iyaja/llama-fs
Llama Fs
llama-fs es un gestor de directorios y organizador de sistemas de archivos automatizado que utiliza modelos de lenguaje grandes (LLM) para categorizar, renombrar y ordenar archivos en directorios estructurados. Funciona como un pipeline de datos local que analiza el contenido de los archivos para determinar jerarquías de carpetas y patrones de nombres apropiados.
El proyecto enfatiza la privacidad al enrutar el procesamiento de datos a instancias de modelos locales, asegurando que la información sensible de los archivos permanezca en el dispositivo en lugar de enviarse a proveedores en la nube. Utiliza análisis multimodal para procesar imágenes, audio y texto, permitiendo al sistema identificar y clasificar diversos tipos de medios para una organización automática.
El sistema incluye monitoreo del sistema de archivos en tiempo real para detectar cambios en directorios y activar tareas de limpieza automatizadas. Admite procesamiento por lotes para reestructurar árboles de directorios completos en una sola operación y síntesis recursiva de directorios para crear automáticamente jerarquías de carpetas anidadas.
Features
- Automated File Organizers - Ships an automated file organizer that monitors directory changes and replicates organization patterns.
- Privacy-Preserving Pipelines - Provides a privacy-focused workflow routing file analysis to local model instances instead of cloud providers.
- Multimodal Content Classifiers - Processes images and audio through specialized models to identify content for automated sorting.
- Content-Based Organizers - Renames and sorts files into structured folders by analyzing internal text via language models.
- File System Organizers - Uses large language models to analyze file text and determine appropriate folder structures and filenames.
- Private File Managers - Uses local Llama 3 instances to organize sensitive documents without routing data to cloud providers.
- Automated Directory Monitoring - Provides automated directory monitoring to relocate files based on analyzed content and naming patterns.
- Local-First Tool Processing - Utilizes local-first tool processing to route AI requests to local model instances for data privacy.
- Hierarchical Organizers - Analyzes unstructured data to create logical folder hierarchies and move files into appropriate locations.
- Filesystem Change Monitors - Provides real-time filesystem change monitors to trigger automated organization and cleanup workflows.
- Multimodal Analysis Tools - Employs multimodal analysis tools to identify and classify image and audio content for automated sorting.
- Multimodal Classification - Implements multimodal classification to identify the purpose and destination of images and audio files.
- File Renaming and Relocations - Implements file renaming and relocations to move files and automatically create missing directory structures.
- Recursive Directory Managers - Includes recursive directory managers to automatically synthesize nested folder hierarchies based on model suggestions.
- Local Data Processing - Directs data processing to local model instances to ensure sensitive file data remains on the device.
- Batch File Operations - Implements batch file operations to apply structural mapping across entire directory trees in a single pass.
