this post was submitted on 22 Oct 2023
1 points (100.0% liked)

Emacs

311 readers
1 users here now

A community for the timeless and infinitely powerful editor. Want to see what Emacs is capable of?!

Get Emacs

Rules

  1. Posts should be emacs related
  2. Be kind please
  3. Yes, we already know: Google results for "emacs" and "vi" link to each other. We good.

Emacs Resources

Emacs Tutorials

Useful Emacs configuration files and distributions

Quick pain-saver tip

founded 1 year ago
MODERATORS
rglullis@communick.news
raphael@communick.news
1
GPT4All mode in Emacs (alien.top)
submitted 1 year ago by publicvoit@alien.top to c/emacs@communick.news
11 comments fedilink hide all child comments
 

Hi,

I was using my search engine to look for available Emacs integrations for the open (and local) https://gpt4all.io/ when I realized that I could not find a single one.

Is there somebody who's using GPT4All with Emacs already and did not publish his/her integration?

you are viewing a single comment's thread
view the rest of the comments
[–] karthink@alien.top 1 points 1 year ago (1 children)

I can add this to gptel quite easily, but I can't find the instructions on how to use it. Does it use a local http server? Where can I find these details?

[–] publicvoit@alien.top 1 points 1 year ago (1 children)

Hi,

I personally would not have expected that the desktop app doesn't have to run in background anyway. ;-)

Any "gtp4all.el"-like mode would help me in writing my queries in Emacs as well as receiving its output directly into Emacs (babel/org-mode preferred, I suppose). Currently, I do a lot of copy&paste for that purpose.

[–] karthink@alien.top 1 points 1 year ago (2 children)

In that case you can use it right now with gptel, which supports an Org interface for chat.

Enable the server mode in the desktop app, and in Emacs, run

(setq-default gptel-model "gpt4all-j-v1.3-groovy"
              gptel-host "http://localhost:4891/v1"
              gptel-api-key "--")

Then you can spawn a dedicated chat buffer with M-x gptel or chat from any buffer by selecting a region of text and running M-x gptel-send.

[–] publicvoit@alien.top 1 points 1 year ago (2 children)

Great news - will try in the next days. Thank you.

[–] karthink@alien.top 1 points 1 year ago (1 children)

In the meantime I added explicit support for GPT4All, the above instructions may be incorrect by the time you get to it. The Readme should have updated instructions (if it mentions support for local LLMs at all).

[–] LionyxML@alien.top 1 points 1 year ago

3 days painfully waiting :)

[–] nickanderson5308@alien.top 1 points 1 year ago

I have played with this a bit in the last few days.

It's nice and minimal, but I am hitting some issues with not enough memory. It seems gptel wants to load whatever model is specified, but I don't have enough memory to run the model GPT4All desktop loads by default plus what gptel wants to load.

[–] ahyatt@alien.top 1 points 1 year ago

It isn't actually the same, though - they don't support streaming. How are you getting around this?