ContentWeaver AI is an intelligent newsletter generator that creates personalized digests based on your interests. It uses AI to curate, summarize, and provide commentary on relevant articles from various sources.
- 🔍 Personalized content curation based on your keywords
- 📝 AI-powered article summarization
- 💭 Smart commentary generation with customizable tone
- 🔄 Real-time RSS feed integration
- 🎯 Semantic search using vector embeddings
- 📱 Clean, user-friendly Streamlit interface
- Python 3.8 or higher
- Hugging Face API token (for LLM access)
- Clone the repository:
git clone https://github.com/b-isry/ContentWeaverAI.git
cd ContentWeaverAI- Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- Install dependencies:
pip install -r requirements.txt- Create a
.envfile in the root directory and add your Hugging Face token:
HF_Token=your_huggingface_token
- Start the Streamlit app:
streamlit run app/main.py-
Open your browser and navigate to the provided local URL (typically http://localhost:8501)
-
In the sidebar:
- Enter your topics/keywords (comma-separated)
- Select your preferred newsletter tone
- Click "Craft" to generate your personalized newsletter
- Content Collection: Fetches articles from configured RSS feeds
- Semantic Search: Uses sentence transformers to find relevant articles based on your keywords
- AI Processing:
- Generates concise summaries of selected articles
- Creates engaging commentary with your preferred tone
- Newsletter Generation: Compiles everything into a well-formatted markdown newsletter
- Streamlit: Web interface
- Transformers: LLM integration
- Sentence-Transformers: Text embeddings
- ChromaDB: Vector database
- BeautifulSoup4: Web scraping
- Feedparser: RSS feed parsing
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.