eventually be supported, just a bit tricky with ffmpeg. But yeah besides PDF's and images, everything else is BM25 based search.