# Generate LinkedIn posts with Telegram and Supabase: n8n workflow > Started by an incoming Telegram message, and works across LinkedIn, Supabase vectors and Telegram. Source: https://millionrounds.com/workflow/generate-linkedin-posts-with-telegram-and-supabase (Millionrounds; every figure on the page links to its filing or article) [Automation library](https://millionrounds.com/workflows) · [Content](https://millionrounds.com/workflows?category=Content#library) # Generate LinkedIn posts with Telegram and Supabase Started by an incoming Telegram message, and works across LinkedIn, Supabase vectors and Telegram. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 25 steps, 1 branch: large, and worth reading before you trust it with anything live. Large Calls a model: Gemini, OpenAI Retrieval [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-linkedin-posts-with-telegram-and-supabase) **25 steps** Large: read it before trusting it with anything live **1** Branch: places the flow splits **0** Loops or waits **3** Services it connects to ## The flow Starts it 2 Model 14 Logic 3 Service 6 The steps in the order they run, from what starts it. - 1 **On Telegram Message** Telegram trigger *Starts it* - 2 **Data Loader** Document Default Data Loader *Model* - 3 **Embeddings** Embeddings Open Ai *Model* - 4 **LinkedIn Form** Form trigger *Starts it* - 5 **4o mini** Lm Chat Open Ai *Model* - 6 **2.5-flash** Lm Chat Google Gemini *Model* - 7 **5 nano** Lm Chat Open Ai *Model* - 8 **Embeddings.** Embeddings Open Ai *Model* - 9 **If** If *Logic* - 10 **Typing....** Telegram *Service* - 11 **Upload Document** Vector Store Supabase *Model* - 12 **Hook Analyse Agent** Agent *Model* - 13 **Post Structure Agent** Agent *Model* - 14 **Post Generator Agent** Agent *Model* - 15 **Structured Output Parser** Output Parser Structured *Model* - 16 **Structured Output Parser.** Output Parser Structured *Model* - 17 **Structured Output Parser1** Output Parser Structured *Model* - 18 **Supabase Vector Store** Vector Store Supabase *Model* - 19 **LinkedIn Post URL** Http Request *Service* - 20 **Wrong URL** Telegram *Service* - 21 **Code** Code *Logic* - 22 **Create a post** Linked In *Service* - 23 **Scrap Content** Html *Logic* - 24 **Unable to Scrape** Telegram *Service* - 25 **✅ Post Scrapped Sucessfully** Telegram *Service* ## How it's built - **Starts on:** An incoming Telegram message - **Steps:** 25, with 1 branch - **Size:** Large: read it before trusting it with anything live - **Connects to:** LinkedIn, Supabase vectors, Telegram - **Model:** Gemini, OpenAI - **Retrieval:** Answers are drawn from documents you supply, not from the model alone ## Questions What does it need to run? An n8n account, plus your own LinkedIn, Supabase vectors and Telegram accounts, and a key for Gemini and OpenAI. You connect your own accounts after importing it; none are included. What starts it? It starts on an incoming Telegram message. Does it use AI? Yes. It calls Gemini and OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n. How long does it take to set up? Take your time. At 25 steps it is large: read it before trusting it with anything live. How do I import it? Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts. **Before you run it** Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 25 steps before you point it at anything that matters. ## Run it in n8n - **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n) - **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-linkedin-posts-with-telegram-and-supabase) - **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts. Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind. ## Connects to Each opens the other workflows that use it. [LinkedIn](https://millionrounds.com/workflows?service=LinkedIn#library)[Supabase vectors](https://millionrounds.com/workflows?service=Supabase+vectors#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library) ## Workflows like it Also content, with the same services where possible, closest in size first. - [**Automate RSS-to-social media with Claude and Gemini** 25 steps · calls a model · Google Sheets, RSS](https://millionrounds.com/workflow/automate-rss-to-social-media-with-claude-and-gemini) - [**Automated WordPress Blogger with Claude and OpenAI** 25 steps · calls a model · Google Sheets, RSS](https://millionrounds.com/workflow/automated-wordpress-blogger-with-claude-and-openai) - [**Create & publish affiliate product videos with Sora-2** 25 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/create-and-publish-affiliate-product-videos-with-sora-2) - [**Daily Dermatology Watch: Automating Article Summaries** 25 steps · calls a model · MongoDB, RSS](https://millionrounds.com/workflow/daily-dermatology-watch-automating-article-summaries) - [**Generate AI B-roll clips from videos with OpenAI** 25 steps · calls a model · Google Cloud Storage, Telegram](https://millionrounds.com/workflow/generate-ai-b-roll-clips-from-videos-with-openai) - [**Generate and post LinkedIn content with OpenAI** 25 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/generate-and-post-linkedin-content-with-openai)