Generate AI-powered LinkedIn posts with Ollama, image creation, and Gmail delivery
Needs changesNeeds changes. This template uses 2 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes), HTTP Request Tool (legacy). 2 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) LinkedIn Post Agent (v1.9), Image Prompt Agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
| HTTP Request Tool (legacy) Tavily | HTTP Request node connected to the AI Agent's Tool input |
Nodes used (9)
- AI Agent
@n8n/n8n-nodes-langchain.agent - n8n Form Trigger
n8n-nodes-base.formTrigger - Manual Trigger
n8n-nodes-base.manualTrigger - Convert to File
n8n-nodes-base.convertToFile - HTTP Request
n8n-nodes-base.httpRequest - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - Send Email
n8n-nodes-base.emailSend - LinkedIn
n8n-nodes-base.linkedIn
What it does
This automation flow is designed to generate professional, research-backed LinkedIn posts based on a user-submitted topic and audience, enhance it with a visually aligned image prompt, and then automatically send the post and image via Gmail and/or publish it to LinkedIn. ⚙️ How It Works (Step-by-Step): 1. 📝 Form Submission (Input Trigger) A user fills out a form with: Email Topic of the Post Target Audience This form submission acts as the entry point of the workflow (Form Trigger node). 2. 🤖 LinkedIn Post Generation Agent An AI agent is triggered that: Uses Tavily API to fetch real-time web search content related to the topic. Processes the topic and audience data using an Ollama Chat Model. Generates a well-structured LinkedIn post that includes: Hook Educational insight Professional tone Source citations Hashtags and call to action 3. 🎨 Image Prompt Agent The generated post is passed to a second agent that: Extracts the core message. Converts it into a graphic prompt using a different Ollama LLM. The prompt is written to be used by an image-generation model like DALL·E or Gemma/GPT-based image tools. 4. 🖼️ Image Generation The image prompt is passed to a local image generation endpoint (localhost:8098) or OpenAI (api.openai.com) to generate a visual asset. The base64 image is converted into a file. 5. 📩 Email Dispatch The post text and the generated image are then sent to the user’s email address via the Gmail node. The email includes: The full LinkedIn post The auto-generated image as an attachment 6. 🔗 LinkedIn Publishing (Optional) If OAuth is enabled, the post can also be published directly to LinkedIn using the LinkedIn node. 🛠️ Tools Used: n8n: Orchestration platform OpenRouter & Ollama: Local/hosted LLMs for post and prompt generation Tavily API: Real-time web search OpenAI or Local Endpoint: Image generation from text SMTP (Gmail): For sending emails LinkedIn API: For automated posting 📦 Key Features: End-to-end automation from form to email/post Uses real-time research for accuracy Creative visual generation with professional branding intent Works locally or with cloud APIs Modular: Can switch tools or endpoints (OpenAI ↔ Localhost, Ollama ↔ OpenRouter) 🚀 Ideal Use Cases: Marketing teams needing fast content turnaround Personal branding assistants Founders, freelancers, and executives sharing thought leadership University or organization-wide communication systems