Automate PDF Image Extraction & Analysis with GPT-4o and Google Drive

{
  "id": "NDCN2arRu5tLuP61",
  "meta": {
    "instanceId": "36147281c0732d54779505fe69cf0516d4b8760fdbbc308b1950e452edcf85e8",
    "templateCredsSetupCompleted": true
  },
  "name": "Automate PDF Image Extraction & Analysis with GPT-4o and Google Drive",
  "tags": [],
  "nodes": [
    {
      "id": "78bb478a-721d-433f-a615-8f131ef1d87f",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -1180,
        140
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "b1c2e97b-3539-4e16-89df-434a34c6a243",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -740,
        -440
      ],
      "parameters": {
        "color": 3,
        "width": 360,
        "height": 480,
        "content": "###  Setup
1.Set up your credentials when you first open the workflow. You’ll need accounts for OpenAI, Convert API, and Google Drive.
2.Convert API does not rate-limit your API, sometimes you may receive 503 service unavailable error.
Nevertheless, it doesn’t mean that you cannot convert your file. It simply means that you should retry the conversion in a few seconds.
3.Upload a PDF with images to Google Drive.
4.Remove unnecessary parts and retrieve image-related information.
5.Integrate image and image analysis information together.
6.Analyze each image using the OPENAI GPT-4o model.
7.Retrieve all image analysis content and image URL
8.Integrate multiple image URLs and analysis content
9.Output content to a .txt file.

Template was created in n8n v1.83.2"
      },
      "typeVersion": 1
    },
    {
      "id": "3b2a81eb-19b4-4685-90a3-1b4096b2d3b7",
      "name": "Get pdf file",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -1000,
        40
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "list",
          "value": "1WoqaMgaCD-gChGWUqPRJ7-pxbTozEuXN",
          "cachedResultUrl": "https://drive.google.com/file/d/1WoqaMgaCD-gChGWUqPRJ7-pxbTozEuXN/view?usp=drivesdk",
          "cachedResultName": "Building Effective AI Agents _ Anthropic.pdf"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "nxqV58j7kOaLFzhj",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "89208aa8-37d8-424c-a936-52539a9bc7ee",
      "name": "Get all img_url",
      "type": "n8n-nodes-base.set",
      "position": [
        -520,
        160
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "7715e33a-c5cc-4a22-aa28-ac19a24bbd7c",
              "name": "url",
              "type": "string",
              "value": "={{ $json.Url }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "5c1ece53-1910-42d6-a1e4-bfa6d5a83fe9",
      "name": "Analyze image",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        -360,
        40
      ],
      "parameters": {
        "text": "Please analyze the video in detail and provide a thorough explanation",
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o",
          "cachedResultName": "GPT-4O"
        },
        "options": {},
        "resource": "image",
        "simplify": false,
        "imageUrls": "={{ $json.url }}",
        "operation": "analyze"
      },
      "credentials": {
        "openAiApi": {
          "id": "4wadssyBOfOAfo2P",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "9e09364d-fb82-4524-b6aa-b8a6040893ba",
      "name": "Extract pdf image",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -840,
        140
      ],
      "parameters": {
        "url": "https://v2.convertapi.com/convert/pdf/to/extract-images",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "contentType": "multipart-form-data",
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "StoreFile",
              "value": "true"
            },
            {
              "name": "ImageOutputFormat",
              "value": "jpg"
            },
            {
              "name": "File",
              "parameterType": "formBinaryData",
              "inputDataFieldName": "data"
            }
          ]
        },
        "genericAuthType": "httpHeaderAuth",
        "headerParameters": {
          "parameters": [
            {}
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "5hUN8DpheywQE5v6",
          "name": "convertapi extract image"
        }
      },
      "retryOnFail": true,
      "typeVersion": 4.2,
      "waitBetweenTries": 5000
    },
    {
      "id": "8fd6e8ae-bea1-4d7f-8599-7bf6f4eee9e5",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1080,
        280
      ],
      "parameters": {
        "color": 5,
        "width": 202,
        "height": 99,
        "content": "### You can exchange this with any trigger you like (*e.g. google drive trigger*)"
      },
      "typeVersion": 1
    },
    {
      "id": "b0ce7fdd-7328-49b2-8ec6-797205aa7ab5",
      "name": "Get image data",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        -680,
        40
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "Files"
      },
      "typeVersion": 1
    },
    {
      "id": "c5855876-41d9-46a4-bdec-e60effa116e8",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1060,
        -220
      ],
      "parameters": {
        "width": 300,
        "content": "### PDF Image Extraction and Analysis  with GPT-4o
This n8n workflow automates the process of extracting images from PDF files and analyzing them with AI, then compiling the results into a document."
      },
      "typeVersion": 1
    },
    {
      "id": "7cea9e1b-0094-4220-bdf6-f13ab795e394",
      "name": "Get image analyze content",
      "type": "n8n-nodes-base.set",
      "position": [
        -200,
        160
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "2868a5bd-86a8-4962-a867-b4a354276181",
              "name": "content",
              "type": "string",
              "value": "={{ $('Get all img_url').item.json.url }}
{{ $json.choices[0].message.content }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "de4b6fab-d086-4bf3-81fc-a6f7b7eac24b",
      "name": "Integrate all content to a a content",
      "type": "n8n-nodes-base.code",
      "position": [
        -40,
        40
      ],
      "parameters": {
        "jsCode": "const mergedContent = items.map(item => item.json.content).join('\n');

return [
  {
    json: {
      content: mergedContent
    }
  }
];
"
      },
      "typeVersion": 2
    },
    {
      "id": "e66f7c66-9096-4bf5-b1dc-02dafeaa62ee",
      "name": "Output content to a .txt file",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        140,
        140
      ],
      "parameters": {
        "options": {},
        "operation": "toText",
        "sourceProperty": "content"
      },
      "typeVersion": 1.1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "timezone": "Asia/Taipei",
    "callerPolicy": "workflowsFromSameOwner",
    "executionOrder": "v1"
  },
  "versionId": "4c2771a6-f532-4bfd-bb98-3eae8b0ee85a",
  "connections": {
    "Get pdf file": {
      "main": [
        [
          {
            "node": "Extract pdf image",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Analyze image": {
      "main": [
        [
          {
            "node": "Get image analyze content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get image data": {
      "main": [
        [
          {
            "node": "Get all img_url",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get all img_url": {
      "main": [
        [
          {
            "node": "Analyze image",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract pdf image": {
      "main": [
        [
          {
            "node": "Get image data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get image analyze content": {
      "main": [
        [
          {
            "node": "Integrate all content to a a content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Output content to a .txt file": {
      "main": [
        []
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Get pdf file",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Integrate all content to a a content": {
      "main": [
        [
          {
            "node": "Output content to a .txt file",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}