Back to Templates

Summarize Nextcloud documents with IONOS AI Model Hub for sovereign AI

Created by

Created by: Fabrice || fwurtz
Fabrice

Last update

Last update 2 days ago

Categories

Share

This n8n template shows you how to automate document summarization while keeping full digital sovereignty. By combining Nextcloud for file storage and the IONOS AI Model Hub, your sensitive documents stay on European infrastructure—fully outside US CLOUD Act jurisdiction.

Use cases

  • Daily briefings: Automatically summarize lengthy reports as soon as your team uploads them.
  • Meeting notes: Turn uploaded transcripts into clear, actionable bullet points—hands-free.
  • Research management: Get instant summaries of academic papers or PDFs the moment they land in your research folder.

How it works

A Schedule Trigger kicks off the workflow at regular intervals. It calls the Nextcloud List a Folder node to retrieve all files in your chosen directory.

A Code node then acts as a filter, checking each file's last-modified timestamp and letting through only files changed within the past 24 hours.

Filtered files are pulled into the workflow via the Nextcloud Download a File node. From there, the Summarization Chain takes over: a Default Data Loader and Token Splitter prepare the content, and the IONOS AI Model Hub Chat Model generates a concise, structured summary.

The final output is saved back to your Nextcloud instance as a note for your team.

Good to know

Nextcloud setup: Make sure your Nextcloud credentials include both read and write permissions—one to download source files, one to upload the generated summary.

Model selection: The IONOS AI Model Hub currently offers several LLMs, including Llama 3.1 8B, Mistral Nemo 12B, Mistral Small 24B, Llama 3.3 70B, GPT-OSS 120B, and Llama 3.1 405B. For document summarization, Llama 3.3 70B strikes the best balance between output quality and speed. If you're processing high volumes or need faster turnaround, Mistral Nemo 12B is a leaner alternative.

How to set it up

  1. Set your folder path in the List a Folder node to the directory you want to monitor.
  2. In the New Files Only code node, adjust the 24 value to change how far back the workflow looks.
  3. Open the Summarization Chain and define your output format—for example: "Summarize this document in 3 bullet points."

Requirements

  • Nextcloud account for file hosting and retrieval
  • IONOS Cloud account to access the AI Model Hub