Skip to content
UsecaseBoard
← All use cases
hashnodeLocal AI

Send yourself a daily technical digest using a local model

At a glance

A developer built an n8n pipeline that summarizes selected RSS feeds with local Ollama inference and emails the digest through Gmail. This workflow is listed under Local AI, RSS, Workflow Automation.

Agents / tools
n8n, Ollama, Gemma, Gmail

SourceBuilding a tool for these workflows? See weekly rates.

What they did

1) Run n8n with a reachable Ollama generate endpoint and a downloaded model. Enable Gmail API in a Google Cloud project, configure OAuth consent and connect Gmail credentials in n8n. 2) Add a daily 09:00 Schedule Trigger and RSS Read nodes for your chosen AI, Kubernetes, AWS or security feeds. Use Edit Fields to retain titles and links and label category and source; merge the items and build a summarization prompt. 3) POST to Ollama's /api/generate with model, prompt and stream set to false. Parse the response and remove unwanted Markdown wrappers. 4) Build subject and html fields. In Gmail, choose Message → Send, set your recipient and map those fields. 5) Test delivery, inspect the received digest and activate the schedule.

How it went

The author reports successful end-to-end delivery after fixing request formatting and enabling Gmail API.

Worth knowing

The model sometimes invented sections and links, and Markdown leaked into emails before cleanup.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

No prompt excerpt was provided by the source.

Sponsored

CodeBuddy

Tencent Cloud AI coding assistant for IDE and CLI.

Try CodeBuddy ↗
Explore all →