Consent Guardian

Consent Guardian is a web application that interprets and translates images of consent forms into simpler, easier to understand language for patients of all ages.

Built with ReactJS, Flask, and Gemini AI

---

Prerequisites

Ensure you have the following installed:

• Node.js (v16+ recommended)
• npm (comes with Node.js)
• Python (3.8+)
• Google Gemini AI API Key (for AI-powered document summarization)
• Tesseract-OCR (for image text extraction)
• poppler-utils (for PDF image conversion)

---

Dependencies

Run

npm install

or otherwise,

npm install react react-dom @types/react @types/react-dom

Install Python dependencies

pip install -r requirements.txt

---

Setup

Clone the repository

gh repo clone julesiet/consent-guardian

Create a virtual environment (recommended)

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

Set up your Gemini AI API key

• Create a .env file in the backend folder
• Add this line inside:

GEMINI_API_KEY=your_api_key_here

Start the flask server in /flask_Backend/services/

python backend_main.py

Navigate to the frontend

cd finally

Start Consent Guardian app

npm run dev

and open the link given.

---

Project Structure

/project-root
│── /frontend          # React app (file upload)
│   ├── src/
│   ├── public/
│   ├── package.json
│   ├── FileUploader.tsx
│── /backend           # Flask backend
│   ├── app.py         # Main Flask server
│   ├── gemini_services.py
│   ├── .env           # API key (not in Git)
│   ├── requirements.txt
│── README.md

---

License

This project is licensed under the MIT License.