Samsung Phone Information System

A comprehensive intelligent system for Samsung smartphone information, featuring web scraping, conversational AI chatbot, multi-agent system, and REST API integration.

Features

• Web Scraping: Automated data collection from GSMArena for Samsung phone specifications
• RAG Chatbot: Conversational AI using free open-source models with retrieval-augmented generation
• Multi-Agent System: Specialized agents for phone specifications, comparisons, and review generation
• REST API: FastAPI-based endpoints for system interaction
• PostgreSQL Database: Structured storage for phone data and generated reviews
• Vector Database: ChromaDB integration for semantic search and RAG capabilities

Technology Stack

• Web Scraping: BeautifulSoup4, aiohttp, Selenium
• Database: PostgreSQL with SQLAlchemy ORM
• Chatbot: Hugging Face Transformers, Sentence Transformers
• Multi-Agent: CrewAI framework
• API: FastAPI with Pydantic models
• Vector Store: ChromaDB
• Models: Free open-source models (no OpenAI API required)

Installation

1. Clone the repository:

   git clone https://github.com/zenjahid/samsung-chatbot-api.git
   cd samsung-chatbot-api

2. Install dependencies:

   pip install -r requirements.txt

3. Set up PostgreSQL database:

   # Install PostgreSQL (Ubuntu/Debian)
   sudo apt-get install postgresql postgresql-contrib
   
   # Create database
   sudo -u postgres createdb samsung_phones
   sudo -u postgres createuser --superuser $USER

4. Configure environment:

   cp .env.example .env
   # Edit .env with your database credentials

5. Initialize the system:

   python -c "from src.database.connection import create_tables; create_tables()"

Usage

1. Start the API Server

python main.py

The API will be available at http://localhost:8000

2. API Documentation

Visit http://localhost:8000/docs for interactive API documentation.

3. Scrape Samsung Phone Data

# Via API
curl -X POST "http://localhost:8000/scraper/run"

# Or directly
python src/scraper/gsmarena_scraper.py

4. Chat with the Bot

curl -X POST "http://localhost:8000/chat" \
  -H "Content-Type: application/json" \
  -d '{"message": "What are the camera specs of the Samsung Galaxy S23?"}'

5. Use Multi-Agent System

# Get specifications
curl -X POST "http://localhost:8000/agents/specifications?phone_name=Galaxy S23"

# Compare phones
curl -X POST "http://localhost:8000/agents/compare" \
  -H "Content-Type: application/json" \
  -d '{"phone_names": ["Galaxy S23", "Galaxy S22"]}'

# Generate review
curl -X POST "http://localhost:8000/agents/review" \
  -H "Content-Type: application/json" \
  -d '{"phone_name": "Galaxy S23 Ultra"}'

API Endpoints

Chat Endpoints

• POST /chat - Chat with RAG-enabled bot
• GET /examples - Get example queries

Phone Information

• GET /phones - List all phones
• GET /phones/{phone_id} - Get phone by ID
• GET /phones/search/{phone_name} - Search phones

Multi-Agent System

• POST /agents/specifications - Get detailed specs
• POST /agents/compare - Compare multiple phones
• POST /agents/review - Generate comprehensive review

Data Management

• POST /scraper/run - Run web scraper
• GET /stats - System statistics
• GET /health - Health check

Project Structure

src/
├── config.py                 # Configuration settings
├── api/
│   └── main.py              # FastAPI application
├── agents/
│   └── multi_agent_system.py # CrewAI multi-agent system
├── chatbot/
│   └── rag_chatbot.py       # RAG chatbot implementation
├── database/
│   ├── connection.py        # Database connection
│   └── models.py           # SQLAlchemy models
└── scraper/
    └── gsmarena_scraper.py  # Web scraper for GSMArena
data/                        # Data storage
tests/                       # Test files

Models Used

The system uses free, open-source models:

• Language Model: microsoft/DialoGPT-medium (conversation)
• Embedding Model: all-MiniLM-L6-v2 (text embeddings)
• Agent Model: microsoft/DialoGPT-small (agent coordination)

Example Queries

Chat Examples

• "What are the camera specs of the Samsung Galaxy S23?"
• "Which Samsung phone has the best battery life?"
• "How does the Galaxy S23 compare to the S22 in terms of performance?"
• "What is the price of the Galaxy Z Fold 4?"

Agent Examples

• Specifications: Get detailed specs for any Samsung phone
• Comparisons: Compare 2 or more Samsung phones
• Reviews: Generate comprehensive AI reviews

Development

Running Tests

pytest tests/

Code Formatting

black src/
isort src/
flake8 src/

Adding New Features

1. Follow the existing project structure
2. Use type hints and docstrings
3. Add appropriate error handling
4. Update API documentation

Configuration

Key configuration options in .env:

• DATABASE_URL: PostgreSQL connection string
• MODEL_NAME: Language model for chatbot
• EMBEDDING_MODEL: Model for text embeddings
• SCRAPING_DELAY: Delay between web scraping requests
• CHROMA_DB_PATH: ChromaDB storage path

Troubleshooting

Common Issues

1. Database Connection Error:

   • Ensure PostgreSQL is running
   • Check database credentials in .env

2. Model Loading Issues:

   • Ensure sufficient disk space for model cache
   • Check internet connection for model downloads

3. Web Scraping Failures:

   • Check GSMArena website accessibility
   • Adjust scraping delays if needed

Logs

Check logs for detailed error information:

tail -f logs/app.log

Contributing

1. Fork the repository
2. Create a feature branch
3. Make changes with tests
4. Submit a pull request

License

This project is for educational and research purposes. Please respect GSMArena's terms of service when scraping data.