Files
kg-scr/src/ocr_pipeline/__init__.py
Aman a32b7508c7 OCR-to-RAG pipeline for life science screenshots
PaddleOCR with preprocessing, scispaCy NER, figure/table detection,
citation extraction, and chunked Markdown output with frontmatter.
Includes watch mode and notebook reprocessing.
2026-07-18 19:35:21 +00:00

13 lines
199 B
Python

from __future__ import annotations
__version__ = "0.1.0"
from .cli import main
from .pipeline import OCRPipeline, PipelineResult
__all__ = [
"OCRPipeline",
"PipelineResult",
"main",
]