search

onuratakan / gpt-computer-assistant

gpt-4o for windows, macos and linux
MIT License
4.74k stars 441 forks source link

Adding custom llm generation ability #24

Open comeback01 opened 3 weeks ago

comeback01 commented 3 weeks ago

I wanted to suggest you the possibility to customize the endpoint.

This allows the use of services compatible with OpenAI such as:

https://openrouter.ai https://fireworks.ai https://www.together.ai

The advantage of OpenRouter is that they also offer free endpoints.

Thank you for the help.

Zhwt commented 3 weeks ago

If base url is configurable, I think local LLMs(Ollama, etc...) will be supported automatically through BerriAI/litellm proxy.

onuratakan commented 3 weeks ago

Oh yeah, we can but what about vision capabilities, the services that you suggested have vision mode. Should we separate the vision mechanism.

onuratakan commented 3 weeks ago

I will add a support to set custom langchain llm class. With this we can be integrated many models above langchain.