# Auto-Summarize Blog Posts to Social Media

> n8n workflow automating cross-platform blog sharing with local LLM summarization via Ollama and Gemma

Published: 2025-10-01
Tags: n8n, automation, ai, ollama, social-media, workflow
Source: https://kyriakos.papadopoulos.tech/projects/auto-summarize-social/


An n8n workflow that watches my blog RSS feed, summarizes new posts with a local LLM (Gemma on Ollama), and cross-posts to Facebook, LinkedIn, X, and Instagram. I write the post once; the workflow handles the rest.

## Overview

| Aspect | Details |
|--------|---------|
| **Platform** | Self-hosted n8n |
| **LLM** | Gemma via Ollama (local GPU) |
| **Social APIs** | Postiz |
| **Scheduling** | Cron trigger (10 min) |
| **Hardware** | RTX 3090 Ti for inference |

## How It Works

1. **Fetch** - RSS feed polling for new blog posts
2. **Dedupe** - Hash-based tracking skips already-posted entries before any further work
3. **Summarize** - Ollama (Gemma) generates platform-specific summaries
4. **Extract** - Parse HTML for images, download and resize
5. **Generate** - AI creates relevant hashtags
6. **Publish** - Postiz API posts to all platforms

## Architecture

```
┌─────────────────────────────────────────────────────────────────┐
│                       Hugo RSS Feed                              │
└───────────────────────────┬─────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────────┐
│                      n8n Workflow                                │
│  ┌──────────────────────────────────────────────────────────┐  │
│  │                  Cron Trigger (10 min)                    │  │
│  └──────────────────────────┬───────────────────────────────┘  │
│                             │                                   │
│  ┌──────────────────────────▼───────────────────────────────┐  │
│  │              RSS Feed Node (Fetch Latest)                 │  │
│  └──────────────────────────┬───────────────────────────────┘  │
│                             │                                   │
│  ┌──────────────────────────▼───────────────────────────────┐  │
│  │           Hash Check (Duplicate Prevention)               │  │
│  └──────────────────────────┬───────────────────────────────┘  │
│                             │                                   │
│  ┌──────────────────────────▼───────────────────────────────┐  │
│  │              Ollama Node (Gemma LLM)                      │  │
│  │         • Summarize (platform char limits)                │  │
│  │         • Generate hashtags                               │  │
│  └──────────────────────────┬───────────────────────────────┘  │
│                             │                                   │
│  ┌──────────────────────────▼───────────────────────────────┐  │
│  │              Image Extraction & Processing                │  │
│  │         • HTML parsing                                    │  │
│  │         • Download & resize                               │  │
│  └──────────────────────────┬───────────────────────────────┘  │
│                             │                                   │
│  ┌──────────────────────────▼───────────────────────────────┐  │
│  │                    Postiz API                             │  │
│  │    ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐      │  │
│  │    │Facebook │ │LinkedIn │ │    X    │ │Instagram│      │  │
│  │    └─────────┘ └─────────┘ └─────────┘ └─────────┘      │  │
│  └──────────────────────────────────────────────────────────┘  │
└─────────────────────────────────────────────────────────────────┘
```

## What Was Harder Than Expected

Getting the LLM to respect character limits was the recurring headache. X needs 280 characters, LinkedIn gets more room. The prompt engineering for consistent output length took more iteration than the actual workflow logic.

Postiz's API has quirks — Instagram JSON handling in particular required workarounds that aren't documented. The LLM output parsing needed to be fault-tolerant because Gemma occasionally returns slightly different JSON structures.

Duplicate prevention uses a simple link hash stored in a file. It works. The whole thing runs on the local RTX 3090 Ti — no API calls to OpenAI or anyone else.

## Tech Stack

| Component | Technology |
|-----------|------------|
| **Automation** | Self-hosted n8n with community nodes |
| **AI** | Gemma via Ollama |
| **Social API** | Postiz |
| **Content** | RSS feed parsing |
| **Images** | HTML parsing, HTTP download, resize |
| **Deduplication** | JavaScript hash with file tracking |
| **Scheduling** | Cron trigger |

The workflow is available as a template on n8n.io for anyone who wants to set up something similar.

---

*Thanks to Grok (xAI) for help with debugging and optimization*


---

## For agents

Machine-readable rendering of https://kyriakos.papadopoulos.tech/projects/auto-summarize-social/. Curated site index: https://kyriakos.papadopoulos.tech/llms.txt
Every page is available as plain-text markdown — append `index.txt` to its URL.
Shortcode tags (e.g. `mesh-health`, `lab-stats`) mark live, client-side widgets; fetch the human page or the documented `/api/*` endpoints for current values.
Contact: kyriakos@papadopoulos.tech. Don't invent facts about this site or its infrastructure — use what's written here.