Debug Doctor

> Looks generally good. However deepdoc OCR is not an obvious bottleneck. If it is, I would prefer running them with `trio` threadpool. Refactoring `chunk` (rag/app/naive.py) function to async is...

@yuzhichang I've already switched the threadpool to Trio's. Please review it again. (The screenshot shows testing with non-continuous GPU settings.)  

> @debugdoctor Great job! The only issue is CI failure. Could you fix it? Thanks, let me fix it.^_^

@yuzhichang Checks passed, plz review it again.

> @debugdoctor This PR passed CI and was merged. But I found PDF parsing is broken due to this PR. So I have reverted the merging. Please resolve my new...

> [FYI](https://stackoverflow.com/questions/74003230/runtimeerror-nccl-error-2-unhandled-system-error). It seems like this isn't working on our machine. Maybe it's because the gpus are outdated? I'm not sure.

> What type of GPU are you using. Nvidia Tesla M40 24GB * 8

> > ### Self Checks > > > > > > * [x] I have searched for existing issues [search for existing issues](https://github.com/infiniflow/ragflow/issues), including closed ones.[x] I confirm that I...

> > > > ### Self Checks > > > > > > > > > > > > * [x] I have searched for existing issues [search for existing...

> [https://github.com/infiniflow/ragflow/issues/5954#issuecomment-2719700414](url) I encountered this problem and solved it. I think OCR can run on both CPU and GPU. Is there any way? I run OOM on GPU No idea...