Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Enhancement]: IS it possible to use as self hosted #1115

Open
MichaelJmad opened this issue Oct 16, 2024 · 2 comments
Open

[Enhancement]: IS it possible to use as self hosted #1115

MichaelJmad opened this issue Oct 16, 2024 · 2 comments
Labels
enhancement New feature or request

Comments

@MichaelJmad
Copy link

Version

VisualStudio Code extension

Suggestion

I am a hobbyist and was wondering if it would be possible to use this in a self-hosted offline setup.
Or at least substitute the openAI for a self-hosted LLM such as Llama
If this question has been asked before I am terribly sorry as I missed it when I was searching for it

@MichaelJmad MichaelJmad added the enhancement New feature or request label Oct 16, 2024
@isbkch
Copy link

isbkch commented Oct 21, 2024

That would be amazing

I've been testing the V1 early access for an idea I've been toying with in my head. After $50 on Pythagora V1 I pretty much got to where someone quoted me $8.5k so I can't complain about the cost, and I would be happy to contribute to help advance the project, but please allow me to use local models

@james-brown-upfeat
Copy link

Just reading the config file you can set an openai base url, so if you serve your model locally with an openai compatible api you can just set the base url to that model's url and it should work.

I'm just guessing though, not an expert, haven't used gpt-pilot before.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants