An AI-powered news aggregation app inspired by InShorts, built with FastAPI and modern AI technologies.

Saransh is an open-source alternative to InShorts that uses AI to:

• Scrape and process Indian news articles
• Categorize and summarize news content
• Provide intelligent news recommendations
• Create 60-word summaries using AI

• Python 3.8+
• PostgreSQL (for production)
• Redis (optional, for caching)

1. Clone the repository

   git clone <your-repo-url>
   cd Saransh

2. Create the Virtual Environment

   python3 -m venv venv
   source venv/bin/activate

3. Install dependencies

   CREATE requirements.in
   pip-compile requirements.in
   pip install -r requirements.txt
   pip freeze > requirements.txt

4. Setup environment variables

   # Copy the example environment file
   cp env.example .env
   
   # Edit .env with your configuration
   nano .env

5. Run the application

   uvicorn main:app --host 0.0.0.0 --port 8000 --reload

6. Access the application

   • API: http://localhost:8000
   • Health Check: http://localhost:8000/health
   • API Documentation: http://localhost:8000/docs

Create a .env file in the root directory with the following variables:

# Database Configuration
DATABASE_URL=postgresql://username:password@localhost:5432/saransh_db

# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key_here

# Application Configuration
APP_ENV=development
DEBUG=True
LOG_LEVEL=INFO

# Server Configuration
HOST=0.0.0.0
PORT=8000

# Redis Configuration (for caching later)
REDIS_URL=redis://localhost:6379

• OpenAI API Key: Get from OpenAI Platform

Saransh/
├── app/
│   ├── agents/          # AI agents and LangChain integration
│   ├── api/             # API routes and endpoints
│   ├── db/              # Database models and connections
│   ├── processors/      # News processing and cleaning
│   ├── scrapers/        # News scraping modules
│   ├── utils/           # Utility functions
│   └── config.py        # Configuration management
├── main.py              # Application entry point
├── requirements.txt     # Python dependencies
├── env.example          # Environment variables template
└── readme.md           # This file

python main.py

The app will run with:

• Auto-reload enabled
• Debug mode on
• Detailed logging

# Set environment to production
export APP_ENV=production
export DEBUG=False

# Run with uvicorn directly
uvicorn main:app --host 0.0.0.0 --port 8000

curl http://localhost:8000/health

Expected response:

{
    "status": "healthy",
    "timestamp": "2024-01-01T12:00:00",
    "service": "saransh-news-app",
    "environment": "development"
}

• Project setup and structure
• Basic FastAPI application
• Environment configuration
• Database setup and models
• News scraping functionality
• AI-powered content processing
• RAG (Retrieval-Augmented Generation) system
• API endpoints for news retrieval
• Docker containerization
• Production deployment

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

This project is licensed under the MIT License.

If you encounter any issues or have questions:

1. Check the Issues page
2. Create a new issue with detailed information
3. Join our community discussions

Built with ❤️ for the AI and news community