Owly News Summariser

Owly News Summariser is a web application that fetches news articles from various RSS feeds, uses an LLM (Large Language Model) to summarize them, and presents them in a clean, user-friendly interface.

Features

• Fetches news from configurable RSS feeds
• Automatically summarizes articles using Ollama LLM
• Filters news by country
• Progressive Web App (PWA) support for offline access
• Scheduled background updates

Project Structure

The project consists of two main components:

• Backend: A FastAPI application that fetches and processes news feeds, summarizes articles, and provides API endpoints
• Frontend: A Vue.js application that displays the news and provides a user interface for managing feeds

Prerequisites

• Python 3.8+ for the backend
• Node.js 16+ and Yarn for the frontend
• Ollama for article summarization

Installing Yarn

Yarn is a package manager for JavaScript that's required for the frontend. Here's how to install it:

Using npm (recommended)

If you already have Node.js installed, the easiest way to install Yarn is via npm:

npm install -g yarn

Platform-specific installations

Windows

• Using Chocolatey: choco install yarn
• Using Scoop: scoop install yarn
• Manual installation: Download and run the installer

macOS

• Using Homebrew: brew install yarn
• Using MacPorts: sudo port install yarn

Linux

• Debian/Ubuntu:

  curl -sS https://dl.yarnpkg.com/debian/pubkey.gpg | sudo apt-key add -
  echo "deb https://dl.yarnpkg.com/debian/ stable main" | sudo tee /etc/apt/sources.list.d/yarn.list
  sudo apt update && sudo apt install yarn
  

• CentOS/Fedora/RHEL:

  curl --silent --location https://dl.yarnpkg.com/rpm/yarn.repo | sudo tee /etc/yum.repos.d/yarn.repo
  sudo yum install yarn
  

• Arch Linux: pacman -S yarn

After installation, verify Yarn is installed correctly:

yarn --version

Setup

Backend Setup

1. Navigate to the backend directory:

   cd backend
   

2. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Create a .env file based on the example:

   cp example.env .env
   

5. Customize the .env file as needed:

   • OLLAMA_HOST: URL for the Ollama service (default: http://localhost:11434)
   • CRON_HOURS: Interval for scheduled news fetching (default: 1)
   • DATABASE_URL: SQLite database connection string

Frontend Setup

1. Navigate to the frontend directory:

   cd frontend
   

2. Install dependencies:

   yarn
   

Running the Application

Running the Backend

1. Navigate to the backend directory:

   cd backend
   

2. Activate the virtual environment:

   source venv/bin/activate  # On Windows: venv\Scripts\activate
   

3. Start the backend server:

   uvicorn app.main:app --reload
   

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

Running the Frontend

1. Navigate to the frontend directory:

   cd frontend
   

2. Start the development server:

   yarn dev:watch
   

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

Building for Production

Building the Backend

The backend can be deployed as a standard FastAPI application. You can use tools like Gunicorn with Uvicorn workers:

pip install gunicorn
gunicorn app.main:app -w 4 -k uvicorn.workers.UvicornWorker

Building the Frontend

1. Navigate to the frontend directory:

   cd frontend
   

2. Build the frontend:

   yarn build
   

   The built files will be in the dist directory and can be served by any static file server.

API Endpoints

The backend provides the following API endpoints:

• GET /news: Get news articles with optional filtering
• GET /meta/last_sync: Get the timestamp of the last feed synchronization
• POST /meta/cron: Set the schedule for automatic feed synchronization
• GET /meta/feeds: List all configured feeds
• POST /meta/feeds: Add a new feed
• DELETE /meta/feeds: Delete a feed
• GET /meta/model: Check the status of the LLM model
• POST /meta/sync: Manually trigger a feed synchronization

Environment Variables

Backend

• OLLAMA_HOST: URL for the Ollama service
• CRON_HOURS: Interval for scheduled news fetching in hours
• DATABASE_URL: SQLite database connection string

License

Code ist unter der PolyForm Noncommercial 1.0.0 lizenziert. Für jegliche kommerzielle Nutzung bitte Kontakt aufnehmen.