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": "6FSx5OMVxp8Ldg8A",
"name": "Prepare CSV files with GPT-4",
"tags": [],
"nodes": [
{
"id": "5b43e57d-1fe1-4ea6-bf3d-661f7e5fc4b0",
"name": "When clicking \"Execute Workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
960,
240
],
"parameters": {},
"typeVersion": 1
},
{
"id": "291466e8-1592-4080-a675-5e9f486d0d05",
"name": "OpenAI",
"type": "n8n-nodes-base.openAi",
"position": [
1160,
240
],
"parameters": {
"model": "gpt-4",
"prompt": {
"messages": [
{
"content": "=please create a list of 10 random users. Return back ONLY a JSON array. Character names of famous fiction characters. Make Names and Surnames start with the same letter. Name and Surname can be from different characters. If subscribed is false then make date_subscribed empty. If date_subscribed is not empty then make it random and no later then 2023-10-01. Make JSON in a single line, avoid line breaks. Here's an example: [{\"user_name\": \"Jack Jones\", \"user_email\":\"jackjo@yahoo.com\",\"subscribed\": true, \"date_subscribed\":\"2023-10-01\" },{\"user_name\": \"Martin Moor\", \"user_email\":\"mmoor@gmail.com\",\"subscribed\": false, \"date_subscribed\":\"\" }]"
}
]
},
"options": {
"n": 3,
"maxTokens": 2500,
"temperature": 1
},
"resource": "chat"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "edd5bed7-a8a1-4298-b026-3b0061c5064a",
"name": "Split In Batches",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1340,
240
],
"parameters": {
"options": {},
"batchSize": 1
},
"typeVersion": 2
},
{
"id": "f0e414e6-741a-42db-86eb-ba95e220f9ef",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
940,
80
],
"parameters": {
"width": 600,
"height": 126,
"content": "## This is a helper workflow to create 3 CSV files\n### Feel free to adapt as needed\n### Some mock data from GPT is pinned for convenience"
},
"typeVersion": 1
},
{
"id": "f1c2891f-5110-423c-9fb4-37e0a0d0f750",
"name": "Parse JSON",
"type": "n8n-nodes-base.set",
"position": [
1520,
240
],
"parameters": {
"fields": {
"values": [
{
"name": "content",
"type": "arrayValue",
"arrayValue": "={{JSON.parse($json.message.content)}}"
}
]
},
"include": "none",
"options": {}
},
"typeVersion": 3
},
{
"id": "ce59d3e1-3916-48ad-a811-fa19ad66284a",
"name": "Make JSON Table",
"type": "n8n-nodes-base.itemLists",
"position": [
1700,
240
],
"parameters": {
"options": {},
"fieldToSplitOut": "content"
},
"typeVersion": 3
},
{
"id": "8b1fda14-6593-4cc2-ab74-483b7aa4d84a",
"name": "Convert to CSV",
"type": "n8n-nodes-base.spreadsheetFile",
"position": [
1880,
240
],
"parameters": {
"options": {
"fileName": "=funny_names_{{ $('Split In Batches').item.json.index+1 }}.{{ $parameter[\"fileFormat\"] }}",
"headerRow": true
},
"operation": "toFile",
"fileFormat": "csv"
},
"typeVersion": 2
},
{
"id": "d2a621e0-88df-4642-91ab-772f062c8682",
"name": "Save to Disk",
"type": "n8n-nodes-base.writeBinaryFile",
"position": [
2420,
240
],
"parameters": {
"options": {},
"fileName": "=./.n8n/{{ $binary.data.fileName }}"
},
"typeVersion": 1
},
{
"id": "20f60bb0-0527-44c4-85d5-a95c20670893",
"name": "Strip UTF BOM bytes",
"type": "n8n-nodes-base.moveBinaryData",
"position": [
2060,
240
],
"parameters": {
"options": {
"encoding": "utf8",
"stripBOM": true,
"jsonParse": false,
"keepSource": false
},
"setAllData": false
},
"typeVersion": 1
},
{
"id": "bda91493-df5d-4b8c-b739-abca6045faf9",
"name": "Create valid binary",
"type": "n8n-nodes-base.moveBinaryData",
"position": [
2240,
240
],
"parameters": {
"mode": "jsonToBinary",
"options": {
"addBOM": false,
"encoding": "utf8",
"fileName": "=funny_names_{{ $('Split In Batches').item.json.index+1 }}.{{ $('Convert to CSV').first().binary.data.fileExtension }}",
"mimeType": "text/csv",
"keepSource": false,
"useRawData": true
},
"convertAllData": false
},
"typeVersion": 1
},
{
"id": "e1b54e0d-56a5-43e7-82b4-aaead2875a9d",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
2007,
140
],
"parameters": {
"width": 394,
"height": 254,
"content": "### These 2 nodes fix an issue with BOM bytes in the beginning of the file.\nWithout them reading the CSV file back becomes tricky"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "91f77342-1d0f-4033-b09a-3e3c8791107e",
"connections": {
"OpenAI": {
"main": [
[
{
"node": "Split In Batches",
"type": "main",
"index": 0
}
]
]
},
"Parse JSON": {
"main": [
[
{
"node": "Make JSON Table",
"type": "main",
"index": 0
}
]
]
},
"Save to Disk": {
"main": [
[
{
"node": "Split In Batches",
"type": "main",
"index": 0
}
]
]
},
"Convert to CSV": {
"main": [
[
{
"node": "Strip UTF BOM bytes",
"type": "main",
"index": 0
}
]
]
},
"Make JSON Table": {
"main": [
[
{
"node": "Convert to CSV",
"type": "main",
"index": 0
}
]
]
},
"Split In Batches": {
"main": [
[
{
"node": "Parse JSON",
"type": "main",
"index": 0
}
]
]
},
"Create valid binary": {
"main": [
[
{
"node": "Save to Disk",
"type": "main",
"index": 0
}
]
]
},
"Strip UTF BOM bytes": {
"main": [
[
{
"node": "Create valid binary",
"type": "main",
"index": 0
}
]
]
},
"When clicking \"Execute Workflow\"": {
"main": [
[
{
"node": "OpenAI",
"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.
openAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow streamlines the preparation of CSV files by leveraging GPT-4 to process and refine data from uploaded spreadsheets, saving you hours of manual editing and ensuring clean, structured outputs ready for analysis or import. It's ideal for data analysts, marketers, or small business owners handling messy datasets who need quick transformations without coding expertise. The key step involves feeding your spreadsheet into OpenAI for intelligent parsing and formatting, followed by batch processing to generate polished CSV files stored directly on disk.
Use this workflow when you have event-driven data uploads requiring AI-assisted cleanup, such as normalising customer lists or extracting insights from reports, especially with integrations like OpenAI and spreadsheet tools. Avoid it for very large datasets over 10,000 rows, where processing might slow down, or simple tasks that don't benefit from AI. Common variations include adding email notifications after file creation or integrating with Google Sheets for direct cloud syncing.
About this workflow
Prepare CSV files with GPT-4. Uses manualTrigger, openAi, splitInBatches, stickyNote. Event-driven trigger; 11 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.
Goal: This workflow demonstrates the full fluidX THE EYE integration — starting a live session, inviting both the customer (via SMS) and the service agent (via email), and then accessing the media (ph
This n8n template automates the transformation of raw meeting notes into structured tasks and documents using GPT (or another model) , syncing them to Notion and TickTick via a Telegram bot. Automate
Setup: Generate Topic Buffet. Uses readBinaryFile, openAi, writeBinaryFile. Event-driven trigger; 10 nodes.
Store a key with a value in a local json file. Multiple keys could be saved in a single file.
Ask questions like “How much did I spend on food last month?” and get instant answers from your financial data — directly in Telegram.