Digest

Get a summary of the latest articles from your favorite blogs directly in your mail ✨

About Project

A small project exploring Apache Airflow pipelines that:

• Parses RSS feeds from the
• Summarizes articles using the Gemini API
• Delivers a daily digest via Gmail SMTP

Instructions

Note: Preferably set up in a .venv virtual environment

1. Install Dependencies

pip install -r requirements.txt

2. Configure Environment Variables

Set environment variables according to .env.example:

• EMAIL_PASSWORD: Get this from Google Account Settings → App passwords

3. Configure Airflow

This sets the $AIRFLOW_HOME to the current directory.

chmod +x start_airflow.sh
./start_airflow.sh

4. Configure desired feeds

You can set src/_feeds.json to accomodate your desired RSS feeds by adding the URL to the blog.

5. Trigger the DAG

Go to localhost:8080 and trigger the digest_pipeline DAG