About this recipe
Recipe Template
{
"id": "af8RV5b2TWB2LclA",
"meta": {
"instanceId": "95f2ab28b3dabb8da5d47aa5145b95fe3845f47b20d6343dd5256b6a28ba8fab",
"templateCredsSetupCompleted": true
},
"name": "Chat with local LLMs using n8n and Ollama",
"tags": [],
"nodes": [
{
"id": "475385fa-28f3-45c4-bd1a-10dde79f74f2",
"name": "When chat message received",
"type": "@n8n\/n8n-nodes-langchain.chatTrigger",
"position": [
700,
460
],
"webhookId": "ebdeba3f-6b4f-49f3-ba0a-8253dd226161",
"parameters": {
"options": []
},
"typeVersion": 1.1
},
{
"id": "61133dc6-dcd9-44ff-85f2-5d8cc2ce813e",
"name": "Ollama Chat Model",
"type": "@n8n\/n8n-nodes-langchain.lmChatOllama",
"position": [
900,
680
],
"parameters": {
"options": []
},
"credentials": {
"ollamaApi": {
"id": "MyYvr1tcNQ4e7M6l",
"name": "Local Ollama"
}
},
"typeVersion": 1
},
{
"id": "3e89571f-7c87-44c6-8cfd-4903d5e1cdc5",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
160,
80
],
"parameters": {
"width": 485,
"height": 473,
"content": "## Chat with local LLMs using n8n and Ollama\nThis n8n workflow allows you to seamlessly interact with your self-hosted Large Language Models (LLMs) through a user-friendly chat interface. By connecting to Ollama, a powerful tool for managing local LLMs, you can send prompts and receive AI-generated responses directly within n8n.\n\n### How it works\n1. When chat message received: Captures the user's input from the chat interface.\n2. Chat LLM Chain: Sends the input to the Ollama server and receives the AI-generated response.\n3. Delivers the LLM's response back to the chat interface.\n\n### Set up steps\n* Make sure Ollama is installed and running on your machine before executing this workflow.\n* Edit the Ollama address if different from the default.\n"
},
"typeVersion": 1
},
{
"id": "9345cadf-a72e-4d3d-b9f0-d670744065fe",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1040,
660
],
"parameters": {
"color": 6,
"width": 368,
"height": 258,
"content": "## Ollama setup\n* Connect to your local Ollama, usually on http:\/\/localhost:11434\n* If running in Docker, make sure that the n8n container has access to the host's network in order to connect to Ollama. You can do this by passing `--net=host` option when starting the n8n Docker container"
},
"typeVersion": 1
},
{
"id": "eeffdd4e-6795-4ebc-84f7-87b5ac4167d9",
"name": "Chat LLM Chain",
"type": "@n8n\/n8n-nodes-langchain.chainLlm",
"position": [
920,
460
],
"parameters": [],
"typeVersion": 1.4
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": "3af03daa-e085-4774-8676-41578a4cba2d",
"connections": {
"Ollama Chat Model": {
"ai_languageModel": [
[
{
"node": "Chat LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Chat LLM Chain",
"type": "main",
"index": 0
}
]
]
}
}
}
How to Use an n8n Template
Create a New Workflow
Click "New Workflow" in your n8n dashboard to get started.
Copy & Paste Template
First, copy this template:
Click here to copy the JSON
.
Then, in n8n, click the three dots (···) → "Import from file" and paste the JSON code.
Customize the Nodes
Go through each node in the workflow to update inputs like spreadsheet IDs, email addresses, or message content. Adjust field mappings to match your data.
Grant Access
For nodes that connect to external apps (like Google Sheets or Slack), you'll need to grant access. Connect your accounts using OAuth or an API key and save the credentials in the node.
Test It
Run the workflow by clicking "Execute Node" for each step or "Run Once" for the whole thing. Check the right sidebar to inspect data and debug any errors (they'll show up in red).
Activate Workflow
Once everything works as expected, click the "Activate" toggle to turn your workflow on. You're all set!