Publish weekly family history stories with GPT-4, Pinecone and WordPress
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What to replace before upgrading
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Story Generation Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (11)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Code
n8n-nodes-base.code - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Wordpress
n8n-nodes-base.wordpress - HTTP Request
n8n-nodes-base.httpRequest - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Schedule Trigger
n8n-nodes-base.scheduleTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore
What it does
Quick Overview This workflow runs weekly to generate an AI-written family-history short story using OpenAI with Pinecone document retrieval, then publishes the HTML story to WordPress and creates a Google Gemini featured image that is uploaded and set on the post. How it works 1. Runs on a weekly schedule every Wednesday. 2. Uses OpenAI (GPT-4o) with session memory and a Pinecone-backed retrieval tool to generate a 500–1000 word family-history short story as WordPress-ready HTML. 3. Extracts the <h1 title, derives a URL slug, and prepares the remaining HTML as the post body. 4. Creates and publishes a WordPress post with the generated story content. 5. Generates a featured image with Google Gemini based on the WordPress post excerpt. 6. Uploads the generated image to the WordPress Media Library and sets it as the post’s featured image. Setup 1. Add your OpenAI API credentials for the GPT-4o chat model and embeddings used in the workflow. 2. Add your Pinecone credentials and ensure the target index (for example, "ariail-ms") exists and is populated with your family documents. 3. Add WordPress API credentials and confirm the site URL, author ID, and any desired categories/status settings match your WordPress configuration. 4. Add Google Gemini credentials and confirm the selected image model is available in your Gemini account. 5. If needed, update the WordPress REST endpoints (media and posts URLs) and the schedule timing to match your environment.