NVIDIA / NVIDIA/NeMo-Retriever
[DOC]: What happens when extract method is none?
Open
Nobody has claimed this yet.
doc
- Dominant language
- Python
- Stars
- 3k
- Forks
- 349
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
How would you describe the priority of this documentation request
Would be nice
Describe the future/missing documentation
i am trying to use nv-ingest in the rag blueprint and i have come across an issue:
when the extract method is pdfium, there is no problem ingesting pdfs but i can not ingest images
when the extract method is None, i can ingest pdfs and images as well but pdfs which are scanned images fail
so what happens when extract method is None?
Where have you looked?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the linked nv-ingest Python API quick-start section and compare the documented behavior of the pdfium and None extract methods. Done means clearly documenting how extract=None handles PDFs, images, and scanned-image PDFs, including the reported failure case.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100