Home
JAQForum Ver 24.01
Log In or Join  
Active Topics
Local Time 06:04 13 Jul 2025 Privacy Policy
Jump to

Notice. New forum software under development. It's going to miss a few functions and look a bit ugly for a while, but I'm working on it full time now as the old forum was too unstable. Couple days, all good. If you notice any issues, please contact me.

Forum Index : Microcontroller and PC projects : Pico/Wembite User manual in docx available?

Author Message
stef123
Regular Member

Joined: 25/09/2024
Location: United Kingdom
Posts: 89
Posted: 06:56am 07 Dec 2024
Copy link to clipboard 
Print this post

Hi,

the reason why i am asking for this - i´d like to feed an LLM/Vector Database with the Informations given in the User Manual, but extracting them from the PDFs leads into a bit of a mess, because the solid line which separates the commands from their explanation sometimes destroys the connection between them when converting from PDF.

My goal is that the LLM should be able to create Pico/Webmite programs, but i know that it is not simply done by pushing a manual into the Vector Database, i will need to perform several adjustments on how and when to use the commands, but for that i also i need a good base to work with. Its just a try and no guarantee that it will work at all.

Many thanks!

Best regards
Stef
 
Mixtel90

Guru

Joined: 05/10/2019
Location: United Kingdom
Posts: 7871
Posted: 07:52am 07 Dec 2024
Copy link to clipboard 
Print this post

You heathen.  ;)
DOCX is a scrambled and seriously damaged format courtesy of Microsoft. Embrace, Extend, Extinguish!

If anyone has one it will be Geoff, but whether he'll be willing to release it for this purpose I don't know. It is copyright material after all.
Mick

Zilog Inside! nascom.info for Nascom & Gemini
Preliminary MMBasic docs & my PCB designs
 
twofingers

Guru

Joined: 02/06/2014
Location: Germany
Posts: 1576
Posted: 09:48am 07 Dec 2024
Copy link to clipboard 
Print this post

Hi, why not RTF?

Geoff will decide Geoff's matter himself.
Finally, there is the option to export the PDF into an editable format.
Michael
causality ≠ correlation ≠ coincidence
 
Mixtel90

Guru

Joined: 05/10/2019
Location: United Kingdom
Posts: 7871
Posted: 09:58am 07 Dec 2024
Copy link to clipboard 
Print this post

I see Microsoft are removing Wordpad from Windows. It appears that they want to get people off RTF. They'll get my RTF editor (Jarte) out of my cold, dead hands - it's better than Wordpad. :)

Wordpad is clever. It can attempt to open anything - including AutoCAD DWG files. It will show which version of the DWG format the file is in, even though it can't display the drawing. IMHO getting rid of it is a serious mistake.
Mick

Zilog Inside! nascom.info for Nascom & Gemini
Preliminary MMBasic docs & my PCB designs
 
twofingers

Guru

Joined: 02/06/2014
Location: Germany
Posts: 1576
Posted: 10:15am 07 Dec 2024
Copy link to clipboard 
Print this post

  Mixtel90 said  ... They'll get my RTF editor (Jarte) out of my cold, dead hands - it's better than Wordpad. :)...

Interesting, I'll take a look at "Jarte".
causality ≠ correlation ≠ coincidence
 
stef123
Regular Member

Joined: 25/09/2024
Location: United Kingdom
Posts: 89
Posted: 11:24am 07 Dec 2024
Copy link to clipboard 
Print this post

  twofingers said  Hi, why not RTF?

Geoff will decide Geoff's matter himself.
Finally, there is the option to export the PDF into an editable format.
Michael


Yup, already tried this with Calibre, but the outcome is not very usable.

The Key problem is the line (and sometimes the commands which span over two pages) i had mentioned, it sometimes tends to produce garbage.

I am in the process to do it all manually - after some automatic approaches by using self-written programs also failed - not totally, but a lot of work has to be done by hand anyway and thats what i wanted to avoid. As you probably know, LLMs / Vector Databases require a quite clean source to work with.
 
Geoffg

Guru

Joined: 06/06/2011
Location: Australia
Posts: 3285
Posted: 11:52am 07 Dec 2024
Copy link to clipboard 
Print this post

Stef, I'm happy to send to you the new manual's source (ie, docx) when it is released.
Send me an email (projects@geoffg.net) with your address.

Geoff
Geoff Graham - http://geoffg.net
 
Print this page


To reply to this topic, you need to log in.

The Back Shed's forum code is written, and hosted, in Australia.
© JAQ Software 2025