I made a FOSS AI file organizer! (github.com)
from justzvan@lemmy.ml to programming@programming.dev on 18 Nov 11:35
https://lemmy.ml/post/22630858

Hey guys! I built an AI powered file organizer! This was my first “big” Python project!

#programming

threaded - newest

FourPacketsOfPeanuts@lemmy.world on 18 Nov 11:39 next collapse

Great work. Can you give some examples of how this works in practice?

Tagify leverages AI to automatically generate and manage tags for files

justzvan@lemmy.ml on 18 Nov 11:43 collapse

Well, my mom has a bit of a problem. She has TONS of unorganized images and documents. I’ll soon implement the folder scanning: so she can just drop in her documents/photos folder and scan the entire thing. Basically, it’s like docs.tagstud.io but I added AI to make the organization process faster.

FourPacketsOfPeanuts@lemmy.world on 18 Nov 13:09 collapse

Thanks

banghida@lemm.ee on 18 Nov 11:45 next collapse

I would not be happy sending a list of my files to 3rd parties. This is not local, it uses an API.

justzvan@lemmy.ml on 18 Nov 11:46 next collapse

Yeah, I know. I’m planning on adding ollama support.

Deckweiss@lemmy.world on 18 Nov 13:14 next collapse

github.com/QiuYannnn/Local-File-Organizer

sukhmel@programming.dev on 18 Nov 14:47 collapse

This is almost what I need for my ancient meme folder

justzvan@lemmy.ml on 18 Nov 14:56 collapse

lol

justzvan@lemmy.ml on 18 Nov 13:27 collapse

There: I added basic ollama support. It doesn’t currently support images, though.

lawrence@lemmy.world on 18 Nov 11:52 next collapse

Interesting. I was thinking about a project for image classification and description, so we could search for our images in an easy way.

infeeeee@lemm.ee on 18 Nov 12:58 next collapse

Some feedback:

  • On white background the text next to the logo is not visible
  • Add screenshots in the README, it’s a GUI app
  • Requirements.txts for dependency management is the old way, read about pyproject.toml you can merge them a single easy to read and edit file
  • "Install the dependencies" means nothing to a non-python developer. Direct users to install your project via pipx, that’s modern and secure way of installing a python application with dependencies for non developers. Publish it to pypi for even easier installation.
  • Add a notice that currently it’s windows only os.path.join(os.environ[“APPDATA”], “Tagify”, “config.yaml”) will fail on *nix systems. Use pathlib.Path instead of os.path. Use pathlib, I see on a lot more places it would make your life much easier.
  • I have a feeling that the file icons are not your work. If you copied them from somewhere make sure their license is compatible, and add an acknowledgement.

Keep up the work, it seems like a nice project!

justzvan@lemmy.ml on 18 Nov 13:51 collapse

Thanks! I fixed the file icon licensing! However, I’m not sure will pipx help. I already provide a binary Inno Setup installer. Any suggestions how to port it to Linux? I dual boot - so it would be very useful for me.

infeeeee@lemm.ee on 18 Nov 14:51 collapse

Python is installed by default on all linux and mac systems, so it’s just one more command to install pipx. From there just pipx install tagify. You don’t need an installer, just specify the build tools in pyproject.toml: packaging.python.org/en/latest/…/pyproject-toml/#… e.g. with setuptools: setuptools.pypa.io/en/…/pyproject_config.html

If you publish to pypi it will build the wheel files when you publish a version. That’s the easiest way I know.

Innosetup is windows only. On linux you don’t need such a thing.

RonSijm@programming.dev on 18 Nov 14:20 next collapse

Also some feedback, a bit more technical, since I was trying to see how it works, more of a suggestion I suppose

It looks like you’re looping through the documents and asking it for known tags, right? ({str(db.current_library.tags)}.)

I don’t know if I would do this through a chat completion and a chat response, there are special functions for keyword-like searching, like embeddings. It’s a lot faster, and also probably way cheaper, since you’re paying barely anything for embeddings compared to chat tokens

So the common way to do something like this in AI would be to use Vectors and embeddings: platform.openai.com/docs/guides/embeddings

So - you’d ask for an embedding (A vector) for all your tags first. Then you ask for embeddings of your document.

Then you can do a Nearest Neighbor Search for the tags, and see how closely they match

justzvan@lemmy.ml on 18 Nov 15:01 collapse

Cool! But one problem: I’m not using OpenAI. It supports Mistral, ollama and xtekky’s gpt4free

GBU_28@lemm.ee on 18 Nov 15:07 next collapse

Embeddings are not unique to openai.

RonSijm@programming.dev on 18 Nov 16:45 collapse
doomsdayrs@lemmy.ml on 18 Nov 16:03 collapse

Ah, Finally someone had the same idea as me, and actually implemented it.

justzvan@lemmy.ml on 18 Nov 16:26 collapse

It’s Windows only though