🤖 Agentic PDF QnA React SPA

Welcome to the next generation of privacy-first, agentic web applications!
Agentic PDF QnA React SPA lets you chat with your own PDF files using AI/ML—all in your browser, with zero data ever leaving your device.

---

✨ Features

🚀 Agentic AI/ML QnA
Ask questions about your PDF using a real AI agent powered by TensorFlow.js and the @tensorflow-models/qna model. No backend, no cloud, no compromise.

📄 PDF Upload & Extraction
Upload any PDF (up to 4MB), instantly extract its text, and start chatting with the content.

💬 ChatGPT-like UI
Enjoy a beautiful, modern chat interface that feels just like ChatGPT—responsive, intuitive, and mobile-friendly.

🔒 Privacy by Design
All processing happens in your browser. No data collection, no analytics, no cookies, no tracking. Your files and questions never leave your device.

🌍 Serverless & Easy Deployment
Deploy to Vercel, Netlify, GitHub Pages, or any static host. No backend or server setup required.

📱 Mobile Ready
Fully responsive for all device sizes.

---

🖼️ Demo

---

🗂️ Project Structure

AgenticWebImplementation
├── public
│   └── index.html
├── src
│   ├── App.jsx
│   ├── index.jsx
│   ├── customHooks
│   │   ├── pdfToText.js      # PDF text extraction hook
│   │   └── aiLogic.js        # TensorFlow QnA hook
│   ├── pages
│   │   └── Home.jsx          # Main chat UI
│   └── pages
│       └── Home.css          # ChatGPT-like styles
├── package.json
└── README.md

---

🚀 Getting Started

1. Clone the repository:

   git clone <repository-url>
   cd AgenticWebImplementation

2. Install dependencies:

   npm install

3. Run the application locally:

   npm start

   The app will open in your browser at http://localhost:3000.

---

🧠 How It Works

1. Upload a PDF: Click the file input to select a PDF (max 4MB). The file is never uploaded to a server.
2. Text Extraction: The app extracts text from your PDF in the browser using a custom React hook.
3. Ask Questions: Type questions about the PDF content. The TensorFlow QnA model answers your questions, all locally.
4. Privacy: No data is sent to any server. All processing is done in your browser for maximum privacy.

---

☁️ Serverless Deployment

Deploy to any static host (Vercel, Netlify, GitHub Pages, etc.)—no backend needed. All AI/ML runs in the browser.

---

🔐 Privacy & Security

• No Data Collection: Your PDFs and questions never leave your device.
• No Analytics: No tracking, analytics, or cookies.
• Open Source: Review the code to verify privacy claims.

---

🤝 Contributing

Contributions are welcome! Please fork the repository and submit a pull request.

---

📄 License

MIT License