📄 Document Summarizer via Google Drive Integration

An AI-powered web application that connects to a Google Drive folder, extracts text from documents, and generates concise summaries using Google Gemini AI.

This project was built as part of a technical assignment for the Sr. Gen AI Developer role and fulfills all specified requirements.

---

🚀 Features

• 🔐 Google OAuth2 authentication
• 📁 Google Drive folder integration
• 📄 Supports PDF, DOCX, and TXT files
• 🧠 AI-powered summarization (4–5 sentences)
• 🌐 Web interface using FastAPI
• 📊 Download summaries as CSV
• 🎯 Summarizes only uploaded documents

---

🧠 Tech Stack

• Backend: FastAPI
• AI Model: Google Gemini (genai SDK)
• Cloud Storage: Google Drive API
• Authentication: OAuth2
• Frontend: HTML, Tailwind CSS, HTMX
• Document Parsing: PyMuPDF, python-docx
• Output Format: CSV

---

📂 Project Structure

document-summarizer-gdrive-ai/ │ ├── app/ │ ├── main.py # FastAPI application │ ├── config.py # API keys & configuration │ ├── services/ │ │ ├── drive_service.py # Google Drive integration │ │ ├── parser_service.py # PDF/DOCX/TXT text extraction │ │ ├── summary_service.py # Gemini AI summarization │ │ └── report_service.py # CSV generation │ ├── templates/ │ │ ├── base.html │ │ └── index.html │ ├── output/ │ └── summaries.csv │ ├── requirements.txt ├── .gitignore └── README.md

---

🔑 Prerequisites

• Python 3.9+
• Google Cloud project with:
  • Google Drive API enabled
  • OAuth2 credentials
• Google Gemini API key

---

⚙️ Setup Instructions

1️⃣ Clone the repository

git clone https://github.com/jaydeb2023/document-summarizer-gdrive-ai.git
cd document-summarizer-gdrive-ai


2️⃣ Create a virtual environment
python -m venv venv
source venv/bin/activate     

3️⃣ Install dependencies
pip install -r requirements.txt


5️⃣ Google Drive OAuth credentials
app/credentials/credentials.json


6️⃣ Run the application
uvicorn app.main:app --reload




| Requirement              | Status |
| ------------------------ | ------ |
| Google Drive OAuth2      | ✅      |
| Folder-based access      | ✅      |
| PDF / DOCX / TXT parsing | ✅      |
| AI summarization         | ✅      |
| Web interface            | ✅      |
| CSV download             | ✅      |



👨‍💻 Author

 Jaydeb Sarader
📧 jaydebsarader@gmail.com

🔗 https://github.com/jaydeb2023


📄 License

This project is provided for technical evaluation purposes only.