scan, split, OCR, prepare for LLM
Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.
Evgeniy Ierusalimov 57152efb4b updated discovered self skills 1 mês atrás
..
AGENTS.md initial release with base split functionality 1 mês atrás
AI_RULES.md refactored code 1 mês atrás
ARCHITECTURE.md renamed inage_split to image_prepare, fixed some code and parameters 1 mês atrás
CODE_STYLE.md polishing the code and docs 1 mês atrás
DEVELOPMENT.md refactored code 1 mês atrás
IMAGE_PROCESSING.md refactored code 1 mês atrás
README.md initial release with base split functionality 1 mês atrás
REQUIREMENTS.md initial release with base split functionality 1 mês atrás
SKILLS.md updated discovered self skills 1 mês atrás
SOLID_AUDIT.md polishing the code and docs 1 mês atrás
TASKS.md initial release with base split functionality 1 mês atrás
VLM_OFFLOAD.md polishing the code and docs 1 mês atrás

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