search

adithya-s-k / omniparse

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
https://docs.cognitivelab.in
GNU General Public License v3.0
5.13k stars 430 forks source link

Great project, Separate GUI code from GPU code #8

Open 99bits opened 3 months ago

99bits commented 3 months ago

Thanks for this amazing project.

I have an interesting use case and wondering if it's possible to do.
I would like to run the user facing Gradio app on my local machine and send the AI GPU code to an online GPU machine. This way I can chose any kind of GPU backend depending on the workload.

Cheers

adithya-s-k commented 3 months ago

@99bits I was thinking about implementing this. I am planning to deploy a Huggingface space where you can just input your hosted server URL and use OmniParse through that.

99bits commented 3 months ago

Awesome, adding this feature would make Omniparse super flexible. Also deployment on HF would be great to quickly test the project.