scan, split, OCR, prepare for LLM
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Evgeniy Ierusalimov 57152efb4b updated discovered self skills 2 days ago
..
AGENTS.md initial release with base split functionality 1 week ago
AI_RULES.md refactored code 1 week ago
ARCHITECTURE.md renamed inage_split to image_prepare, fixed some code and parameters 4 days ago
CODE_STYLE.md polishing the code and docs 5 days ago
DEVELOPMENT.md refactored code 1 week ago
IMAGE_PROCESSING.md refactored code 1 week ago
README.md initial release with base split functionality 1 week ago
REQUIREMENTS.md initial release with base split functionality 1 week ago
SKILLS.md updated discovered self skills 2 days ago
SOLID_AUDIT.md polishing the code and docs 5 days ago
TASKS.md initial release with base split functionality 1 week ago
VLM_OFFLOAD.md polishing the code and docs 5 days ago

README.md

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

  • LLM
  • RAG
  • поиск
  • анализ документов