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

Using local api #14

Open
mkayhko opened this issue Mar 7, 2024 · 1 comment
Open

Using local api #14

mkayhko opened this issue Mar 7, 2024 · 1 comment

Comments

@mkayhko
Copy link

mkayhko commented Mar 7, 2024

Hello, I'm trying to use a local OpenAI-compatible API (by oobabooga) at http://localhost:5001/v1/completions and I get no replies from the bot. There's nothing in the log that would help me.

It works if I query it with curl, for example.

@oxagast
Copy link
Owner

oxagast commented Mar 8, 2024

Hi!
Which branch are you using?
I've recently brought the Cohere branch up even with frank_master, so frank_master will not work with OpenAI formed API requests. You'll need to specifify either the Davinci 003 branch, or the GPT 3.5 Turbo Instruct branch (whichever your API you're running fits). There also is no direct option to change the API from the Irssi controls, as it wasn't designed to work like that, you'll need to dig into the src and change the calls manually, there are two, one in callapi() and another in asshat() and replace it with your API location. If you have done all that, make sure there are not any other minor nuiances in the API calls that may need to be modified to fit your local model.

Hope this helps,
oxagast

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

No branches or pull requests

2 participants