Skip to content

Ashutosh10192/MindVault

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 MindVault

An AI-powered Intelligent Learning & IQ Assessment System
Built with ❤️ using FastAPI & React.js


📘 Overview

MindVault is an AI-driven education platform designed to test and enhance human memorization and intelligence through Generative AI.
Users can upload PDFs or images, and the system will:

  • Extract text via OCR (Tesseract)
  • Generate smart, contextual questions using Transformer models (T5, Sentence-BERT)
  • Evaluate answers to estimate IQ level and memory retention power

🧩 In short — MindVault helps you read, recall, and reason — like training your mind with AI.


✨ Features

🧠 Feature 💡 Description
📄 Smart File Uploads Upload PDFs or images — MindVault automatically extracts text content.
🧩 AI Question Generation Uses transformer models to generate meaningful questions from content.
⚙️ FastAPI Backend Handles OCR, AI inference, and scoring logic securely and efficiently.
💻 React Frontend Clean, responsive dashboard for uploads, answers, and analytics.
🔍 IQ & Memory Analysis Predicts your intelligence and recall performance dynamically.
🔄 Adaptive Learning Adjusts question difficulty based on user performance.
☁️ Cloud Ready Scalable deployment on AWS / GCP / Azure with GPU acceleration.

🧰 Tech Stack

Layer Technology
Frontend React.js, Tailwind CSS
Backend FastAPI, PyTorch, Transformers, PyMuPDF (fitz), pytesseract
AI Models T5-base, Sentence-BERT
Database PostgreSQL / Firebase
Cloud & Tools AWS S3, Docker, Git, VS Code

⚙️ Installation & Setup

Follow these simple steps to run MindVault locally 👇

🔹 1. Clone the repository

git clone https://github.com/<your-username>/MindVault.git
cd "MindVault Project App"

🔹 2. Setup the Backend

cd backend
python -m venv venv
venv\Scripts\activate       # On Windows
pip install -r requirements.txt
python main.py

👉 Access API Docs: http://127.0.0.1:8000/docs

🔹 3. Setup the Frontend

cd frontend
npm install
npm start

👉 Frontend runs at: http://localhost:3000


🧩 How It Works

  1. 📤 Upload a PDF/Image
  2. 🔍 OCR Engine extracts text
  3. 🤖 Transformer model (T5) generates smart questions
  4. 🧮 User answers → AI predicts IQ & memory score
  5. 📊 Results displayed on dashboard with improvement insights

📊 API Overview

Method Endpoint Description
POST /upload/ Upload a PDF or image and generate questions.
GET /health Check server health status.

📘 Swagger Docs: http://127.0.0.1:8000/docs


🗂 Folder Structure

MindVault Project App/
│
├── backend/
│   ├── main.py
│   ├── model/
│   │   ├── config.json
│   │   ├── tokenizer_config.json
│   │   ├── model.safetensors
│   └── ...
│
├── frontend/
│   ├── src/
│   ├── package.json
│   └── ...
│
├── .gitignore
├── README.md
└── requirements.txt

🧱 Project Architecture

[User Uploads File] → [FastAPI Backend]
        ↓
   OCR (Tesseract)
        ↓
 Transformer Model (T5)
        ↓
 Generate Questions + Evaluate Answers
        ↓
     Return IQ & Memory Score
        ↓
   [React Frontend Dashboard]

🧩 Development Roadmap

Phase Goal Status
Phase 1 Research & Planning ✅ Completed
Phase 2 Model Integration ✅ Done
Phase 3 Prototype Build ✅ Tested
Phase 4 Optimization & Testing ⚙️ In progress
Phase 5 Deployment 🚀 Coming Soon
Phase 6 Scaling & Gamification 🔜 Planned

🧾 License

This project is licensed under the MIT License.


👨‍💻 Author

Kushagra Chandel 💼 AI Engineer 📧 Email 🌐 GitHub | LinkedIn


“Read • Think • Answer • Evolve – MindVault helps you unlock the power of your mind.”

⭐ Don’t forget to star the repo if you found it useful!

```

🪄 What makes it “interactive” like your reference:

  • Center-aligned header & badges
  • Emoji-based sections
  • Markdown tables for clarity
  • Syntax-highlighted commands
  • Screenshot placeholders
  • Collapsible feel with clean visual hierarchy
  • Perfect for GitHub dark mode

About

Full-stack AI-powered wellness assistant offering NLP journaling, emotional check-ins & personalized recommendation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • JavaScript 47.1%
  • Python 32.3%
  • HTML 13.4%
  • CSS 7.2%