Automated newsletter from RSS: LLM filtering, summariza

This workflow automates the collection, relevance evaluation, and delivery of articles from RSS feeds using local language models. Designed for professionals who need only high-relevance content without manual curation.

## Who it´s for
- AI specialists tracking domain-specific news
- Developers using local LLMs for content processing
- Analysts needing automated weekly article digests
- Companies adopting no-code solutions for internal newsletters

## What the automation does
- Periodically checks an RSS feed for new articles (via cron or manual trigger)
- Evaluates article relevance using a local LLM (Ollama) against user-defined interests
- Filters only high-rated articles (scores 7–10)
- Generates concise summaries using a second LLM model
- Merges summaries with metadata, formats into an HTML email, and sends via Gmail
- Stores all data including ratings and metadata in PostgreSQL for analytics and deduplication

## What´s included
- Ready-to-use n8n workflow
- Trigger logic: cron schedule and manual execution
- Integrations with RSS, Gmail, Ollama, and PostgreSQL
- Basic text instructions for setup and adaptation

## Requirements for setup
- Access to an n8n instance
- Configured Ollama server with required models (e.g., Qwen3 for scoring, Gemma3 for summarization)
- Gmail account with API enabled
- Running PostgreSQL instance with external access
- Target RSS feed with desired content

## Benefits and outcomes
- Saves time by eliminating manual scanning of numerous articles
- Personalized content filtering based on defined topics (e.g., ´AI Automation´, ´RAG´)
- Uses local LLMs — data remains within your infrastructure
- Enables long-term trend analysis via stored records in Postgres
- Prevents duplicates through database tracking
- Flexible: easily adjustable to new topics or sources
- Reliable delivery with clean HTML formatting via Gmail

## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via Telegram: @gleb923.