🔧 How to Set Up Ollama with n8n

Integrating Ollama—a locally running large language model (LLM)—with n8n allows you to automate intelligent workflows using natural language prompts. Below is a step-by-step professional setup guide:

✅ Prerequisites

• • Ollama installed and running locally — Official site
  • n8n installed (locally or via cloud) — Install options

• Basic familiarity with creating workflows in n8n

🧠 Step 1: Run a Model in Ollama

After installing Ollama, start a language model (e.g., LLaMA 3) by running the following in your terminal:

ollama run llama3

This launches a local API server at:

http://localhost:11434

🔁 Step 2: Create a New Workflow in n8n

1. Open your n8n dashboard.
2. Create a new workflow.
3. Add a Trigger node (e.g., Manual Trigger or Webhook).

📡 Step 3: Send a Prompt to Ollama via HTTP Request

Add a new node: HTTP Request, then configure it as follows:

• HTTP Method: POST
• URL: http://localhost:11434/api/generate
• Headers:

{
  "Content-Type": "application/json"
}

Body (JSON):

{
  "model": "llama3",
  "prompt": "Hello, can you explain what Ollama is?",
  "stream": false
}

🔄 Step 4: Process the Response

Ollama will return a JSON response like this:

{
  "response": "Ollama is a platform for running local LLMs...",
  ...
}

You can use Set, Function, or Logic nodes in n8n to work with this response.

📁 Optional: Full Sample Workflow JSON

Here’s a minimal working example of an n8n workflow to call Ollama:

{
  "nodes": [
    {
      "parameters": {},
      "id": "Manual Trigger",
      "name": "Manual Trigger",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [250, 250]
    },
    {
      "parameters": {
        "requestMethod": "POST",
        "url": "http://localhost:11434/api/generate",
        "jsonParameters": true,
        "options": {},
        "bodyParametersJson": "{\"model\":\"llama3\",\"prompt\":\"Tell me a fun fact about AI\",\"stream\":false}"
      },
      "id": "HTTP Request",
      "name": "Query Ollama",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 2,
      "position": [450, 250]
    }
  ],
  "connections": {
    "Manual Trigger": {
      "main": [
        [
          {
            "node": "Query Ollama",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

📌 Notes & Best Practices

• Ensure Ollama is running when making requests; otherwise, requests will fail.
• Consider using a reverse proxy and authentication for production use.
• Limit the request rate to avoid overloading your local machine.

💬 Final Thoughts

This integration enables you to use powerful open-source LLMs in your automation flows—great for content creation, summarization, classification, and much more.

Related Content: https://7balance.org/can-n8n-access-stockhero-trading-bots-without-an-api/