AI-Powered CSV Data Cleaner

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": "CSV Data Cleaner with AI",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "csv-cleaner",
        "responseMode": "responseNode",
        "options": {
          "rawBody": true
        }
      },
      "id": "a1b2c3d4-1111-4000-8000-000000000001",
      "name": "Webhook - CSV Upload",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "const csvText = $input.first().json.body;\nconst lines = csvText.split('\\n');\nconst headers = lines[0].split(',').map(h => h.trim());\nconst rows = [];\nfor (let i = 1; i < lines.length; i++) {\n  if (lines[i].trim() === '') continue;\n  const values = lines[i].split(',').map(v => v.trim());\n  const row = {};\n  headers.forEach((h, idx) => {\n    row[h] = values[idx] || '';\n  });\n  rows.push(row);\n}\nreturn [{ json: { headers, rows, rowCount: rows.length, rawCsv: csvText } }];"
      },
      "id": "a1b2c3d4-1111-4000-8000-000000000002",
      "name": "Code - Parse CSV",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        480,
        300
      ]
    },
    {
      "parameters": {
        "resource": "chat",
        "model": "gpt-4o",
        "messages": {
          "values": [
            {
              "content": "=You are a data cleaning specialist. Given the following CSV data, perform these operations:\n1. Standardize date formats to ISO 8601 (YYYY-MM-DD)\n2. Fix common typos and inconsistencies in text fields\n3. Normalize phone numbers to E.164 format\n4. Remove duplicate rows\n5. Fill obvious missing values where possible\n6. Standardize capitalization (Title Case for names, lowercase for emails)\n\nReturn ONLY the cleaned CSV data with headers, no explanations.\n\nHeaders: {{ $json.headers.join(', ') }}\n\nData ({{ $json.rowCount }} rows):\n{{ $json.rawCsv }}"
            }
          ]
        },
        "options": {
          "temperature": 0.1,
          "maxTokens": 4096
        }
      },
      "id": "a1b2c3d4-1111-4000-8000-000000000003",
      "name": "OpenAI - Clean & Standardize",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "typeVersion": 1.4,
      "position": [
        720,
        300
      ],
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const cleanedCsv = $input.first().json.message.content;\nconst lines = cleanedCsv.split('\\n').filter(l => l.trim() !== '');\nconst headers = lines[0].split(',').map(h => h.trim());\nconst cleanedRows = [];\nfor (let i = 1; i < lines.length; i++) {\n  const values = lines[i].split(',').map(v => v.trim());\n  const row = {};\n  headers.forEach((h, idx) => {\n    row[h] = values[idx] || '';\n  });\n  cleanedRows.push(row);\n}\nreturn [{ json: { cleanedCsv, cleanedRows, rowCount: cleanedRows.length, headers } }];"
      },
      "id": "a1b2c3d4-1111-4000-8000-000000000004",
      "name": "Code - Format Output",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        960,
        300
      ]
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ JSON.stringify({ success: true, cleanedCsv: $json.cleanedCsv, rowCount: $json.rowCount, headers: $json.headers }) }}",
        "options": {
          "responseHeaders": {
            "entries": [
              {
                "name": "Content-Type",
                "value": "application/json"
              }
            ]
          }
        }
      },
      "id": "a1b2c3d4-1111-4000-8000-000000000005",
      "name": "Respond with Cleaned Data",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        1200,
        300
      ]
    }
  ],
  "connections": {
    "Webhook - CSV Upload": {
      "main": [
        [
          {
            "node": "Code - Parse CSV",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Code - Parse CSV": {
      "main": [
        [
          {
            "node": "OpenAI - Clean & Standardize",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI - Clean & Standardize": {
      "main": [
        [
          {
            "node": "Code - Format Output",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Code - Format Output": {
      "main": [
        [
          {
            "node": "Respond with Cleaned Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [
    {
      "name": "ai-data"
    }
  ]
}

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

About this workflow

CSV Data Cleaner with AI. Uses openAi. Webhook trigger; 5 nodes.

Source: https://github.com/mlnjsh/n8n-workflows-mega/blob/main/workflows/ai-data/01-csv-data-cleaner.json — original creator credit. Request a take-down →

More Data & Sheets workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.