This workflow follows the Agent → OpenAI Chat 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 →
{
"name": "n8n Chat Demo (GitHub) copy",
"nodes": [
{
"parameters": {
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1300,
-120
],
"id": "b7caf2b6-a438-47d6-95cb-d423edcc5ee6",
"name": "Respond to Webhook"
},
{
"parameters": {},
"type": "n8n-nodes-base.merge",
"typeVersion": 3.1,
"position": [
460,
-120
],
"id": "4a0b1e1e-c6c1-454c-9cd1-ecefd5f9336e",
"name": "Merge"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.8,
"position": [
680,
-120
],
"id": "ab7a8154-bb01-49f6-9629-a81a8eddd692",
"name": "AI Agent"
},
{
"parameters": {
"model": {
"__rl": true,
"value": "gpt-4o-mini",
"mode": "list",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
680,
100
],
"id": "b2bdfe0f-a59c-463e-b8a9-cb56abfd5a28",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "5354b213-107d-4000-9f1f-cdf2614ea607",
"leftValue": "={{ $json.body }}",
"rightValue": "",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
}
},
{
"id": "75209ef6-7649-41fc-a070-95783175a0d6",
"leftValue": "={{ $json.body.chatInput }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
-540,
-20
],
"id": "c9aa6824-e13a-4ace-b1d9-ae0118705d93",
"name": "Check if chatInput is set"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
820,
100
],
"id": "ba90f182-b8c4-4b11-b02d-691625bd7107",
"name": "Simple Memory"
},
{
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "return {\n output: $json.output,\n sessionId: $('Merge').item.json.sessionId,\n};\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1080,
-120
],
"id": "14bb742d-1dfc-4142-a1c0-870b952832fc",
"name": "Build response with sessionId"
},
{
"parameters": {
"httpMethod": "POST",
"path": "4af602f1-e8c7-4f0c-856b-e08623232897",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
-780,
-20
],
"id": "e5ca41d9-4716-4ae9-8b85-01b7ff0e6537",
"name": "Webhook"
},
{
"parameters": {
"jsCode": "return $input.first().json.body;"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
-220,
-120
],
"id": "3833b6e3-759a-423a-8712-75463270c542",
"name": "Get \"body\""
},
{
"parameters": {
"options": {
"responseCode": 500
}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
-220,
80
],
"id": "c08e12ae-7f90-46c7-a212-e5e916e97847",
"name": "Error"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 2
},
"conditions": [
{
"id": "75209ef6-7649-41fc-a070-95783175a0d6",
"leftValue": "={{ $json.sessionId }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
20,
-120
],
"id": "99cea5a2-3800-4ffd-aef4-6a5ce6476df0",
"name": "Existing \"sessionId\"?"
},
{
"parameters": {
"action": "generate",
"dataPropertyName": "sessionId"
},
"type": "n8n-nodes-base.crypto",
"typeVersion": 1,
"position": [
240,
80
],
"id": "dc182701-3ab5-43a4-9cb3-605eacd57b96",
"name": "Generate sessionId"
}
],
"connections": {
"Merge": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Build response with sessionId",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Check if chatInput is set": {
"main": [
[
{
"node": "Get \"body\"",
"type": "main",
"index": 0
}
],
[
{
"node": "Error",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Build response with sessionId": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Webhook": {
"main": [
[
{
"node": "Check if chatInput is set",
"type": "main",
"index": 0
}
]
]
},
"Get \"body\"": {
"main": [
[
{
"node": "Existing \"sessionId\"?",
"type": "main",
"index": 0
}
]
]
},
"Existing \"sessionId\"?": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
],
[
{
"node": "Generate sessionId",
"type": "main",
"index": 0
}
]
]
},
"Generate sessionId": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "6f813a10-515b-4ce5-a8f4-8953ad0896b2",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "U8YIj8ChjQkZV5wY",
"tags": []
}
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.
openAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
n8n Chat Demo (GitHub) copy. Uses agent, lmChatOpenAi, memoryBufferWindow, crypto. Webhook trigger; 12 nodes.
Source: https://github.com/symbiosika/n8n-embedded-chat-interface/blob/20dd04395d893df444a9969bb456399cbc3fe1d5/examples/n8n/n8n_Chat_Demo.json — 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.
L&D_AgentsAI_ATIVO. Uses httpRequest, agent, googleCalendarTool, toolSerpApi. Webhook trigger; 93 nodes.
Remi 1.1. Uses lmChatOpenAi, memoryPostgresChat, openAi, postgres. Webhook trigger; 89 nodes.
My workflow 15. Uses httpRequest, memoryBufferWindow, agent, lmChatOpenAi. Webhook trigger; 74 nodes.
Enhance your support, onboarding, and internal knowledge workflows with an intelligent RAG-powered chatbot that responds using live data stored in Google Sheets. 🤖📚 Built for teams that rely on struct
Flux. Uses lmChatOpenAi, agent, googleGemini, httpRequest. Webhook trigger; 67 nodes.