Auto-Generate LinkedIn Posts from Wikipedia with GPT-4.1-mini Summaries and Ideogram Images (n8n)

Wikipedia article name → Bright Data scrape → AI summary for LinkedIn → Ideogram image → auto-post to LinkedIn with shareable URL

Who

Operators or content creators with an n8n instance who need to maintain an active LinkedIn presence

You get

Submit a Wikipedia article name and automatically receive a LinkedIn post with an image and a public shareable link

You need

n8n

Steps

1. Import the workflow

   In n8n, go to Workflows → + Add workflow → Import from JSON, paste the provided workflow.json, and save with a descriptive name.

2. Configure API credentials

   Add credentials in n8n for: Bright Data API (replace BRIGHT_DATA_API_KEY in all HTTP Request nodes), OpenAI API (link to OpenAI Chat Model node), Anthropic API (optional, link to Anthropic Chat Model node), Ideogram API (replace IDEOGRAM_API_KEY in Image Generate node), and LinkedIn OAuth2 (replace LINKEDIN_PROFILE_ID in Create a post node). Test each connection.

3. Configure workflow parameters

   Adjust node settings as needed: Form Trigger title and field labels; AI Agent systemMessage to change writing style; Image Generate resolution and rendering speed (default 1280x704, TURBO); LinkedIn Post additional fields like hashtags or mentions.

   Execution prompt · Source text。AI Agent node systemMessage field

   Copy prompt

   =Task:- 
   Summarize the following article in under 2000 characters, keeping it professional, informative, and engaging enough for a LinkedIn audience.
   
   Use bullet points if helpful. Avoid repetition. Remove any unnecessary fluff.
   
   Tone should be confident, insightful, and thought-leadership oriented — ideal for busy professionals who want quick understanding.
   
   Here's the content:
   ---
   {{ $json.cataloged_text[0].text }}
   ---

4. Test the workflow

   Start with a simple Wikipedia article (e.g., "Artificial Intelligence"). Monitor each node execution log, verify summary quality, image generation, LinkedIn posting status, and final URL output. [First-test safety] Before the first test, disconnect or disable the Create a post node, or use a LinkedIn test/sandbox account; enable publishing only after the summary and image look correct.

5. Run: submit article and get results

   Access the form via its webhook URL, enter the exact Wikipedia article title, and submit. The workflow auto-executes: Bright Data scrape → AI summary (≤2000 chars) → Ideogram image → LinkedIn publish → Code node generates public link. Check n8n execution logs for progress; final output is the LinkedIn post URL.

   Execution prompt · Source text。AI Agent node text input field (references prior scrape results)

   Copy prompt

   =here is the title:-  {{ $json.cataloged_text[0].title }}
   here is the article of my title :- {{ $json.cataloged_text[0].text }}

   Execution prompt · Source text。Create a post (LinkedIn) node text field

   Copy prompt

   ={{ $('AI Agent').item.json.output.text }}

   Execution prompt · Source text。LinkedIn URL (Code node) jsCode field

   Copy prompt

   const item = $input.item;
   const shareUrn = item.json.urn || '';
   
   // Check if it's a valid LinkedIn share URN
   if (shareUrn.startsWith('urn:li:share:')) {
     item.json.linkedinUrl = `https://www.linkedin.com/feed/update/${shareUrn}/`;
   } else {
     item.json.linkedinUrl = 'Invalid LinkedIn URN';
   }
   
   return item;

You are an n8n workflow setup assistant. The user wants to replicate the 'Generate LinkedIn posts from Wikipedia' template. First confirm they have: an n8n instance, Bright Data API, OpenAI API, Ideogram API, and LinkedIn OAuth2 credentials. Then guide them to import workflow.json, configure credentials, adjust the AI Agent systemMessage style, test, and run. Do not generate or modify API keys for the user.