Hacker News throwback machine - see what was hot on this day, every year!
Ready for 3.0What this workflow does
This AI workflow has 13 nodes and runs on a schedule (every day at 21:00). Along the way it connects Google Gemini Chat Model and Telegram.
How it runs
Trigger: On a schedule (every day at 21:00).
- CreateYearsList (Code): runs custom JavaScript code
- CleanUpYearList (Edit Fields (Set)): sets 1 field: datesToFetch
- Split Out: splits a list into separate items
- GetFrontPage (HTTP Request): calls an HTTP API
- ExtractDetails (HTML): parses or builds HTML
- GetHeadlines (Edit Fields (Set)): sets 1 field: headlines
- GetDate (Edit Fields (Set)): sets 1 field: date
- Merge: merges the data from its input branches
- SingleJson (Aggregate): combines items into one
- Basic LLM Chain: sends a prompt to an LLM, with model: Google Gemini Chat Model
…plus 1 more step. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (11)
- Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Code
n8n-nodes-base.code - Edit Fields (Set)
n8n-nodes-base.set - Split Out
n8n-nodes-base.splitOut - HTTP Request
n8n-nodes-base.httpRequest - HTML
n8n-nodes-base.html - Merge
n8n-nodes-base.merge - Aggregate
n8n-nodes-base.aggregate - Telegram
n8n-nodes-base.telegram
From the author
This is a simple workflow that grabs HackerNews front-page headlines from today's date across every year since 2007 and uses a little AI magic (Google Gemini) to sort 'em into themes, sends a neat Markdown summary on Telegram. How it works 1. Runs daily,…