this post was submitted on 25 Jun 2025
446 points (97.0% liked)
memes
15756 readers
3652 users here now
Community rules
1. Be civil
No trolling, bigotry or other insulting / annoying behaviour
2. No politics
This is non-politics community. For political memes please go to !politicalmemes@lemmy.world
3. No recent reposts
Check for reposts when posting a meme, you can only repost after 1 month
4. No bots
No bots without the express approval of the mods or the admins
5. No Spam/Ads
No advertisements or spam. This is an instance rule and the only way to live.
A collection of some classic Lemmy memes for your enjoyment
Sister communities
- !tenforward@lemmy.world : Star Trek memes, chat and shitposts
- !lemmyshitpost@lemmy.world : Lemmy Shitposts, anything and everything goes.
- !linuxmemes@lemmy.world : Linux themed memes
- !comicstrips@lemmy.world : for those who love comic stories.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I recently did a project.
Self-hosted Ntfy as communication, python bot in a container. If you say remember something It drops it into a text file verbatim. If you say remind me, It loads the text file into an ollama AI RAG and queries it with whatever you asked it to remind you. At the moment it can take a good 5 seconds to get back to you.
Then I added a grocery list and a separate bot that handles scheduling reminders. Remind me in 20 minutes to feed the dog. Forget this item. Remind me on the 20th of every April that it's fu's birthday.
At the moment, it's based on keywords and if you don't specify a keyword it just asks the model directly. I'm thinking about having it send all requests through the model and giving the model a prompt that has a determines what you're trying to do and translates that to a keyword that the bot can act on.