[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72325":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":32,"readmeContent":33,"aiSummary":34,"trendingCount":16,"starSnapshotCount":16,"syncStatus":35,"lastSyncTime":36,"discoverSource":37},72325,"Local-File-Organizer","QiuYannnn\u002FLocal-File-Organizer","QiuYannnn","An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.","",null,"Python",3243,320,47,26,0,7,8,39,21,81.42,"MIT License",false,"main",true,[27,28,29,30,31],"file-organizer","llama3","llm","on-device-ai","vlm","2026-06-12 04:01:04","# Local File Organizer: AI File Management Run Entirely on Your Device, Privacy Assured\n\nTired of digital clutter? Overwhelmed by disorganized files scattered across your computer? Let AI do the heavy lifting! The Local File Organizer is your personal organizing assistant, using cutting-edge AI to bring order to your file chaos - all while respecting your privacy.\n\n## How It Works 💡\n\nBefore:\n\n```\n\u002Fhome\u002Fuser\u002Fmessy_documents\u002F\n├── IMG_20230515_140322.jpg\n├── IMG_20230516_083045.jpg\n├── IMG_20230517_192130.jpg\n├── budget_2023.xlsx\n├── meeting_notes_05152023.txt\n├── project_proposal_draft.docx\n├── random_thoughts.txt\n├── recipe_chocolate_cake.pdf\n├── scan0001.pdf\n├── vacation_itinerary.docx\n└── work_presentation.pptx\n\n0 directories, 11 files\n```\n\nAfter:\n\n```\n\u002Fhome\u002Fuser\u002Forganized_documents\u002F\n├── Financial\n│   └── 2023_Budget_Spreadsheet.xlsx\n├── Food_and_Recipes\n│   └── Chocolate_Cake_Recipe.pdf\n├── Meetings_and_Notes\n│   └── Team_Meeting_Notes_May_15_2023.txt\n├── Personal\n│   └── Random_Thoughts_and_Ideas.txt\n├── Photos\n│   ├── Cityscape_Sunset_May_17_2023.jpg\n│   ├── Morning_Coffee_Shop_May_16_2023.jpg\n│   └── Office_Team_Lunch_May_15_2023.jpg\n├── Travel\n│   └── Summer_Vacation_Itinerary_2023.docx\n└── Work\n    ├── Project_X_Proposal_Draft.docx\n    ├── Quarterly_Sales_Report.pdf\n    └── Marketing_Strategy_Presentation.pptx\n\n7 directories, 11 files\n```\n\n## Updates 🚀\n\n**[2024\u002F09] v0.0.2**:\n* Featured by [Nexa Gallery](https:\u002F\u002Fnexaai.com\u002Fgallery) and [Nexa SDK Cookbook](https:\u002F\u002Fgithub.com\u002FNexaAI\u002Fnexa-sdk\u002Ftree\u002Fmain\u002Fexamples)!\n* Dry Run Mode: check sorting results before committing changes\n* Silent Mode: save all logs to a txt file for quieter operation\n* Added file support:  `.md`, .`excel`, `.ppt`, and `.csv` \n* Three sorting options: by content, by date, and by type\n* The default text model is now [Llama3.2 3B](https:\u002F\u002Fnexaai.com\u002Fmeta\u002FLlama3.2-3B-Instruct\u002Fgguf-q3_K_M\u002Ffile)\n* Improved CLI interaction experience\n* Added real-time progress bar for file analysis\n\nPlease update the project by deleting the original project folder and reinstalling the requirements. Refer to the installation guide from Step 4.\n\n\n## Roadmap 📅\n\n- [ ] Copilot Mode: chat with AI to tell AI how you want to sort the file (ie. read and rename all the PDFs)\n- [ ] Change models with CLI \n- [ ] ebook format support\n- [ ] audio file support\n- [ ] video file support\n- [ ] Implement best practices like Johnny Decimal\n- [ ] Check file duplication\n- [ ] Dockerfile for easier installation\n- [ ] People from [Nexa](https:\u002F\u002Fgithub.com\u002FNexaAI\u002Fnexa-sdk) is helping me to make executables for macOS, Linux and Windows\n\n## What It Does 🔍\n\nThis intelligent file organizer harnesses the power of advanced AI models, including language models (LMs) and vision-language models (VLMs), to automate the process of organizing files by:\n\n\n* Scanning a specified input directory for files.\n* Content Understanding: \n  - **Textual Analysis**: Uses the [Llama3.2 3B](https:\u002F\u002Fnexaai.com\u002Fmeta\u002FLlama3.2-3B-Instruct\u002Fgguf-q3_K_M\u002Ffile) to analyze and summarize text-based content, generating relevant descriptions and filenames.\n  - **Visual Content Analysis**: Uses the [LLaVA-v1.6](https:\u002F\u002Fnexaai.com\u002Fliuhaotian\u002Fllava-v1.6-vicuna-7b\u002Fgguf-q4_0\u002Ffile) , based on Vicuna-7B, to interpret visual files such as images, providing context-aware categorization and descriptions.\n\n* Understanding the content of your files (text, images, and more) to generate relevant descriptions, folder names, and filenames.\n* Organizing the files into a new directory structure based on the generated metadata.\n\nThe best part? All AI processing happens 100% on your local device using the [Nexa SDK](https:\u002F\u002Fgithub.com\u002FNexaAI\u002Fnexa-sdk). No internet connection required, no data leaves your computer, and no AI API is needed - keeping your files completely private and secure.\n\n\n## Supported File Types 📁\n\n- **Images:** `.png`, `.jpg`, `.jpeg`, `.gif`, `.bmp`\n- **Text Files:** `.txt`, `.docx`, `.md`\n- **Spreadsheets:** `.xlsx`, `.csv`\n- **Presentations:** `.ppt`, `.pptx`\n- **PDFs:** `.pdf`\n\n## Prerequisites 💻\n\n- **Operating System:** Compatible with Windows, macOS, and Linux.\n- **Python Version:** Python 3.12\n- **Conda:** Anaconda or Miniconda installed.\n- **Git:** For cloning the repository (or you can download the code as a ZIP file).\n\n## Installation 🛠\n\n> For SDK installation and model-related issues, please post on [here](https:\u002F\u002Fgithub.com\u002FNexaAI\u002Fnexa-sdk\u002Fissues).\n\n### 1. Install Python\n\nBefore installing the Local File Organizer, make sure you have Python installed on your system. We recommend using Python 3.12 or later.\n\nYou can download Python from [the official website]((https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)).\n\nFollow the installation instructions for your operating system.\n\n### 2. Clone the Repository\n\nClone this repository to your local machine using Git:\n\n```zsh\ngit clone https:\u002F\u002Fgithub.com\u002FQiuYannnn\u002FLocal-File-Organizer.git\n```\n\nOr download the repository as a ZIP file and extract it to your desired location.\n\n### 3. Set Up the Python Environment\n\nCreate a new Conda environment named `local_file_organizer` with Python 3.12:\n\n```zsh\nconda create --name local_file_organizer python=3.12\n```\n\nActivate the environment:\n\n```zsh\nconda activate local_file_organizer\n```\n\n### 4. Install Nexa SDK ️\n\n#### CPU Installation\nTo install the CPU version of Nexa SDK, run:\n```bash\npip install nexaai --prefer-binary --index-url https:\u002F\u002Fnexaai.github.io\u002Fnexa-sdk\u002Fwhl\u002Fcpu --extra-index-url https:\u002F\u002Fpypi.org\u002Fsimple --no-cache-dir\n```\n\n#### GPU Installation (Metal - macOS)\nFor the GPU version supporting Metal (macOS), run:\n```bash\nCMAKE_ARGS=\"-DGGML_METAL=ON -DSD_METAL=ON\" pip install nexaai --prefer-binary --index-url https:\u002F\u002Fnexaai.github.io\u002Fnexa-sdk\u002Fwhl\u002Fmetal --extra-index-url https:\u002F\u002Fpypi.org\u002Fsimple --no-cache-dir\n```\nFor detailed installation instructions of Nexa SDK for **CUDA** and **AMD GPU** support, please refer to the [Installation section](https:\u002F\u002Fgithub.com\u002FNexaAI\u002Fnexa-sdk?tab=readme-ov-file#installation) in the main README.\n\n\n### 5. Install Dependencies \n\n1. Ensure you are in the project directory:\n   ```zsh\n   cd path\u002Fto\u002FLocal-File-Organizer\n   ```\n   Replace `path\u002Fto\u002FLocal-File-Organizer` with the actual path where you cloned or extracted the project.\n\n2. Install the required dependencies:\n   ```zsh\n   pip install -r requirements.txt\n   ```\n\n**Note:** If you encounter issues with any packages, install them individually:\n\n```zsh\npip install nexa Pillow pytesseract PyMuPDF python-docx\n```\n\nWith the environment activated and dependencies installed, run the script using:\n\n### 6. Running the Script🎉\n```zsh\npython main.py\n```\n\n## Notes\n\n- **SDK Models:**\n  - The script uses `NexaVLMInference` and `NexaTextInference` models [usage](https:\u002F\u002Fdocs.nexaai.com\u002Fsdk\u002Fpython-interface\u002Fgguf).\n  - Ensure you have access to these models and they are correctly set up.\n  - You may need to download model files or configure paths.\n\n\n- **Dependencies:**\n  - **pytesseract:** Requires Tesseract OCR installed on your system.\n    - **macOS:** `brew install tesseract`\n    - **Ubuntu\u002FLinux:** `sudo apt-get install tesseract-ocr`\n    - **Windows:** Download from [Tesseract OCR Windows Installer](https:\u002F\u002Fgithub.com\u002FUB-Mannheim\u002Ftesseract\u002Fwiki)\n  - **PyMuPDF (fitz):** Used for reading PDFs.\n\n- **Processing Time:**\n  - Processing may take time depending on the number and size of files.\n  - The script uses multiprocessing to improve performance.\n\n- **Customizing Prompts:**\n  - You can adjust prompts in `data_processing.py` to change how metadata is generated.\n\n## License\n\nThis project is dual-licensed under the MIT License and Apache 2.0 License. You may choose which license you prefer to use for this project.\n\n- See the [MIT License](LICENSE-MIT) for more details.","Local File Organizer 是一款基于AI的文件管理工具，能够通过智能扫描、重组和组织本地文本和图片文件来确保隐私并提供快速无缝访问。该项目利用了Llama3.2 3B和Llava v1.6模型以及Nexa SDK，支持多种文件格式，并提供了三种排序选项：按内容、日期和类型。它特别适合那些需要高效整理大量混乱文件的个人或小型团队使用，能够在不牺牲用户隐私的前提下显著提高文件管理和检索效率。此外，项目还计划增加更多功能如Copilot模式、模型切换等，以进一步增强用户体验。",2,"2026-06-11 03:41:22","high_star"]