🎬 Generate AI-powered markdown posts from workflow JSON with Gemini & LlamaIndex
⚡ 299 views · 🎬 Content Creation & Video
💡 Pro Tip — HTTP Request scraping tends to break when sites update their markup. If you’re scraping a major platform, check if ScraperNode covers it — it has maintained scrapers for LinkedIn, Instagram, TikTok, YouTube, and 20+ other platforms that return structured data.
Description
Turn any n8n workflow JSON into a publication-ready, SEO-optimized markdown post for the n8n community. Upload your workflow file and let Google Gemini 2.5 Pro, guided by a LlamaIndex knowledge base of best practices, write the post for you.
Last updated: September 2026.
Why Use This Workflow?
Time Savings: A detailed workflow post drops from over an hour of manual writing to under 2 minutes.
Cost Reduction: No separate AI content subscriptions or outsourced writing needed.
Error Prevention: A knowledge base of n8n’s official guidelines keeps content quality and structure consistent, minimizing formatting errors.
Ideal For
- n8n Workflow Creators: Document and share creations on the community platform without the tedious writing.
- Developer Advocates: Standardize and accelerate technical tutorials and workflow showcases.
- Content & Marketing Teams: Streamline the pipeline for n8n-related blog posts, tutorials, and community content.
How It Works
- Trigger: The process starts when you upload an n8n workflow JSON file via a simple web form.
- Data Extraction: The workflow automatically extracts the JSON content from the uploaded file.
- Intelligence Layer: An AI agent powered by Google Gemini 2.5 Pro analyzes the structure, nodes, and metadata of your workflow.
- Knowledge Retrieval: The agent consults a specialized in-memory knowledge base built from n8n’s content guidelines. Documents are parsed with LlamaIndex and refined with a Cohere Reranker for maximum accuracy.
- Content Generation: The AI agent combines the technical details from your JSON with knowledge base best practices to write a complete, benefit-driven markdown post.
- Output & Delivery: The final polished markdown is generated as the workflow output, ready to copy-paste into the n8n community platform.
Setup Guide
Prerequisites
| Requirement | Type | Purpose |
|---|---|---|
| n8n instance | Essential | Workflow execution platform |
| Google Gemini API Key | Essential | Powers the core AI content generation |
| LlamaIndex Cloud API Key | Essential | Parses documents for the knowledge base |
| Cohere API Key | Optional | Improves knowledge base search results |
| Google Drive Account | Optional | For automatically updating the knowledge base from a Google Doc |
Installation Steps
- Import the JSON file to your n8n instance.
- Configure credentials:
- Google Gemini: In the “Gemini 2.5 Pro” node, create and add your Google Gemini API credential.
- LlamaIndex: In the three HTTP Request nodes named “Parse Document…”, “Monitor Document…”, and “Retrieve Parsed…”, create an HTTP Header Auth credential. The header name is
Authorizationand the value isBearer YOUR_LLAMA_INDEX_API_KEY. - Cohere: (Optional) In the “Reranker Cohere” node, create and add your Cohere API credential.
- Google Drive: (Optional) If you plan to auto-update the knowledge base, configure Google Drive OAuth2 credentials for the “Knowledge Base Updated Trigger” and “Download Knowledge Document” nodes.
- Update environment-specific values:
- To use the knowledge base auto-update feature, go to the “Knowledge Base Updated Trigger” node and select the Google Drive file containing your content guidelines.
- Customize settings:
- The primary system prompt in the “n8ncreator” agent node can be modified to adjust the tone, style, or structure of the generated content.
- Test execution:
- Run the workflow manually and use the form to upload a sample n8n workflow JSON file to verify that all connections work correctly.
Technical Details
Core Nodes
| Node | Purpose | Key Configuration |
|---|---|---|
| Form Trigger | Initiates the workflow via a file upload. | Set the “Input Json Workflow” field to required. |
| Langchain Agent | Orchestrates the entire content creation process. | The system prompt contains all instructions for the AI. |
| ChatGoogleGemini | Provides the core generative AI capabilities. | Select your Gemini model of choice (e.g., gemini-2.5-pro). |
| VectorStoreInMemory | Acts as the agent’s knowledge base tool. | Configured to use embeddings from a Google Gemini model. |
| HTTPRequest | Interacts with the LlamaIndex API to parse documents. | Set up with LlamaIndex API endpoint and authentication. |
Customization Options
Basic Adjustments:
- Change AI Model: Replace the
ChatGoogleGemininode with another LLM node (e.g., OpenAI, Anthropic) to use a different provider. - Adjust System Prompt: Modify the prompt in the “n8ncreator” node to tailor the output for different platforms (e.g., blog, internal wiki) or change the writing style.
Advanced Enhancements:
- Automated Publishing: Connect the output of the “n8ncreator” node to a
Ghost,WordPress, orGitHubnode to automatically publish the generated post. - Add Web Search: Equip the Langchain Agent with a web search tool to allow it to fetch live information about new n8n nodes or services.
- Batch Processing: Replace the
Form Triggerwith aRead Binary Filesnode to process an entire folder of workflow JSON files in a single run.
Performance & Optimization
| Metric | Expected Performance | Optimization Tips |
|---|---|---|
| Execution time | ~1 minute per run | Largely dependent on the Gemini API response time. |
| API calls | 1 LLM call per post | Knowledge base updates trigger LlamaIndex/Google calls separately. |
| Error handling | Built-in retry logic for document parsing | Add an error workflow path after the “n8ncreator” node to handle AI generation failures. |
Troubleshooting
Common Issues:
| Problem | Cause | Solution |
|---|---|---|
| AI output is generic or incomplete | The input JSON file is invalid or lacks key information (e.g., no node names). | Ensure you are uploading a valid, exported n8n workflow JSON. Verify the workflow has been saved with descriptive node names. |
| LlamaIndex parsing fails | The LlamaIndex API key is incorrect or the source document is inaccessible. | Double-check your LlamaIndex API credential. Ensure the Google Doc sharing settings allow access. |
| Credential Error | API keys are missing or incorrect for Gemini, LlamaIndex, or Cohere. | Go to the specified nodes and verify that the correct credentials have been created and selected. |
Quick Answers
What do I upload?
Any exported n8n workflow JSON file, through the built-in web form.
Which AI writes the post?
Google Gemini 2.5 Pro, guided by a LlamaIndex knowledge base of content guidelines.
Where does the post go?
It is generated as workflow output, ready to copy-paste into the community platform.
Made by: khmuhtadin Category: AI Tags: AI, Content Generation, Google Gemini, LlamaIndex, Automation Need custom workflows? Contact me
Connect with the creator: Portfolio • Workflows • LinkedIn • Medium • Threads
Additional info
Built with n8n. Need an assessment on your business? Feel free to reach out at https://khmuhtadin.com/consultation/
đź”— Nodes Used
HTTP Request, Google Drive, Google Drive Trigger, AI Agent, Simple Vector Store, n8n Form Trigger
đź“Ą Import
Download workflow.json and import into n8n:
Workflow menu → Import from File