PaddleOCR with preprocessing, scispaCy NER, figure/table detection, citation extraction, and chunked Markdown output with frontmatter. Includes watch mode and notebook reprocessing.
4 lines
98 B
Python
4 lines
98 B
Python
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent.parent / "src")) |