✨ AI Summarizer — Smart Text Summaries in Seconds

AI Summarizer is a powerful, multi-format summarization platform that intelligently condenses content across text, documents, images, and structured files like CSV/XLSX. Whether you're a student, researcher, analyst, writer, or business professional, this tool instantly extracts the most meaningful information from any file — all with a clean, simple, and highly interactive interface.

Built with modern web technologies and advanced AI models, AI Summarizer transforms long, messy, or complex inputs into clear summaries you can understand in seconds.

---

🚀 Features

🔍 Instant AI Summaries

• Get perfect summaries within seconds for any file type.

📚 OCR Support for Images

• Automatically extracts text from screenshots and photos.

🗂️ Multi-format Support

• Summarize PDF, CSV, XLSX, or plain text files.

🧠 Currently Supports

• Gemini AI model.

🌐 REST API Ready

• Easy backend integration for other tools.

---

🌐 Tech Stack

• 🎨 Frontend: React, Tailwind CSS
• 🛠️ Backend: Python, Flask
• Others: dotenv for environment variables

---

📁 Project Structure

AI-Summarizer/
│── backend/
│   ├── app.py
│   ├── requirements.txt
│   ├── .env
│
│── frontend/
│   ├── src/
│   ├── package.json
│   ├── vite.config.js
│
└── README.md

---

🔮 Setup Locally

Prerequisites

• Node.js (v18+ recommended)
• python 3.13

📦 Installation

This guide walks step-by-step through the setup.

📌 1. Clone the Repository

git clone https://github.com/your-username/AI-Summarizer.git

cd AI-Summarizer

---

🧠 2. Backend Setup (Flask + Gemini + OCR)

cd backend

📌 Create Virtual Environment

python -m venv venv

Activate:

Windows

venv\Scripts\activate

Mac/Linux

source venv/bin/activate

📌 Install Dependencies

pip install -r requirements.txt

---

📌 3. Install Tesseract OCR (Required for Image Text Extraction) Without Tesseract, images cannot be summarized.

🔹 Windows (EXE Installer)

Download from: https://github.com/UB-Mannheim/tesseract/wiki

Install, then add this to PATH manually:

C:\Program Files\Tesseract-OCR

Verify:

tesseract --version

---

🔹 Mac (Homebrew)

brew install tesseract

---

🔹 Linux

sudo apt update
sudo apt install tesseract-ocr

---

🔑 4. Add Gemini API Key Create .env inside backend folder:

GEMINI_API_KEY=your_gemini_api_key_here

Get your Gemini API key from: https://aistudio.google.com/app/apikey

---

▶️ 5. Start Backend

cd backend
python app.py

The backend will be available at http://127.0.0.1:5000

---

⚛️ Frontend Setup (React + Vite)

cd frontend
npm install
npm run dev

The frontend will be available at http://localhost:5173/

🤝 Want to Contribute?

• Fork repository
• Create new branch
• Make changes
• Open a Pull Request

Follow:

• PEP8 for Python
• React best practices
• Clear commit messages