Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

I Was Too Lazy to Organize My Files, So I Taught a Sloth (Gemma) to Do It

Описание и применение

Автор создал приложение LazyDesk AI, использующее локальную модель Gemma 3 (1B) для автоматической переименования и сортировки файлов, обнаружения дубликатов и создания ZIP‑архива после ручного утверждения.

Задача

The author’s Downloads folder contained messy filenames and duplicate files, and manual organization was tedious and unlikely to be performed.

Результат

In a test with six messy files, the app detected a duplicate pair, processed all files in 32 seconds, and produced a ZIP containing only approved files in suggested folders. The author estimates saving ~3 minutes for six files, implying significant time savings for larger collections.

Рабочий процесс

  • Upload files to the Streamlit UI
  • Ollama runs local Gemma 3 (1B) to suggest clean names and folders
  • SHA‑256 hashes identify duplicate pairs
  • Duplicate files are flagged and can be removed
  • An editable approval table (pandas st.data_editor) displays suggestions
  • User reviews and edits suggestions
  • Approved files are packaged into a ZIP for download

Доказательства

I built LazyDesk AI 🦥, a file decluttering app where a local open-weight Gemma model reads your messy files and suggests clean names and folders.

Источник

All 6 files processed in 32 seconds

Источник

Duplicate detective (SHA-256) caught the identical pair: duplicate_copy.txt and duplicate_original.txt

Источник

  • Дата записи: 2026-10-26T07:11:13.369Z