Cooper 
This workflow corresponds to n8n.io template #5857 — we link there as the canonical source.
This workflow follows the Agent → Chainllm 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": "SIDZ9gnOf5yEftvX",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "chat",
"tags": [],
"nodes": [
{
"id": "6f6eb820-f3d4-4aa9-b856-1f327650924d",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-882,
-620
],
"parameters": {
"text": "=Describe the content of the image or pdf in detail then wait for questions about it. Based on what is in the content, suggest 3 questions the user may ask",
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "GPT-4O"
},
"options": {
"detail": "high"
},
"resource": "image",
"inputType": "base64",
"operation": "analyze",
"binaryPropertyName": "data0"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.8
},
{
"id": "64b1e72e-ad85-4759-8def-785ca524e468",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-584,
-520
],
"parameters": {
"text": "=Describe `{{ $json.content }}`\n\nUse the text from the chat to focus the response:\n`{{ $('chat').item.json.chatInput }}`",
"batching": {},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "16246a1a-2adb-4b41-809c-64e173738aba",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-496,
-300
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "gpt-4o"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "00dafa35-ee47-4c21-8ba6-de6e139b5cba",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-584,
-20
],
"parameters": {
"text": "=You are an expert and will help the user with their query `{{ $(\"chat\").item.json.chatInput }}` about\n{{ $json.messages[$json.messages.length - 1].kwargs.content }}\n",
"options": {},
"promptType": "define"
},
"typeVersion": 2
},
{
"id": "39223440-863c-4285-9f27-edf971e953d1",
"name": "If",
"type": "n8n-nodes-base.if",
"position": [
-1180,
-420
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "c9a2577d-0589-41ca-9480-2feda2dfbd9b",
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
},
"leftValue": "={{ $json.files[0].fileName }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "e1970f2b-1a01-4a11-bf65-9b3d9f0e2001",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-436,
200
],
"parameters": {
"sessionKey": "={{ $('chat').item.json.sessionId }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "ee3533c1-f12a-4955-bcb8-a0618f80a67c",
"name": "OpenAI Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-556,
200
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "gpt-4o"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "2bced281-2c19-407f-ad4b-53075667da17",
"name": "chatmem",
"type": "@n8n/n8n-nodes-langchain.memoryManager",
"position": [
-584,
-920
],
"parameters": {
"mode": "insert",
"messages": {
"messageValues": [
{
"type": "ai",
"message": "={{ $json.content }}"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "d5622336-38c3-41f5-880c-a673a90c3ab3",
"name": "chatmem1",
"type": "@n8n/n8n-nodes-langchain.memoryManager",
"position": [
-960,
-20
],
"parameters": {
"options": {},
"simplifyOutput": false
},
"typeVersion": 1.1
},
{
"id": "01d2fa3b-0d56-41a9-ad8a-c79c0038a9b8",
"name": "Simple Memory1",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-496,
-700
],
"parameters": {
"sessionKey": "={{ $(\"chat\").item.json.sessionId }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "417d63c5-3577-446c-844e-bdc9369571f1",
"name": "chat",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1400,
-420
],
"parameters": {
"public": true,
"options": {
"allowFileUploads": true
},
"initialMessages": ""
},
"typeVersion": 1.1
},
{
"id": "9ac78a30-890a-46e7-9148-29795d8ce432",
"name": "Simple Memory2",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-872,
200
],
"parameters": {
"sessionKey": "={{ $(\"chat\").item.json.sessionId }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "1e545980-1e75-436d-ad79-a4a434c6a7dd",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1520,
-740
],
"parameters": {
"width": 340,
"height": 480,
"content": "## Chat with thing\n\nThis n8n template lets you build a smart AI chat assistant that can handle text, images, and PDFs \u2014 using OpenAI's GPT-4o multimodal model. It supports dynamic conversations and file analysis, making it great for AI-driven support bots, personal assistants, or embedded chat widgets."
},
"typeVersion": 1
},
{
"id": "11295c5b-fa66-4487-807c-2593991b48c0",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1100,
-740
],
"parameters": {
"content": "This route runs when an image/file/pdf is attached. It saves what it sees in the chatmem"
},
"typeVersion": 1
},
{
"id": "dee500b2-edba-4639-b505-d0bdec350c0f",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-360,
-640
],
"parameters": {
"content": "Use this node to set the conversation"
},
"typeVersion": 1
},
{
"id": "ac84b377-ce03-4a19-a5ed-6fd5952e702c",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-960,
-160
],
"parameters": {
"content": "This runs after the upload, it retrieves the initial content from the memory\n"
},
"typeVersion": 1
},
{
"id": "3dd32789-a317-44aa-9bc7-2b440a5e57f9",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-360,
-140
],
"parameters": {
"content": "This is the main chat, adjust the prompt to match your use case."
},
"typeVersion": 1
}
],
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "5eb243f1-9afc-48c4-8d1f-d8d091615fab",
"connections": {
"If": {
"main": [
[
{
"node": "OpenAI",
"type": "main",
"index": 0
}
],
[
{
"node": "chatmem1",
"type": "main",
"index": 0
}
]
]
},
"chat": {
"main": [
[
{
"node": "If",
"type": "main",
"index": 0
}
]
]
},
"OpenAI": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
},
{
"node": "chatmem",
"type": "main",
"index": 0
}
]
]
},
"chatmem1": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Simple Memory1": {
"ai_memory": [
[
{
"node": "chatmem",
"type": "ai_memory",
"index": 0
}
]
]
},
"Simple Memory2": {
"ai_memory": [
[
{
"node": "chatmem1",
"type": "ai_memory",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model1": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"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.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n template lets you build a smart AI chat assistant that can handle text, images, and PDFs — using OpenAI's GPT-4o multimodal model. It supports dynamic conversations and file analysis, making it great for AI-driven support bots, personal assistants, or embedded chat…
Source: https://n8n.io/workflows/5857/ — 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.
This template obtains all the possible tools from Bright Data MCP, process this through chatbot, then run any tool based on the user's query
Agent, Chat Trigger, OpenAI Chat +6
✨ Intro This workflow shows how to go beyond a “plain” AI chatbot by:
Telegram, OpenAI, OpenAI Chat +13
⚠️ DISCLAIMER: This workflow uses the AnySite LinkedIn community node, which is only available on self-hosted n8n instances. It will not work on n8n.cloud.
OpenAI Chat, Output Parser Structured, Google Sheets +6
HDW Lead Geländewagen. Uses chatTrigger, lmChatOpenAi, memoryBufferWindow, outputParserStructured. Chat trigger; 92 nodes.
Chat Trigger, OpenAI Chat, Memory Buffer Window +5
Community Node Disclaimer: This workflow uses KlickTipp community nodes.
Chat Trigger, OpenAI Chat, Memory Buffer Window +6