correa_brian

Can you send me an email to support at golivecosmos dot com? I think there's a way for us to try it out.

I'm working on a Windows version! Will let you know when it's ready!

CLIP is the vision model used for indexing media: https://openai.com/index/clip/

Understood. Thanks for checking it out. I'm not not offering a free trial, but can let you know if that changes.

Appreciate you checking it out! I'm not offering a free trial at the moment, but I'll definitely let you if that changes.

Not currently, but that is on roadmap to add soon. Right now you can search for famous people, but not custom tagging. I can let you know when this is supported.

Thank you for the feedback. Appreciate you taking a look. Right now there is a demo on Youtube: https://www.youtube.com/watch?v=EIUgPNHOKKc

Planning on adding more photos/videos to the site soon.

Indexing file metadata is on the roadmap. Right now Desktop Docs will render file metadata (resolution, file size, duration), but planning on making this a searchable field.

100%. Desktop Docs uses ffprobe under the hood to get file metadata.

It runs on both intel and Apple chips. I do think it's a bit faster on the silicon macs.

This feature is out!

You should see a "Delete" button on the "Logs" page on your next update.

Thanks for buying Desktop Docs! I'm actually working on this right now. Releasing an update shortly.

That's cool. I'm not a big Photos user, but I've heard some people really like it. Thanks for sharing!

This is awesome. Nice work.

I didn't realize there was an ML programming language! I also didn't know OCaml was part of the ML family.

If enough people asked for it, sure!

The resizing process doesn't introduce any compression artifacts but there is some loss when the images are processed by CLIP, depending on the dimensions.

CLIP likes perfect squares, so that's a limitation on the model size.

In terms of general compression are you familiar with FFmpeg? It has support for lossless compression into a bunch of different image formats.

I've given this some thought and it's definitely on the roadmap. A few other people have asked for this in the comments. Tagging people is very doable. Right now the model does a decent job with famous people, but not custom faces.

Seems like it's worth bumping this up in priority.

Love the name. I'll take a look too.

It doesn't specifically detect duplicates, but it's something I've considered adding. Would have to think through how to implement it, but seems doable.

Is this something you'd be interested in?

Working on it! I'll let you know when it's ready.

Never heard of Immich. I'll check it out!

Exactly

Correct. Videos are broken down into frames and each is indexed with a vision model. The images get scaled down to optimize for space. The more media you index, obviously that will increase the size of the index, so we're always looking for ways to improve the process for scale, like compressing the vectors or partitioning the embeddings so they can be stored elsewhere.

I'm still learning a lot about performance for this type of operation, so it's a work in progress.

Upgrades are included in the purchase! Once you install Desktop Docs you'll get the new versions automatically.

1) Yes the purchase includes upgrades. After you install those happen automatically.

2) This doesn't support NAS yet, but it's on the roadmap. If enough people are interested in that I'd bump it up in priority.

Exactly

For the best performance you'd probably want to use something other than CLIP's text encoder, but yeah you already have the text and could index it.

If enough people asked for it, I would consider adding a different embeddings models.

Correct. No text search, but it's something I'd consider adding if enough people asked for it.

Sounds cool! I haven't explored that but there are lots of interesting ways to approach this type of thing. Tons of creative ways to use these models.