Ask about new KDE functionnalities.

[Maître Frédéric CUIF | DESCARTES AVOCATS]

Le vendredi 28 avril 2023, 15:32:20 CEST Nate Graham a écrit :
>On 4/28/23 04:14, Nicolas Lécureuil wrote:
>> Hello,
>> 
>> i don't know if i post on the good ML but i have a friend searching for 
>> developpers to mostly integrate ChatGPT into KDE. He accepts to 
>> contribute financially.
>> 
>> "
>>      I don't know if it's possible, but for example, I would like to 
>> allow the generation and saving of configuration files from the UI.
>>      integrate "a chatGPT" to enable script generation within the 
>> graphical environment and thus execute these scripts: for example, read 
>> the headers of a message and its attachments and suggest saving the 
>> email "in a hard copy" (.eml) to the hard drive with the attachments, 
>> with the help of voice and multiple choice help bubbles.
>
>Not sure now ChatGPT could help with either of these ideas, and it's 
>already possible for someone to develop such features without ChatGPT.
>
>Can you help explain what ChatGPT would be bringing to the table here?
>
>Nate
>

Hello,

I asked Nicolas to help me, but I think I would be better able to detail what I'm looking for.

I've been using KDE in my job (lawyer) for over 15 years and I'm looking for a way to automate tasks in a smart way.

The most explicit example is that of an email. Let me explain.

When I receive an email from a client, it includes headers, body and attachments. I am looking for how to semi-automate the recording of an email in a folder tree in my HDD (.eml).

The "engine" chosen must be able to read a header and the content of an email to suggest where it will be saved (file number, sender's name, references, etc.). It must be able to offer me the possibility, in a GUI, choices to save the email in suggested locations, name it with an explicit file name and extension. Then, he must be able to know in which directory to save the attachments (which are not stored in the same place). For example, an email from a client is saved in a "correspondence" directory, while an email from an opposing lawyer is saved in a "procedure" directory and a judgment as an attachment must be saved in another directory.

The engine must also be able to return to my local KDE environment to search for indexed documents that I have saved, note appointments in Kontact. I thought that an LLM (not necessarily chatGPT4) had a greater ability to run a series of scripts allowing me to perform daunting and repetitive tasks. However, he must know how to do it well.

Is that clearer ?

Many thanks.

---
** Maître Frédéric CUIF | SARL DESCARTES AVOCATS | Société d'avocats d'affaires | **
19 rue Saint-Louis, 3e étage - 86000 Poitiers |
Téléphone : +33 5 49 88 70 61
Site internet : https://descartes-avocats.com
courriel : cabinet at descartes-avocats.com