docling-project / docling-project/docling
DocumentExtractor remote vlm?
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 3d 4h
- Merged PRs (30d)
- 95
Description
### Question
Hello
Is it possible to use remote vlm for DocumentExtractor (https://docling-project.github.io/docling/examples/extraction/) like you can use it for DocumentConverter (https://docling-project.github.io/docling/examples/vlm_pipeline_api_model/)?
As far as I understand it is using numind/NuExtract-2.0-8B model for data extraction?
Contributor guide
Research direction
Compare the DocumentExtractor example at the extraction documentation URL with the DocumentConverter VLM pipeline API model example. First determine how DocumentExtractor selects its extraction model and whether the referenced NuExtract-2.0-8B model is part of that path; done means the documentation or implementation clearly states whether remote VLM use is supported and how.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100