eliranwong / letmedoit

An advanced AI assistant that leverages the capabilities of ChatGPT API, Gemini Pro, AutoGen, and open-source LLMs, enabling it both to engage in conversations and to execute computing tasks on local devices.
https://letmedoit.ai
GNU General Public License v3.0
121 stars 26 forks source link

Changing base url #54

Closed thelege2nd closed 7 months ago

thelege2nd commented 9 months ago

I have not installed it yet, but I didn't see any documentation on how to change the API base URL?

I want to send the requests to my localhost:PORT as that's where I am running a self hosted API for GPT 4.

eliranwong commented 9 months ago

At the moment, this option is not supported.

thelege2nd commented 9 months ago

but since letmedoit can be used with local models, then it should be able easy to change the API endpoint for openai too.

eliranwong commented 9 months ago

It makes sense, I will implement it in https://github.com/eliranwong/freegenius

Alternately, welcome a pull request to letmedoit

eliranwong commented 8 months ago

You can use gemini and ollama for chat features without openai in LetMeDoIt AI.

To fully support Gemini and Ollama, and Llama.cpp, i. E. for both chat and task execution, use sibling project https://github.com/eliranwong/freegenius instead.

eliranwong commented 7 months ago

For using with open-source LLMs, please check: https://github.com/eliranwong/freegenius