ei
/
scan4llm
보기 1
좋아요 0
포크 0
코드 이슈 0 풀 리퀘스트 0 릴리즈 0 위키 Activity
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.
11 커밋
1 브렌치
트리: b5e5b7f394
브랜치 태그
${ item.name }
Create branch ${ searchTerm }
from 'b5e5b7f394'
${ noResults }
scan4llm/.ai
Evgeniy Ierusalimov d1c9afdfdf polishing the code and docs 5 일 전
..
AGENTS.md initial release with base split functionality 1 주 전
AI_RULES.md refactored code 1 주 전
ARCHITECTURE.md renamed cli to image_split 6 일 전
CODE_STYLE.md polishing the code and docs 5 일 전
DEVELOPMENT.md refactored code 1 주 전
IMAGE_PROCESSING.md refactored code 1 주 전
README.md initial release with base split functionality 1 주 전
REQUIREMENTS.md initial release with base split functionality 1 주 전
SOLID_AUDIT.md polishing the code and docs 5 일 전
TASKS.md initial release with base split functionality 1 주 전
VLM_OFFLOAD.md polishing the code and docs 5 일 전

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