search

keldenl / gpt-llama.cpp

A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.
MIT License
594 stars 67 forks source link

Change listening ip to public ip? #60

Closed Dougie777 closed 1 year ago

Dougie777 commented 1 year ago

I have a scenario where I want to run the API for a client app that runs on another server. Thus I need to run gpt-llama so it runs on the public ip. Is there a way to do this. Or is there a place in the code I can change it?

Thanks, Doug

Dougie777 commented 1 year ago

Never mind it was a dumb question. I had to set the default port at the top of index.js

I had assumed the conflict was the ip but it was that port 443 was already being used by my web server. On linux the spec to set the port on the command line does not work. So i just changed the script built in default.

So it turns out it automatically listens to the public ip address. I just didn't know this while debugging.