Does it support extracting structured information from the results recognized by OCR
Open
- Dominant language
- Python
- Stars
- 38.6k
- Forks
- 2.7k
- Avg merge
- 3d 15h
- Merged PRs (30d)
- 3
Description
Suppose I now use a certain OCR model to extract MarkDown files from product information PDFS or some contract form-based PDFS. Can langextract reasonably parse structured information from md files? If possible, I think this will be a really great project
Contributor guide
Assessment
This issue has not been assessed yet.