bolha.us is one of the many independent Mastodon servers you can use to participate in the fediverse.
We're a Brazilian IT Community. We love IT/DevOps/Cloud, but we also love to talk about life, the universe, and more. | Nós somos uma comunidade de TI Brasileira, gostamos de Dev/DevOps/Cloud e mais!

Server stats:

251
active users

#orgmode

19 posts17 participants1 post today

And just a day later, here's a git repo with more philosophy than good code.

I think the philosophy part is more important personally, the code we can fix later.

https://git.bajsicki.com/phil/gptel-org-tools

TL;DR: Emacs (and its ecosystem) makes the whole vectorization/ RAG/ training stuff entirely redundant for this application.

Yes, this code fails still... a bunch, especially given the current lack of guardrails. But the improvement I've seen in the last few days makes me cautiously believe that with enough safeguards and a motivating enough system prompt, an active assistant may be possible.

Image attached isn't
nearly as good as I've seen, but it's an off-hand example that demonstrates it working.

The only thing missing for me to be happy with this is one of those organic, grass-fed LLM models whose existence isn't predicated on theft.

#emacs #orgmode #gptel #orgql

RE:
https://fed.bajsicki.com/notes/a6jw3n155z

So... I strongly disagree with LLMs (mostly with the marketing and the training data issue), but I found a use-case for myself that they may actually be 'alright' at.

I organize my life in
#Emacs #orgmode . It's great.

But over the years, my notes and journals and everything have become so large, that I don't really have a grasp of all the bits and pieces that I have logged.

So I started using org-ql recently, which works great for a lot of cases, but not all.

Naturally, I wanted more consolidation between the results, and better filtering, as well as a more general, broad view of the topics I wanted to look up in my notes.

So I started writing some tooling for
#gptel, to allow LLMs to call tools within Emacs, and leverage existing packages to do just that.

It's in its inception, and works only 20-25% of the time (because the LLM needs to write the queries in the first place), but it works reasonably well even with smaller models (Mistral Small 24B seems to do alright with 16k context, using llama.cpp).

In general:
- It kinda works, when it wants to.
- The main failure point at the moment is that the LLM isn't able to consistently produce proper syntax for org-ql queries.
- The context window sucks, because I have years of journals and some queries unexpectedly explode, leading to the model going stupid.

So far it's been able to:
- retrieve journal entries
- summarize them
- provide insights on habits (e.g. exercise, sleep quality, eating times)
- track specific people across my journal and summarize interactions, sentiment, important events

It doesn't sound like a lot, but these are things which would take me more time to do in the next year than I already spent on setting this up.

And I don't need to do anything to my existing notes. It just reads from them as they are, no RAG, no preprocessing, no fuss.

At the same time, this is only part of my plan. Next:

1. Add proper org-agenda searches (such that the LLM can access information about tasks done/ planned)
2. Add e-mail access (via mu4e, so it can find all my emails from people/ businesses and add them as context to my questions)
3. Add org-roam searches (to add more specific context to questions - currently I'm basing this entire project around my journal, which isn't ideal)
4. Build tooling for updating information about people in my people.org file (currently I do this manually and while there's a bunch of stuff, I would
love if it was more up to date with my journal, as an additional context resource)

For now, this is
neat, and I think there's potential in this as a private, self-hosted personal assistant. Not ideal, not smart by any means (god it's really really not smart), but with sufficient guardrails, it can speed some of my daily/ weekly tasks up. Considerably.

So yeah. I'm
actually pretty happy with this, so far.

PS.
#orgql because org-ql doesn't show as an existing tag.

Überzeugte Benutzer:innen von #Emacs #orgmode können bei dem Video von @CT3003COOL drunter einen Kommentar hinterlassen, sich eventuell mal in einem anderen Video mit Org zu probieren. (Ich habe kein Account, um YouTube-Kommentare zu hinterlassen.)

Bei diesem Zielpublikum eine interessante Herausforderung, denn sowas wie lock-in Effekte, Migrationsaufwand, Möglichkeiten, an den Rohdaten selbst mitzufrickeln (extern generieren/auswerten, ...) kam gar nicht vor.

Wichtiger scheinen da optische Gimmicks wie Titelbilder, Emoticons und Gifs. Wer das nachvollziehen kann, darf sich bitte bei mir zwecks ein paar Fragen melden.

Endlich Leben im Griff 🤓 | #Anytype statt #Notion
youtube.com/watch?v=MKvDdsa6oy

Of course, if you do have long-time plans for your personal #knowledgemanagement, you should not use proprietary tools like #Obsidian, #OneNote, #Evernote and alike.

You also should think of switching to a much better (learnability, portability/compatibility, typobility, logic, featureset) markup syntax like #orgdown which is used in #Emacs #Orgmode (among other tools).

But if you start with Org-mode, you need to know the right way of doing it, as so many web pages recommend. Here's my take:

#UOMF: The Right Way to Use #OrgMode
karl-voit.at/2021/08/30/the-or

ad syntax/Markdown/Orgdown/#LML: karl-voit.at/2017/09/23/orgmod

A specific blog post about the #lockin effects of Obsidian and Co (despite using some tool-specific flavor of MD) is in the making. (Please don't start a religious discussion here.)

public voit - Web-page of Karl Voit · UOMF: The Right Way to Use Org ModeUOMF: The Right Way to Use Org Mode

For folks who are interested, I've been working on a macOS utility (pre-release) that acts as a proxy for Org Protocol URL requests. This utility is intended to complement another utility called Captee (yummymelon.com/captee/) which can send an Org Protocol request from the Share Menu. I'm currently looking for testers. If you're interested, please DM me your email address. Thanks!
#Emacs #OrgMode

yummymelon.comCaptee for macOSCaptee is an app that shares a link in either Markdown or Org syntax straight from the macOS Share menu.

#irreal and @bbatsov about #Emacs startup time: irreal.org/blog/?p=12903

I, too, am totally convinced that it really doesn't matter if it is one or sixty seconds.

However, if your bootup time is much longer than mine (15-30s once a week) then you most probably have room for improvement (if you want). Consistent use of #usepackage with dependencies and "defer" did help on my side.

My config has 7724 lines of #elisp (19851 including #orgmode comments): github.com/novoid/dot-emacs/bl

irreal.orgEmacs Startup Time | Irreal