Phil<p><span>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.<br><br>I organize my life in </span><a href="https://fed.bajsicki.com/tags/Emacs" rel="nofollow noopener noreferrer" target="_blank">#Emacs</a> <a href="https://fed.bajsicki.com/tags/orgmode" rel="nofollow noopener noreferrer" target="_blank">#orgmode</a><span> It's great.<br><br>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.<br><br>So I started using org-ql recently, which works great for a lot of cases, but not all.<br><br>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.<br><br>So I started writing some tooling for </span><a href="https://fed.bajsicki.com/tags/gptel" rel="nofollow noopener noreferrer" target="_blank">#gptel</a><span>, to allow LLMs to call tools within Emacs, and leverage existing packages to do just that. <br><br>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).<br><br>In general:<br>- It kinda works, when it wants to.<br>- The main failure point at the moment is that the LLM isn't able to consistently produce proper syntax for org-ql queries.<br>- The context window sucks, because I have years of journals and some queries unexpectedly explode, leading to the model going stupid.<br><br>So far it's been able to: <br>- retrieve journal entries<br>- summarize them<br>- provide insights on habits (e.g. exercise, sleep quality, eating times)<br>- track specific people across my journal and summarize interactions, sentiment, important events<br><br>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.<br><br>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.<br><br>At the same time, this is only part of my plan. Next:<br><br>1. Add proper org-agenda searches (such that the LLM can access information about tasks done/ planned)<br>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)<br>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)<br>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 </span><i>love</i><span> if it was more up to date with my journal, as an additional context resource)<br><br>For now, this is </span><i>neat</i><span>, 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.<br><br>So yeah. I'm </span><i>actually</i><span> pretty happy with this, so far. <br><br>PS. </span><a href="https://fed.bajsicki.com/tags/orgql" rel="nofollow noopener noreferrer" target="_blank">#orgql</a> because org-ql doesn't show as an existing tag.</p>