OCR-to-RAG pipeline for life science screenshots

Browse Source

PaddleOCR with preprocessing, scispaCy NER, figure/table detection,
citation extraction, and chunked Markdown output with frontmatter.
Includes watch mode and notebook reprocessing.

...

This commit is contained in:

Aman

2026-07-18 19:34:22 +00:00

parent 012549b4bc

commit a32b7508c7

68 changed files with 8708 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

src/ocr_pipeline/detectors/__pycache__/figures.cpython-313.pyc Normal file

Binary file not shown.