{
  "id": "sUIPemKdKqmUQFt6",
  "meta": {
    "instanceId": "workflow-dcaac409",
    "versionId": "1.0.0",
    "createdAt": "2025-09-29T07:07:44.725085",
    "updatedAt": "2025-09-29T07:07:44.725100",
    "owner": "n8n-user",
    "license": "MIT",
    "category": "automation",
    "status": "active",
    "priority": "high",
    "environment": "production"
  },
  "name": "Extract text from PDF and image using Vertex AI (Gemini) into CSV",
  "tags": [
    "automation",
    "n8n",
    "production-ready",
    "excellent",
    "optimized"
  ],
  "nodes": [
    {
      "id": "f60ef5f9-bc08-4cc9-804e-697ae6f88b9b",
      "name": "Google Gemini Chat Model",
      "type": "n8n-nodes-base.noOp",
      "position": [
        980,
        920
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-1.5-pro-latest"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "hmNTKSKfppgtDbM5",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1,
      "notes": "This lmChatGoogleGemini node performs automated tasks as part of the workflow."
    },
    {
      "id": "81d3f7b8-20cb-4aac-82a9-d4e8e6581105",
      "name": "Get PDF or Images",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        220,
        420
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "1HOeRP5iwccg93UPUYmWYD7DyDmRREkhj",
          "cachedResultUrl": "{{ $env.WEBHOOK_URL }}",
          "cachedResultName": "Actual Budget"
        },
        "authentication": "{{ $credentials.serviceAccount }}"
      },
      "credentials": {
        "googleApi": {
          "id": "axkK6IN61bEAT6GM",
          "name": "Google Service Account account"
        }
      },
      "typeVersion": 1,
      "notes": "This googleDriveTrigger node performs automated tasks as part of the workflow."
    },
    {
      "id": "fe9a8228-7950-4e2c-8982-328e03725782",
      "name": "Route based on PDF or Image",
      "type": "n8n-nodes-base.switch",
      "position": [
        480,
        420
      ],
      "parameters": {
        "rules": {
          "rules": [
            {
              "value2": "application/pdf",
              "outputKey": "YOUR_CREDENTIAL_HERE"
            },
            {
              "value2": "image/",
              "operation": "contains",
              "outputKey": "YOUR_CREDENTIAL_HERE"
            }
          ]
        },
        "value1": "={{$json.mimeType}}",
        "dataType": "string"
      },
      "typeVersion": 2,
      "notes": "This switch node performs automated tasks as part of the workflow."
    },
    {
      "id": "f62b71e5-af17-4f85-abff-7cee5100affc",
      "name": "Download PDF",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        740,
        320
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $('Get PDF or Images').item.json.id }}"
        },
        "options": {},
        "operation": "download",
        "authentication": "{{ $credentials.serviceAccount }}"
      },
      "credentials": {
        "googleApi": {
          "id": "axkK6IN61bEAT6GM",
          "name": "Google Service Account account"
        }
      },
      "executeOnce": true,
      "typeVersion": 3,
      "notes": "This googleDrive node performs automated tasks as part of the workflow."
    },
    {
      "id": "fa99fbcf-1353-410d-a0db-48cea1178a76",
      "name": "Download Image",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        740,
        740
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $('Get PDF or Images').item.json.id }}"
        },
        "options": {},
        "operation": "download",
        "authentication": "{{ $credentials.serviceAccount }}"
      },
      "credentials": {
        "googleApi": {
          "id": "axkK6IN61bEAT6GM",
          "name": "Google Service Account account"
        }
      },
      "executeOnce": true,
      "retryOnFail": false,
      "typeVersion": 3,
      "alwaysOutputData": true,
      "notes": "This googleDrive node performs automated tasks as part of the workflow."
    },
    {
      "id": "e4979746-44bb-493e-b5eb-f9646b510888",
      "name": "Extract data from PDF",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        980,
        320
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1,
      "notes": "This extractFromFile node performs automated tasks as part of the workflow."
    },
    {
      "id": "6549c335-e749-4b95-b77d-096a5e77af5e",
      "name": "Send data to A.I.",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1180,
        320
      ],
      "parameters": {
        "url": "{{ $env.API_BASE_URL }}",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"model\": \"meta-llama/llama-3.1-70b-instruct:free\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"You are given a bank statement.{{encodeURIComponent($json.text)}}. Read the PDF and export all the transactions as CSV. Add a column called category and based on the information assign a category name. Return only the CSV data starting with the header row.\"\n    }\n  ]\n}",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "{{ $credentials.genericCredentialType }}",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "WY7UkF14ksPKq3S8",
          "name": "Header Auth account 2"
        }
      },
      "typeVersion": 4.2,
      "alwaysOutputData": false,
      "notes": "This httpRequest node performs automated tasks as part of the workflow."
    },
    {
      "id": "42341f03-c9fc-4290-963e-1a723202a739",
      "name": "Convert to CSV",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        1400,
        320
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1,
      "notes": "This convertToFile node performs automated tasks as part of the workflow."
    },
    {
      "id": "bb446447-3f46-47e7-96a2-3fc720715828",
      "name": "Upload to Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        1640,
        320
      ],
      "parameters": {
        "name": "={{$today}}",
        "driveId": {
          "__rl": true,
          "mode": "list",
          "value": "My Drive",
          "cachedResultUrl": "{{ $env.WEBHOOK_URL }}",
          "cachedResultName": "My Drive"
        },
        "options": {},
        "folderId": {
          "__rl": true,
          "mode": "list",
          "value": "1Zo4OFCv1qWRX1jo0VL_iqUBf4v0fZEXe",
          "cachedResultUrl": "{{ $env.WEBHOOK_URL }}",
          "cachedResultName": "CSV Exports"
        },
        "authentication": "{{ $credentials.serviceAccount }}"
      },
      "credentials": {
        "googleApi": {
          "id": "axkK6IN61bEAT6GM",
          "name": "Google Service Account account"
        }
      },
      "typeVersion": 3,
      "notes": "This googleDrive node performs automated tasks as part of the workflow."
    },
    {
      "id": "843bc9c1-79a6-4f42-b9ee-fbec5f30b18d",
      "name": "Convert to CSV2",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        1360,
        740
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1,
      "notes": "This convertToFile node performs automated tasks as part of the workflow."
    },
    {
      "id": "6404bf65-3a7e-4be9-9b7f-98a23dca2ffd",
      "name": "Upload to Google Drive1",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        1640,
        740
      ],
      "parameters": {
        "name": "={{$today}}",
        "driveId": {
          "__rl": true,
          "mode": "list",
          "value": "My Drive",
          "cachedResultUrl": "{{ $env.WEBHOOK_URL }}",
          "cachedResultName": "My Drive"
        },
        "options": {},
        "folderId": {
          "__rl": true,
          "mode": "list",
          "value": "1Zo4OFCv1qWRX1jo0VL_iqUBf4v0fZEXe",
          "cachedResultUrl": "{{ $env.WEBHOOK_URL }}",
          "cachedResultName": "CSV Exports"
        },
        "authentication": "{{ $credentials.serviceAccount }}"
      },
      "credentials": {
        "googleApi": {
          "id": "axkK6IN61bEAT6GM",
          "name": "Google Service Account account"
        }
      },
      "typeVersion": 3,
      "notes": "This googleDrive node performs automated tasks as part of the workflow."
    },
    {
      "id": "5dd5771f-6ccb-47ab-acbb-d6cbec60d22b",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        220,
        -40
      ],
      "parameters": {
        "width": 589.0376569037658,
        "height": 163.2468619246862,
        "content": "## How to extract PDF and image text into CSV using n8n (without manual data entry)\n\nThis workflow will extract text data from PDF and images, then store it as CSV.\n\n[💡 You can read more about this workflow here]({{ $env.WEBHOOK_URL }}"
      },
      "typeVersion": 1,
      "notes": "This stickyNote node performs automated tasks as part of the workflow."
    },
    {
      "id": "37416630-9b52-4ce6-98d0-1bdd39ff0d6b",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        160,
        160
      ],
      "parameters": {
        "color": 4,
        "width": 248.11715481171547,
        "height": 432.7364016736402,
        "content": "## Get PDF or image\nYou need to create a new folder inside Google Drive for uploading your PDF and images.\n\nOnce you create a folder, you need to add your Google cloud user by going to Share -> Add user. The user email should be like: n8n-server@n8n-server-435232.iam.gserviceaccount.com"
      },
      "typeVersion": 1,
      "notes": "This stickyNote node performs automated tasks as part of the workflow."
    },
    {
      "id": "3ab10f17-de8f-4263-aef8-cc2fb090ffe5",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1120,
        52.864368048917754
      ],
      "parameters": {
        "color": 5,
        "height": 446.3929762816575,
        "content": "## Send to Openrouter\nYou need to set up an Openrouter account to use this. It sends the data to openrouter to extract text.\n\nUse Header Auth. Name is \"Authorization\" and value is \"Bearer {API token}\"."
      },
      "typeVersion": 1,
      "notes": "This stickyNote node performs automated tasks as part of the workflow."
    },
    {
      "id": "e966f95c-c54e-4d11-895d-d5f75c53aca5",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        920,
        540
      ],
      "parameters": {
        "color": 6,
        "width": 399.0962343096232,
        "height": 517.154811715481,
        "content": "## Vertex AI for image recogniztion\nWe send the photo to Vertex AI to extract text. You'll need to activate Vertex AI and add the correct rights to your Google cloud credentials. \n- Enable Vertex API\n- Add vertex to user account"
      },
      "typeVersion": 1,
      "notes": "This stickyNote node performs automated tasks as part of the workflow."
    },
    {
      "id": "daa3ab66-fa14-4792-96d0-3bcbeffd5d60",
      "name": "Vertex A.I. extract text",
      "type": "n8n-nodes-base.noOp",
      "position": [
        980,
        740
      ],
      "parameters": {
        "text": "=Extract the transactions from the image",
        "messages": {
          "messageValues": [
            {
              "message": "=You are given a screenshot of payment transactions. Read the image and export all the transactions as CSV. Add a column called category and based on the information assign a category name. Return only the CSV data starting with the header row."
            },
            {
              "type": "HumanMessagePromptTemplate",
              "messageType": "imageBinary"
            }
          ]
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 1.4,
      "notes": "This chainLlm node performs automated tasks as part of the workflow."
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1",
    "saveManualExecutions": true,
    "callerPolicy": "workflowsFromSameOwner",
    "errorWorkflow": null,
    "timezone": "UTC",
    "executionTimeout": 3600,
    "maxExecutions": 1000,
    "retryOnFail": true,
    "retryCount": 3,
    "retryDelay": 1000
  },
  "versionId": "80635382-3d1c-4e46-a753-84b033cfc3a7",
  "connections": {
    "6549c335-e749-4b95-b77d-096a5e77af5e": {
      "main": [
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-7f9eb0d0",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-bdf4abd3",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-4406bef7",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-e8296f0e",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-ec311837",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-ea64d1d0",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-20900edf",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "error-handler-6549c335-e749-4b95-b77d-096a5e77af5e-8c1e0a63",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f60ef5f9-bc08-4cc9-804e-697ae6f88b9b": {
      "main": [
        [
          {
            "node": "error-handler-f60ef5f9-bc08-4cc9-804e-697ae6f88b9b-8d5a542d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "81d3f7b8-20cb-4aac-82a9-d4e8e6581105": {
      "main": [
        [
          {
            "node": "error-handler-81d3f7b8-20cb-4aac-82a9-d4e8e6581105-fa61bc62",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f62b71e5-af17-4f85-abff-7cee5100affc": {
      "main": [
        [
          {
            "node": "error-handler-f62b71e5-af17-4f85-abff-7cee5100affc-5c393443",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "fa99fbcf-1353-410d-a0db-48cea1178a76": {
      "main": [
        [
          {
            "node": "error-handler-fa99fbcf-1353-410d-a0db-48cea1178a76-059c8c87",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "e4979746-44bb-493e-b5eb-f9646b510888": {
      "main": [
        [
          {
            "node": "error-handler-e4979746-44bb-493e-b5eb-f9646b510888-e5198170",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "42341f03-c9fc-4290-963e-1a723202a739": {
      "main": [
        [
          {
            "node": "error-handler-42341f03-c9fc-4290-963e-1a723202a739-cb9ede58",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "bb446447-3f46-47e7-96a2-3fc720715828": {
      "main": [
        [
          {
            "node": "error-handler-bb446447-3f46-47e7-96a2-3fc720715828-41b91e98",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "843bc9c1-79a6-4f42-b9ee-fbec5f30b18d": {
      "main": [
        [
          {
            "node": "error-handler-843bc9c1-79a6-4f42-b9ee-fbec5f30b18d-45e967c5",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "6404bf65-3a7e-4be9-9b7f-98a23dca2ffd": {
      "main": [
        [
          {
            "node": "error-handler-6404bf65-3a7e-4be9-9b7f-98a23dca2ffd-9081d9cb",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "description": "Automated workflow: Extract text from PDF and image using Vertex AI (Gemini) into CSV. This workflow integrates 10 different services: convertToFile, stickyNote, httpRequest, googleDriveTrigger, lmChatGoogleGemini. It contains 27 nodes and follows best practices for error handling and security.",
  "notes": "Excellent quality workflow: Extract text from PDF and image using Vertex AI (Gemini) into CSV. This workflow has been optimized for production use with comprehensive error handling, security, and documentation."
}