📝 SmartNotes

"I hate doing repetitive document summarization... so I automated it!"

AI-powered document summarization and quiz generation application. Upload PDFs or text documents to get instant summaries, keyword extraction, and automatically generated comprehension quizzes.

NEW: AutoNotes batch processor - process entire folders of documents in one command!

Features

SmartNotes (Single Document)

• 📄 PDF & Text Support: Upload PDF files or paste text directly
• 🤖 AI-Powered Analysis: Automatic summarization using LLM
• 🔑 Keyword Extraction: Identifies key concepts and terms
• ❓ Quiz Generation: Creates 5 multiple-choice questions
• 💾 Persistent Storage: SQLite database for note history
• 🎨 Modern UI: Clean, responsive interface

AutoNotes (Batch Processing) 🚀

• 📁 Batch Processing: Process entire folders of documents
• ⚡ One Command: Analyze dozens of files automatically
• 📊 HTML Index: Beautiful overview of all results
• 🗂️ Organized Output: Each document in its own folder with metadata
• 🔄 Cross-Platform: Works on Windows, Mac, and Linux

Quick Start

Prerequisites

• Python 3.11 or higher
• pip package manager

Installation

1. Clone the repository:

git clone https://github.com/yourusername/smartnotes.git
cd smartnotes

2. Install dependencies:

pip install -r requirements.txt

3. Set up environment variables:

cp .env.example .env
# Edit .env and add your LLM API key

4. Run the application:

python app/main.py

5. Run the application:

python run.py

6. Open your browser to http://localhost:5000

AutoNotes - Batch Processing

Process entire folders of documents automatically:

# Process a folder of documents
python scripts/auto_notes.py /path/to/documents

# Specify output location
python scripts/auto_notes.py /path/to/documents -o my_output

# Run the demo
bash scripts/run_demo.sh

What you get:

• Organized folder structure (one folder per document)
• metadata.json with full analysis for each document
• summary.txt for quick reference
• Beautiful HTML index showing all results
• Original files preserved

Example:

# Process test fixtures
python scripts/auto_notes.py tests/fixtures -o auto_notes_output

# Open the index
open auto_notes_output/index.html  # Mac
start auto_notes_output/index.html  # Windows
xdg-open auto_notes_output/index.html  # Linux

Running Tests

Run the complete test suite:

pytest tests/ -v

Run with coverage report:

pytest tests/ -v --cov=app --cov-report=html

API Documentation

POST /api/upload

Upload a document for analysis.

Request:

• Method: POST
• Content-Type: multipart/form-data or application/x-www-form-urlencoded

Parameters:

• file: PDF or text file (multipart/form-data)
• text: Raw text content (form data or JSON)

Response:

{
  "id": 1,
  "summary": "Document summary...",
  "keywords": ["keyword1", "keyword2", "keyword3"],
  "quiz": [
    {
      "q": "Question text?",
      "options": ["A", "B", "C", "D"],
      "answer_index": 0
    }
  ]
}

GET /api/health

Health check endpoint.

Response:

{
  "status": "healthy",
  "service": "SmartNotes"
}

Deployment

Heroku

1. Create a new Heroku app:

heroku create your-app-name

2. Deploy:

git push heroku main

3. Set environment variables:

heroku config:set LLM_API_KEY=your_key_here

Docker

docker build -t smartnotes .
docker run -p 5000:5000 -e LLM_API_KEY=your_key smartnotes

Project Structure

smartnotes/
├── app/
│   ├── main.py           # Flask application entry point
│   ├── api.py            # API endpoints
│   ├── models.py         # Data models
│   ├── db.py             # Database layer
│   └── services/
│       ├── llm_client.py    # LLM integration
│       ├── pdf_parser.py    # PDF processing
│       └── summarizer.py    # Text processing
├── templates/
│   └── index.html        # Frontend HTML
├── static/
│   ├── app.js           # Frontend JavaScript
│   └── styles.css       # Styles
├── tests/               # Test suite
├── .kiro/              # Kiro AI workflows
└── docs/               # Documentation

Configuration

Environment variables (see .env.example):

• LLM_API_KEY: Your LLM API key
• LLM_API_URL: LLM API endpoint
• SECRET_KEY: Flask secret key
• DATABASE_PATH: SQLite database path
• FLASK_DEBUG: Enable debug mode
• HOST: Server host (default: 0.0.0.0)
• PORT: Server port (default: 5000)

How Kiro Helped

This project was built with assistance from Kiro AI. Here's exactly what Kiro generated:

1. Project Structure & Setup

• ✅ Complete directory structure (app/, tests/, docs/, .kiro/)
• ✅ Configuration files (requirements.txt, .env.example, Procfile)
• ✅ Git configuration (.gitignore with .kiro/ included)

2. Backend Development

• ✅ Flask application with REST API (app/main.py, app/api.py)
• ✅ Service layer abstraction (services/llm_client.py, pdf_parser.py, summarizer.py)
• ✅ Database layer with SQLite (app/db.py, app/models.py)
• ✅ Error handling and logging throughout
• ✅ Environment variable configuration

3. Frontend Development

• ✅ Single-page application (templates/index.html)
• ✅ Responsive CSS with modern gradient design (static/styles.css)
• ✅ Interactive JavaScript (static/app.js)
• ✅ Tab-based interface and quiz functionality

4. Testing Infrastructure

• ✅ Comprehensive pytest test suite (tests/test_*.py)
• ✅ Mocked external dependencies (LLM, PDF parsing)
• ✅ Test fixtures and sample data
• ✅ Cross-platform compatibility

5. AutoNotes Automation

• ✅ Batch processing script (scripts/auto_notes.py)
• ✅ Demo automation (scripts/run_demo.sh)
• ✅ HTML index generation
• ✅ Organized output structure
• ✅ Tests for AutoNotes (tests/test_auto_notes.py)

6. Documentation

• ✅ Main README with installation and usage
• ✅ Deployment guide (Heroku, AWS, Docker)
• ✅ Git commands and workflow
• ✅ AWS Builder Center blog drafts (2 posts)
• ✅ Demo recording instructions
• ✅ Troubleshooting guides

7. Kiro Workflows

• ✅ Workflow definition (.kiro/kiro.json) with 8 steps
• ✅ Task prompts for regeneration (4 prompt files)
• ✅ Kiro usage documentation (.kiro/README_kiro.md)

Total: 40+ files, ~3,000+ lines of production-ready code, all generated with Kiro assistance.

See .kiro/README_kiro.md for detailed Kiro workflow documentation.

License

MIT License - see LICENSE file for details

Contributing

Contributions welcome! Please open an issue or submit a pull request.