使用OpenAI从CSV文件中移除个人身份信息（PII）

• •Google Drive API 凭证
• •OpenAI API Key

{
  "meta": {
    "instanceId": "2f9460831fcdb0e9a4494f0630367cfe2968282072e2d27c6ee6ab0a4c165a36"
  },
  "nodes": [
    {
      "id": "ff4e8706-09a0-4bf1-86c1-dfb65f55ccb3",
      "name": "Google Drive 触发器",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        20,
        -140
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "1-hRMnBRYgY6iVJ_youKMyPz83k9GAVYu",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1-hRMnBRYgY6iVJ_youKMyPz83k9GAVYu",
          "cachedResultName": "nnnnnnnnnnn8n"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "PlyNQuMqlwn9SuLb",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "340fb03b-3b8a-4eb4-ad4c-b0ba12b72b19",
      "name": "Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        260,
        -140
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {
          "binaryPropertyName": "data"
        },
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "PlyNQuMqlwn9SuLb",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "4a5d037f-0103-4645-87d0-785dfdfb80d1",
      "name": "从文件提取",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        260,
        60
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1,
      "alwaysOutputData": false
    },
    {
      "id": "36c7e83d-f22f-4a71-b5a2-64ed3e4ce24b",
      "name": "OpenAI",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        -120,
        260
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini",
          "cachedResultName": "GPT-4O-MINI"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "Analyze the provided tabular data and identify the columns that contain personally identifiable information (PII). Return only the column names that contain PII, separated by commas. Key name: 'content'. Do not include any additional text or explanation."
            },
            {
              "content": "=Here is some tabular data with column headers and two example rows.\n\nHeaders: {{Object.keys($json)}}\n\nExample Row 1: {{Object.values($json)}}\n\n"
            }
          ]
        },
        "jsonOutput": true
      },
      "credentials": {
        "openAiApi": {
          "id": "Mld1OIvnEVogxjDH",
          "name": "OpenAi account"
        }
      },
      "executeOnce": true,
      "typeVersion": 1.7
    },
    {
      "id": "771c6535-47d4-4c70-b487-bd5ac602e29c",
      "name": "合并",
      "type": "n8n-nodes-base.merge",
      "position": [
        440,
        260
      ],
      "parameters": {
        "numberInputs": 3
      },
      "typeVersion": 3
    },
    {
      "id": "1fc467fd-379d-4841-978b-89c1453b61d8",
      "name": "上传到 Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        740,
        260
      ],
      "parameters": {
        "name": "={{ $json.fileName }}",
        "content": "={{ $json.content }}",
        "driveId": {
          "__rl": true,
          "mode": "list",
          "value": "My Drive"
        },
        "options": {},
        "folderId": {
          "__rl": true,
          "mode": "list",
          "value": "1F30Qu3csrmMhtcu_prMipeiGm-64VEdd",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1F30Qu3csrmMhtcu_prMipeiGm-64VEdd",
          "cachedResultName": "processed"
        },
        "operation": "createFromText"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "PlyNQuMqlwn9SuLb",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "92715586-e630-4584-83a3-1af42d7cb50e",
      "name": "获取文件名",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        20,
        60
      ],
      "parameters": {
        "options": {
          "destinationFieldName": "originalFilename"
        },
        "fieldToSplitOut": "name"
      },
      "executeOnce": true,
      "typeVersion": 1
    },
    {
      "id": "2c4b3242-34db-4948-b835-cd2340ad7b19",
      "name": "获取结果",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        200,
        260
      ],
      "parameters": {
        "options": {
          "destinationFieldName": "data"
        },
        "fieldToSplitOut": "message.content.content"
      },
      "typeVersion": 1
    },
    {
      "id": "4207dc71-5b0e-4780-9f23-00f5a7fc3862",
      "name": "移除 PII 列",
      "type": "n8n-nodes-base.code",
      "position": [
        580,
        260
      ],
      "parameters": {
        "jsCode": "// Input: All items from the previous node\nconst input = $input.all();\n\n// Step 1: Extract the PII column names from the first item\nconst firstItem = input[0];\nif (!firstItem.json.data || !firstItem.json.data) {\n  throw new Error(\"PII column names are missing in the input data.\");\n}\nconst piiColumns = firstItem.json.data.split(',').map(col => col.trim());\n//console.log(\"PII Columns to Remove:\", piiColumns);\n\n// Step 2: Remove the first two items and process the remaining rows\nlet rows = input.slice(2).map(item => item.json); // Exclude the first item\n//console.log(\"Rows to convert (before skipping last):\", rows);\n\n\n// Ensure there are rows to process\nif (rows.length === 0) {\n  throw new Error(\"No rows to convert to CSV.\");\n}\n\n// Step 3: Remove PII columns from each row\nconst sanitizedRows = rows.map(row => {\n  const sanitizedRow = { ...row }; // Copy the row\n  piiColumns.forEach(column => delete sanitizedRow[column]); // Remove PII columns\n  return sanitizedRow;\n});\n//console.log(\"Sanitized Rows:\", sanitizedRows);\n\n// Step 4: Extract headers from sanitized rows\nconst headers = Object.keys(sanitizedRows[0]); // Extract updated headers\n//console.log(\"CSV Headers:\", headers);\n\n// Step 5: Convert rows to CSV format\nconst csvRows = [\n  headers.join(','), // Add header row\n  ...sanitizedRows.map(row => \n    headers.map(header => String(row[header] || '').replace(/,/g, '')).join(',') // Match headers with rows\n  )\n];\n\n// Join all rows with a newline character\nconst csvContent = csvRows.join('\\n');\n//console.log(\"CSV Content:\", csvContent);\n\nconst originalFileName = input[1].json.originalFilename;\n\n// Step 7: Generate a new filename\nconst fileExtension = originalFileName.split('.').pop();\nconst baseName = originalFileName.replace(`.${fileExtension}`, '');\nconst newFileName = `${baseName}_PII_removed.${fileExtension}`;\n//console.log(\"New Filename:\", newFileName);\n\n// Step 8: Return the CSV content and filename as JSON\nreturn [\n  {\n    json: {\n      fileName: newFileName, // New file name\n      content: csvContent // CSV content as plain text\n    }\n  }\n];\n"
      },
      "typeVersion": 2
    },
    {
      "id": "e9f25ee7-cd00-4496-9062-5d57cab5788d",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -300,
        -220
      ],
      "parameters": {
        "height": 260,
        "content": "## 从 CSV 文件中移除 PII"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "Merge": {
      "main": [
        [
          {
            "node": "Remove PII columns",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI": {
      "main": [
        [
          {
            "node": "Get result",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get result": {
      "main": [
        [
          {
            "node": "Merge",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get filename": {
      "main": [
        [
          {
            "node": "Merge",
            "type": "main",
            "index": 1
          }
        ]
      ]
    },
    "Google Drive": {
      "main": [
        [
          {
            "node": "Extract from File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Upload to Drive": {
      "main": [
        []
      ]
    },
    "Extract from File": {
      "main": [
        [
          {
            "node": "OpenAI",
            "type": "main",
            "index": 0
          },
          {
            "node": "Merge",
            "type": "main",
            "index": 2
          }
        ]
      ]
    },
    "Remove PII columns": {
      "main": [
        [
          {
            "node": "Upload to Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive Trigger": {
      "main": [
        [
          {
            "node": "Get filename",
            "type": "main",
            "index": 0
          },
          {
            "node": "Google Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}