This workflow follows the Chainllm → Chat Trigger recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "Telr6HU0ltH7s9f7",
"name": "\ud83d\udde8\ufe0fOllama Chat",
"tags": [],
"nodes": [
{
"id": "9560e89b-ea08-49dc-924e-ec8b83477340",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
280,
60
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "c7919677-233f-4c48-ba01-ae923aef511e",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"onError": "continueErrorOutput",
"position": [
640,
60
],
"parameters": {
"text": "=Provide the users prompt and response as a JSON object with two fields:\n- Prompt\n- Response\n\nAvoid any preample or further explanation.\n\nThis is the question: {{ $json.chatInput }}",
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "b9676a8b-f790-4661-b8b9-3056c969bdf5",
"name": "Ollama Model",
"type": "@n8n/n8n-nodes-langchain.lmOllama",
"position": [
740,
340
],
"parameters": {
"model": "llama3.2:latest",
"options": {}
},
"credentials": {
"ollamaApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "61dfcda5-083c-43ff-8451-b2417f1e4be4",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-380,
-380
],
"parameters": {
"color": 4,
"width": 520,
"height": 860,
"content": "# \ud83e\udd99 Ollama Chat Workflow\n\nA simple N8N workflow that integrates Ollama LLM for chat message processing and returns a structured JSON object.\n\n## Overview\nThis workflow creates a chat interface that processes messages using the Llama 3.2 model through Ollama. When a chat message is received, it gets processed through a basic LLM chain and returns a response.\n\n## Components\n- **Trigger Node**\n- **Processing Node**\n- **Model Node**\n- **JSON to Object Node**\n- **Structured Response Node**\n- **Error Response Node**\n\n## Workflow Structure\n1. The chat trigger node receives incoming messages\n2. Messages are passed to the Basic LLM Chain\n3. The Ollama Model processes the input using Llama 3.2\n4. Responses are returned through the chain\n\n## Prerequisites\n- N8N installation\n- Ollama setup with Llama 3.2 model\n- Valid Ollama API credentials\n\n## Configuration\n1. Set up the Ollama API credentials in N8N\n2. Ensure the Llama 3.2 model is available in your Ollama installation\n\n"
},
"typeVersion": 1
},
{
"id": "64f60ee1-7870-461e-8fac-994c9c08b3f9",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
340,
280
],
"parameters": {
"width": 560,
"height": 200,
"content": "## Model Node\n- Name: Ollama Model\n- Type: LangChain Ollama Integration\n- Model: llama3.2:latest\n- Purpose: Provides the language model capabilities"
},
"typeVersion": 1
},
{
"id": "bb46210d-450c-405b-a451-42458b3af4ae",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
200,
-160
],
"parameters": {
"color": 6,
"width": 280,
"height": 400,
"content": "## Trigger Node\n- Name: When chat message received\n- Type: Chat Trigger\n- Purpose: Initiates the workflow when a new chat message arrives"
},
"typeVersion": 1
},
{
"id": "7f21b9e6-6831-4117-a2e2-9c9fb6edc492",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
520,
-380
],
"parameters": {
"color": 3,
"width": 500,
"height": 620,
"content": "## Processing Node\n- Name: Basic LLM Chain\n- Type: LangChain LLM Chain\n- Purpose: Handles the processing of messages through the language model and returns a structured JSON object.\n\n"
},
"typeVersion": 1
},
{
"id": "871bac4e-002f-4a1d-b3f9-0b7d309db709",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
560,
-200
],
"parameters": {
"color": 7,
"width": 420,
"height": 200,
"content": "### Prompt (Change this for your use case)\nProvide the users prompt and response as a JSON object with two fields:\n- Prompt\n- Response\n\n\nAvoid any preample or further explanation.\nThis is the question: {{ $json.chatInput }}"
},
"typeVersion": 1
},
{
"id": "c9e1b2af-059b-4330-a194-45ae0161aa1c",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1060,
-280
],
"parameters": {
"color": 5,
"width": 420,
"height": 520,
"content": "## JSON to Object Node\n- Type: Set Node\n- Purpose: A node designed to transform and structure response data in a specific format before sending it through the workflow. It operates in manual mapping mode to allow precise control over the response format.\n\n**Key Features**\n- Manual field mapping capabilities\n- Object transformation and restructuring\n- Support for JSON data formatting\n- Field-to-field value mapping\n- Includes option to add additional input fields\n"
},
"typeVersion": 1
},
{
"id": "3fb912b8-86ac-42f7-a19c-45e59898a62e",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
1520,
-180
],
"parameters": {
"color": 6,
"width": 460,
"height": 420,
"content": "## Structured Response Node\n- Type: Set Node\n- Purpose: Controls how the workflow responds to users chat prompt.\n\n**Response Mode**\n- Manual Mapping: Allows custom formatting of response data\n- Fields to Set: Specify which data fields to include in response\n\n"
},
"typeVersion": 1
},
{
"id": "fdfd1a5c-e1a6-4390-9807-ce665b96b9ae",
"name": "Structured Response",
"type": "n8n-nodes-base.set",
"position": [
1700,
60
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "13c4058d-2d50-46b7-a5a6-c788828a1764",
"name": "text",
"type": "string",
"value": "=Your prompt was: {{ $json.response.Prompt }}\n\nMy response is: {{ $json.response.Response }}\n\nThis is the JSON object:\n\n{{ $('Basic LLM Chain').item.json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "76baa6fc-72dd-41f9-aef9-4fd718b526df",
"name": "Error Response",
"type": "n8n-nodes-base.set",
"position": [
1460,
660
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "13c4058d-2d50-46b7-a5a6-c788828a1764",
"name": "text",
"type": "string",
"value": "=There was an error."
}
]
}
},
"typeVersion": 3.4
},
{
"id": "bde3b9df-af55-451b-b287-1b5038f9936c",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
1240,
280
],
"parameters": {
"color": 2,
"width": 540,
"height": 560,
"content": "## Error Response Node\n- Type: Set Node\n- Purpose: Handles error cases when the Basic LLM Chain fails to process the chat message properly. It provides a fallback response mechanism to ensure the workflow remains robust.\n\n**Key Features**\n- Provides default error messaging\n- Maintains consistent response structure\n- Connects to the error output branch of the LLM Chain\n- Ensures graceful failure handling\n\nThe Error Response node activates when the main processing chain encounters issues, ensuring users always receive feedback even when errors occur in the language model processing.\n"
},
"typeVersion": 1
},
{
"id": "b9b2ab8d-9bea-457a-b7bf-51c8ef0de69f",
"name": "JSON to Object",
"type": "n8n-nodes-base.set",
"position": [
1220,
60
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "12af1a54-62a2-44c3-9001-95bb0d7c769d",
"name": "response",
"type": "object",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "5175454a-91b7-4c57-890d-629bd4e8d2fd",
"connections": {
"Ollama Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"JSON to Object": {
"main": [
[
{
"node": "Structured Response",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "JSON to Object",
"type": "main",
"index": 0
}
],
[
{
"node": "Error Response",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
ollamaApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
Enable seamless, local AI conversations directly within your n8n workflows with this Ollama Chat setup, delivering instant responses without relying on external cloud services for enhanced privacy and control. It's ideal for developers, data analysts, or teams handling sensitive information who need a reliable chatbot for tasks like querying datasets or brainstorming ideas on the fly. The core process begins with the chatTrigger capturing incoming messages, which then feeds into the chainLlm and lmOllama nodes to generate context-aware replies using your chosen local model.
Use this workflow when building interactive AI assistants that must run offline or on self-hosted infrastructure, such as internal support bots or personal research tools, ensuring compliance with data protection standards. Avoid it for high-traffic applications requiring ultra-low latency, where cloud-based alternatives like OpenAI integrations might perform better. Common variations include adding custom prompts via stickyNote nodes for specialised domains like code generation or sentiment analysis.
About this workflow
🗨️Ollama Chat. Uses chatTrigger, chainLlm, lmOllama, stickyNote. Chat trigger; 14 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Becomex v2. Uses chatTrigger, lmChatOllama, agent, toolWorkflow. Chat trigger; 17 nodes.
Transform your local N8N instance into a powerful chat interface using any local & private Ollama model, with zero cloud dependencies ☁️. This workflow creates a structured chat experience that proces
This comprehensive workflow automates the complete financial document processing pipeline using AI. Upload invoices via chat, drop expense receipts into a folder, or add bank statements - the system a
Forscher_Workflow. Uses chatTrigger, chainLlm, lmChatOpenAi, toolWorkflow. Chat trigger; 61 nodes.
The original LLM Council concept was introduced by Andrej Karpathy and published as an open-source repository demonstrating multi-model consensus and ranking. This workflow is my adaptation of that or