scan, split, OCR, prepare for LLM

文件历史

Evgeniy Ierusalimov 57152efb4b updated discovered self skills		3 天前
..
AGENTS.md	initial release with base split functionality	1周前
AI_RULES.md	refactored code	1周前
ARCHITECTURE.md	renamed inage_split to image_prepare, fixed some code and parameters	5 天前
CODE_STYLE.md	polishing the code and docs	5 天前
DEVELOPMENT.md	refactored code	1周前
IMAGE_PROCESSING.md	refactored code	1周前
README.md	initial release with base split functionality	1周前
REQUIREMENTS.md	initial release with base split functionality	1周前
SKILLS.md	updated discovered self skills	3 天前
SOLID_AUDIT.md	polishing the code and docs	5 天前
TASKS.md	initial release with base split functionality	1周前
VLM_OFFLOAD.md	polishing the code and docs	5 天前

Offline Document Pipeline

Назначение проекта

Преобразование больших технических документов, полученных после печати и сканирования, в структурированный HTML без использования облачных сервисов.

Поддерживается полностью offline работа.

Pipeline

JPEG/TIFF/PDF

↓

Split pages

↓

Deskew

↓

Crop

↓

PaddleOCR

↓

HTML

Вне scope проекта