docling-project / docling-project/docling
docling is about to generate some kind of embedded form of images and it says that we can use api or vlm based method to get the description of the image
Open
question
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
so what all can we get from vlm or api exactly and also tell me how to do that using code and also give me the links or something for the examples related to it
Contributor guide
Assessment
This issue has not been assessed yet.