gptel-org-tools update.
Edit: there's some kind of issue with @Codeberg@social.anoxinon.de which prevents the link from working (returns 404). The old (but up to date) repo is here: git.bajsicki.com/phil/gptel-or…
1. Cloned to codeberg.org/bajsicki/gptel-or…, and all future work will be happening on Codeberg.
2. Added gptel-org-tools-result-limit and a helper function for it. This sets a hard limit on the number of characters a tool can return. If it's over that, the LLM is prompted to be more specific in its query. Not applied to all tools, just the ones that are likely to blow up the context window.
3. Added docstrings for the functions called by the tools, so LLMs can look up their definitions.
... show moregptel-org-tools update.
Edit: there's some kind of issue with @Codeberg@social.anoxinon.de which prevents the link from working (returns 404). The old (but up to date) repo is here: git.bajsicki.com/phil/gptel-orâŠ
1. Cloned to codeberg.org/bajsicki/gptel-orâŠ, and all future work will be happening on Codeberg.
2. Added gptel-org-tools-result-limit and a helper function for it. This sets a hard limit on the number of characters a tool can return. If it's over that, the LLM is prompted to be more specific in its query. Not applied to all tools, just the ones that are likely to blow up the context window.
3. Added docstrings for the functions called by the tools, so LLMs can look up their definitions.
4. Improved the precision of some tool descriptions so instructions are easier to follow.
5. Some minor improvements w/r/t function names and calls, logic, etc. Basic QA.
Now, as a user:
1. I'm finding it increasingly frustrating that Gemma 3 refuses to follow instructions. So here's a PSA: Gemma 3 doesn't respect the system prompt. It treats it just the same as any other user input.
2. Mistral 24B is a mixed bag. I'm not sure if it's my settings or something else, but it fairly consistently ends up looping; it'll call the same tool over and over again with the exact same arguments. This happens with other models as well, but not nearly as frequently.
3. Qwen 2.5 14B: pretty dang good, I'd say. The Cogito fine-tune is also surprisingly usable.
4. Prompting: I have found that a good, detailed system prompt tends to /somewhat/ improve results, especially if it contains clear directions on where to look for things related to specific topics. I'm still in the middle of writing one that's accurate to my Emacs set-up, but when I do finish it, it'll be in the repository as an example.
5. One issue that I still struggle with is that the LLMs don't take any time to process the user request. Often they'll find some relevant information in one file, and then decide that's enough and just refuse to look any further. Often devolving into traversing directories /as if/ they're looking for something... and they get stuck doing that without end.
It all boils down to the fact that LLMs aren't intelligent, so while I have a reasonable foundation for the data collection, the major focus is on creating guardrails, processes and inescapable sequences. These will (ideally) railroad LLMs into doing actual research and processing before they deliver a summary/ report based on the org-mode notes I have.
Tags:
#Emacs #gptel #codeberg #forgejo #orgmode #orgql #llm #ai #informationmanagement #gptelorgtools
Tooling for LLM interactions with org-mode. Requires gptel and org-ql.
Phil's Git
