Do you need to file a feature request?
Feature Request Description
Provide a lightweight alternative to mineru and docling for lightrag (that can extract images) like PyMuPDF4LLM.
This would enable DeepTutor (and lightrag) to easily run on lower-end devices
Related Module
Knowledge Base Management
Use Case
Hi, I was looking at the options lightrag has, and almost all the options (that can work with pdf documents and extract images), i.e., mineru and docling pull a CUDA dependency. I'm running DeepTutor on a device similar to a Raspberry Pi.
It would be nice, if something lightweight like PyMuPDF4LLM could be used. Link here: https://github.com/pymupdf/pymupdf4llm
To me it seems that this solution is quite efficient, although a bit time taking.
Do tell me if this issue makes more sense to open in the lightrag repo.
Additional Context
No response
Do you need to file a feature request?
Feature Request Description
Provide a lightweight alternative to mineru and docling for lightrag (that can extract images) like PyMuPDF4LLM.
This would enable DeepTutor (and lightrag) to easily run on lower-end devices
Related Module
Knowledge Base Management
Use Case
Hi, I was looking at the options lightrag has, and almost all the options (that can work with pdf documents and extract images), i.e., mineru and docling pull a CUDA dependency. I'm running DeepTutor on a device similar to a Raspberry Pi.
It would be nice, if something lightweight like PyMuPDF4LLM could be used. Link here: https://github.com/pymupdf/pymupdf4llm
To me it seems that this solution is quite efficient, although a bit time taking.
Do tell me if this issue makes more sense to open in the lightrag repo.
Additional Context
No response