Skip to content

Ryexocious/Project-FileCfy.ai-Team-Explorer-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 

Repository files navigation

Project-FileCfy.ai-Team-Explorer-

An AI-powered desktop application that organizes user-uploaded educational files (PDF, DOCX, TXT, etc.) into course-specific folders by analyzing their content. The app uses React for the frontend and Python (FastAPI + NLP) for the backend.

Description

Users input their course names, and the app scans their device for related files, such as PDFs, lecture notes, and assignments, based on naming patterns, file content and file types.

It then creates folders for each course and moves the appropriate files, making it easy for students to keep their study materials clean and organized.

What Makes It Different

Utilizes AI to analyze and comprehend the actual content of documents, rather than relying on filenames, types or metadata.
Sorts files based on semantic similarity to user-defined course names, even if exact terms aren’t mentioned in the file.
Provides a seamless interface for bulk uploading and organizing files.
Designed specifically for academic contexts such as lectures, assignments, and notes.

Estimate Features

  • Upload and organize lecture notes, assignments, slides, etc.
  • Uses AI to detect the course/topic based on file content
  • Automatically creates course-named folders and moves files
  • Remembers user’s past sorting behavior for better accuracy
  • Local-first: no cloud dependency, all processing on your desktop

Tech Stack

Componet Technology
Frontend React, Tailwind CSS
Backend Python (FastAPI)
NLP HuggingFace Transformers / SentenceTransformers
Storage SQLite3 + Local filesystem
File Parsing PyMuPDF, python-docx, textract

How will it Work

User uploads files via the React UI
Backend extracts text from files using libraries like PyMuPDF and python-docx
Text is embedded into vectors using a pretrained SentenceTransformer model (e.g., all-MiniLM-L6-v2)
User-defined courses are also embedded into the same vector space
The closest course (cosine similarity) is picked for each file
Files are moved into respective folders like /files/Data Structures/
Past actions are remembered to improve categorization over time

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors