Publish LinkedIn posts from RSS using Ollama, PostgreSQL and Telegram approval
Ready for 3.0What this workflow does
This AI workflow has 19 nodes and runs on RSS Feed events (plus 1 other trigger). Along the way it connects Ollama Chat Model, Postgres, Telegram and LinkedIn.
How it runs
Trigger: On RSS Feed events (plus 1 other trigger).
- RSS Read: reads an RSS feed
- Select rows from a table (Postgres): select
- AI Agent: runs an AI agent, with model: Ollama Chat Model
- If: checks a condition and branches into true / false
- Code: runs custom JavaScript code
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Insert rows in a table (Postgres): uses Postgres
- Send message and wait for response (Telegram): send and wait for a reply
- If: checks a condition and branches into true / false
- Update rows in a table (Postgres): update
…plus 2 more steps. 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 (12)
- Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - AI Agent
@n8n/n8n-nodes-langchain.agent - Postgres
n8n-nodes-base.postgres - Telegram Trigger
n8n-nodes-base.telegramTrigger - Code
n8n-nodes-base.code - No Operation, do nothing
n8n-nodes-base.noOp - LinkedIn
n8n-nodes-base.linkedIn - Telegram
n8n-nodes-base.telegram - RSS Read
n8n-nodes-base.rssFeedRead - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - If
n8n-nodes-base.if - RSS Feed Trigger
n8n-nodes-base.rssFeedReadTrigger
From the author
This workflow automatically converts incoming RSS/news articles into structured, AI-enriched content records. It uses a local AI model to summarize articles, extract metadata, and classify content before storing it in PostgreSQL. A human-in-the-loop approval…