Gemini AIをベースにした画像データ抽出API

• •HTTP Webhookエンドポイント（n8nが自動生成）
• •ターゲットAPIの認証情報が必要な場合あり

{
  "id": "YKZBEx4DTf0KGEBR",
  "meta": {
    "instanceId": "f5267db717c7383a3924a6083f6b9950be64cf36e2b4e9421d42eb2121922a14"
  },
  "name": "Image-Based Data Extraction API using Gemini AI",
  "tags": [],
  "nodes": [
    {
      "id": "e3448003-5c62-4da6-8fcc-6817915dcbb8",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        40,
        40
      ],
      "webhookId": "18118afb-7fd2-47a5-a474-50813c5b20c8",
      "parameters": {
        "path": "data-extractor",
        "options": {},
        "responseMode": "responseNode"
      },
      "typeVersion": 2
    },
    {
      "id": "3682c6bf-3442-4fba-ab6c-ae29e361ef93",
      "name": "Webhook への応答",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [
        1180,
        40
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "bfa352d0-68a9-4f33-be54-254a5df22664",
      "name": "URLから画像を取得",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        280,
        40
      ],
      "parameters": {
        "url": "={{ $json.body.image_url }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "c6c8de12-08dc-42e8-9c0e-86e04c7cacc0",
      "name": "画像で Gemini API (Flash Lite) を呼び出す",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        760,
        40
      ],
      "parameters": {
        "url": "=https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-lite:generateContent",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"inlineData\": {\n            \"data\": \"{{$json.data1}}\",\n            \"mimeType\": \"image/jpeg\"\n          }\n        }\n      ]\n    },\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"check this\"\n        }\n      ]\n    }\n  ],\n  \"systemInstruction\": {\n    \"role\": \"user\",\n    \"parts\": [\n      {\n        \"text\": \"{{ $('Webhook').first().json.body.Requirement}}\"\n      }\n    ]\n  },\n  \"generationConfig\": {\n    \"temperature\": 1,\n    \"topK\": 40,\n    \"topP\": 0.95,\n    \"maxOutputTokens\": 8192,\n    \"responseMimeType\": \"application/json\",\n    \"responseSchema\": {\n      \"type\": \"object\",\n      \"properties\": {{ $('Webhook').first().json.body.properties.toJsonString()}}\n    }\n  }\n}\n",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "predefinedCredentialType",
        "nodeCredentialType": "googlePalmApi"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "MhMVz0OkKPSPX2Wn",
          "name": "Gemini API Srinivasan Online"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "06b0f807-aeba-44d6-bb1d-dfa1d50e1082",
      "name": "必要なデータのみ出力するようフィールドを編集",
      "type": "n8n-nodes-base.set",
      "position": [
        980,
        40
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "4a2f1343-4b5d-4de8-b04b-5640e0a38d27",
              "name": "result",
              "type": "string",
              "value": "={{ $json.candidates[0].content.parts[0].text.parseJson()}}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "8c69dba2-f67c-4f8b-be18-02a414fd2ead",
      "name": "付箋",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        20,
        280
      ],
      "parameters": {
        "color": 5,
        "width": 820,
        "height": 420,
        "content": "## Sample API Call (cURL) \n```\ncurl --request GET \\\n  --url https://your_domain.com/webhook/data-extractor \\\n  --data '{\n  \"image_url\":\"https://www.immihelp.com/nri/images/sample-pan-card-front.jpg\",\n  \"Requirement\":\"extract the details from the image\",\n  \"properties\": {\n        \"PAN Number\": {\n          \"type\": \"string\"\n        },\n        \"Name\": {\n          \"type\": \"string\"\n        },\n        \"Date of Birth\": {\n          \"type\": \"string\"\n        },\n        \"Valid\": {\n          \"type\": \"boolean\"\n        }\n      }\n}'\n```"
      },
      "typeVersion": 1
    },
    {
      "id": "8839f0d7-306f-4dc2-aca5-6ca529e1a2ff",
      "name": "付箋1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        20,
        740
      ],
      "parameters": {
        "color": 5,
        "width": 1240,
        "height": 140,
        "content": "## Sample Output\n```\n{\n  \"result\": \"{\\\"Date of Birth\\\":\\\"23/11/1974\\\",\\\"Name\\\":\\\"RAHUL GUPTA\\\",\\\"PAN Number\\\":\\\"ABCDE1234F\\\",\\\"Valid\\\":true}\"\n}\n```"
      },
      "typeVersion": 1
    },
    {
      "id": "df733e11-f194-4878-a514-47ddc9811281",
      "name": "付箋2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        40,
        -520
      ],
      "parameters": {
        "width": 940,
        "height": 440,
        "content": "## Convert the workflow into an Endpoint\n\nThis n8n workflow provides a ready-to-use API endpoint for extracting structured data from images. The API takes an image URL as input, processes it using an AI-powered OCR model, and returns relevant extracted details in a structured JSON format.\n\n- The workflow converts the image to base64 before processing.\n- It utilizes an AI-powered model (Gemini API) for text extraction.\n- The output is formatted to include only the required fields.\n- You can customize the extraction criteria by modifying the request parameters.\n- Supports integration with various applications for automated data entry and processing.\n\nIt can be used for various use cases, such as:\n\n- Document OCR (ID cards, invoices, receipts)\n- Text Extraction from Images\n- Automated Form Processing\n- Business Card Data Extraction\n\nSimply send a GET request with an image URL, define the extraction requirements, and receive structured JSON data in response.\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "aecf7331-6341-411e-8906-e42fc0ef264a",
      "name": "画像をbase64に変換",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        520,
        40
      ],
      "parameters": {
        "options": {
          "encoding": "ascii"
        },
        "operation": "binaryToPropery",
        "destinationKey": "data1"
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "b1fad586-998c-47ce-9921-e59527da029a",
  "connections": {
    "e3448003-5c62-4da6-8fcc-6817915dcbb8": {
      "main": [
        [
          {
            "node": "bfa352d0-68a9-4f33-be54-254a5df22664",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "bfa352d0-68a9-4f33-be54-254a5df22664": {
      "main": [
        [
          {
            "node": "aecf7331-6341-411e-8906-e42fc0ef264a",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "aecf7331-6341-411e-8906-e42fc0ef264a": {
      "main": [
        [
          {
            "node": "c6c8de12-08dc-42e8-9c0e-86e04c7cacc0",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "c6c8de12-08dc-42e8-9c0e-86e04c7cacc0": {
      "main": [
        [
          {
            "node": "06b0f807-aeba-44d6-bb1d-dfa1d50e1082",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "06b0f807-aeba-44d6-bb1d-dfa1d50e1082": {
      "main": [
        [
          {
            "node": "3682c6bf-3442-4fba-ab6c-ae29e361ef93",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}