search

mattvr / ShellGPT

Upgrade your terminal with GPT-4. Ask questions, automate commands, pipe I/O, etc. Made with Deno.
MIT License
232 stars 11 forks source link

Add local model #11

Closed kirkog86 closed 8 months ago

kirkog86 commented 1 year ago

Please add an option to API into local OpenAI compatible API server (llama.cpp.python[server] for example)

mattvr commented 8 months ago

@kirkog86 does being able to change the API URL resolve this?

I just added in 0.3.6 support for the environment variable OPENAI_CHAT_URL.

I'm assuming you could target http://localhost:[your-llama-port] to use it with local models.