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 d1c9afdfdf polishing the code and docs 5 dagen geleden
..
AGENTS.md initial release with base split functionality 1 week geleden
AI_RULES.md refactored code 1 week geleden
ARCHITECTURE.md renamed cli to image_split 6 dagen geleden
CODE_STYLE.md polishing the code and docs 5 dagen geleden
DEVELOPMENT.md refactored code 1 week geleden
IMAGE_PROCESSING.md refactored code 1 week geleden
README.md initial release with base split functionality 1 week geleden
REQUIREMENTS.md initial release with base split functionality 1 week geleden
SOLID_AUDIT.md polishing the code and docs 5 dagen geleden
TASKS.md initial release with base split functionality 1 week geleden
VLM_OFFLOAD.md polishing the code and docs 5 dagen geleden

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