[Bug]: Error 109 was reported after uploading pdf file

[zscxc]

Is there an existing issue for the same bug?

• [x] I have checked the existing issues.

RAGFlow workspace code commit ID

v0.17.0

RAGFlow image version

v0.17.0

Other environment information

On Ali Cloud's gpu server

Actual behavior

After configuring the knowledge base and the large model, I set up an assistant for testing. When I uploaded pdf, I reported an error, but I did not report an error when uploading excel, but also did not parse the content

Expected behavior

Steps to reproduce

After configuring the knowledge base and the large model, I set up an assistant for testing. When I uploaded pdf, I reported an error, but I did not report an error when uploading excel, but also did not parse the content

Additional information

[KevinHuSh]

My suggestion is that start RAGFlow without GPU configuration and deploy an embedding inference server on GPUs via Ollama/Xinference e.g.. And start multiple task executors via python rag/svr/task_executor.py 1,2,3,4....