Re: Org tag generator?

[Jean Louis <bugs@gnu.support>]

* Christopher Howard <christopher@librehacker.com> [2024-12-24 19:35]:
> Jean Louis <bugs@gnu.support> writes:
> 
> > and then relate it to "toddler" and then if any of such word is
> > mentioned let us say "more than once" in section, it could get a tag.
> >
> > So I could make a function to verify if any of defined words is
> > mentioned more than once.
> 
> Now you are recommending a system whereby I myself have to manual recognize and record all specific words that lead me to assign a specific tag. This works, in a sense, but does nothing to reduce my work load. There might be, for example, thousands of plant-related words that lead me to apply the tag :botany:. I don't want to have to figure out what those words are specifically and make a record of them. I just want to intuitively apply the tag :botany: and then the software figures out, after observing many nodes, that the words "rainforest" or "flower" or should generate the tag :botany:.

Sounds like you wish to use the features of text recognition as it is
today provided in Large Language Model (LLM) software.

Try it out here:
https://huggingface.co/spaces/Qwen/Qwen2.5

Give it the instruction. Here is example:


Give me name of 3 different flowers

Sure! Here are three different flowers:

    Rose - Known for its beauty and fragrance, the rose is a popular flower available in many colors such as red, pink, white, and yellow.

    Daisy - Characterized by its simple, charming appearance with white petals and a yellow center, the daisy symbolizes innocence and purity.

    Tulip - A spring favorite, tulips come in a variety of colors and are known for their cup-shaped blooms. They are often associated with the Netherlands.

Give me 3 different car models

Certainly! Here are three different car models:

    Toyota Camry - A popular mid-size sedan known for its reliability and fuel efficiency.
    Ford Mustang - An iconic American muscle car known for its powerful engines and sporty design.
    Tesla Model S - A high-performance electric sedan known for its advanced technology, long range, and sleek design.

I will now give you lines, and you will recognize if some of these tags apply: '("BOTANY", "TRANSPORT", "TRAVEL", "GARDEN"), return tags joined with colon : suitable for Org mode.

Sure, I can help with that! Please provide the lines, and I'll tag them accordingly.

Toyota Camry - A popular mid-size sedan known for its reliability and fuel efficiency.

TRANSPORT
(the above answer TRANSPORT was given by software)

Daisy - Characterized by its simple, charming appearance with white petals and a yellow center, the daisy symbolizes innocence and purity.

BOTANY:GARDEN

--------------(づ｡◕‿‿◕｡)づ --------------------------

Once you gain understanding, then you can integrate it in Emacs to
become very very effortless.

I would gather list of those tags and then just add tags by using LLM,
it is on-the-fly.

Here is small demo how integration within Emacs works, though I don't
think this model is suitable for that task of tagging:
https://yewtu.be/watch?v=XrK-X7LZ6aE

I would make it so:

1. Make function to tag your Org documents.
2. Copy original-file.org to tagged-file.org for safety.
3. Work on tagged-file.org
4. Extract list of all Org files automatically.
5. Parse each section and use that list to invoke LLM, to return the tags. 
6. Insert returned tags by Emacs function into the section header.
7. Continue parsing.
8. Continue with all files.

-- 
Jean Louis