Study Assistant

A Flask web app that extracts text from uploaded PDF notes and generates an AI-powered summary with key points using the Anthropic API.

Features

• Upload a PDF (lecture notes, textbook excerpts, study materials)
• Extracts text from the PDF automatically
• Sends the content to Claude for summarization
• Returns a concise summary and a list of key points
• Clean, responsive UI with side-by-side layout on desktop

Tech Stack

• Backend: Python, Flask
• PDF Extraction: PyMuPDF (fitz)
• AI Summarization: Anthropic API (Claude)
• Frontend: HTML, CSS, Bootstrap, Jinja2
• Environment Management: python-dotenv

Project Structure

study-assistant/
├── app.py               # Flask app, routes, and helper functions
├── templates/
│   └── index.html       # Main UI template
├── static/
│   └── style.css        # Custom styles
├── uploads/             # Temporary PDF storage
├── .env                 # API key (not committed)
├── .gitignore
└── requirements.txt

Getting Started

Prerequisites

• Python 3.x
• An Anthropic API key

Installation

1. Clone the repository

git clone https://github.com/yourusername/study-assistant.git
cd study-assistant

2. Create and activate a virtual environment

python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

4. Create a .env file in the project root and add your API key

ANTHROPIC_API_KEY=your_api_key_here

5. Run the app

flask run

6. Open your browser and go to http://127.0.0.1:5000

Usage

1. Click the upload area or browse to select a PDF file
2. Click Upload & Summarize
3. The app extracts the text, sends it to Claude, and displays a summary with key points

Security Notes

• File uploads are validated for .pdf extension only
• Filenames are sanitized using werkzeug.utils.secure_filename
• API keys are stored in .env and never committed to version control

Future Improvements

• Quiz and flashcard generation from uploaded notes
• Support for saving and revisiting past summaries
• Token limit handling for very large PDFs
• Deployment to a live URL