n8nでGemini AIを使って画像とPDFを5つの方法で処理
上級
これはBuilding Blocks, AI分野の自動化ワークフローで、28個のノードを含みます。主にSet, Filter, SplitOut, HttpRequest, ManualTriggerなどのノードを使用、AI技術を活用したスマート自動化を実現。 n8nでGemini AIを使って画像とPDFを処理する5つの方法
前提条件
- •ターゲットAPIの認証情報が必要な場合あり
- •Google Gemini API Key
使用ノード (28)
カテゴリー
ワークフロープレビュー
ノード接続関係を可視化、ズームとパンをサポート
ワークフローをエクスポート
以下のJSON設定をn8nにインポートして、このワークフローを使用できます
{
"meta": {
"instanceId": "d4d7965840e96e50a3e02959a8487c692901dfa8d5cc294134442c67ce1622d3",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "eec7d9b8-d1e3-4a43-9e0d-f6d750e736b5",
"name": "ワークフローテストをクリック",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-640,
-400
],
"parameters": {},
"typeVersion": 1
},
{
"id": "5276a2cf-3d42-409a-800d-9080aa5e1a09",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1820,
-60
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash"
},
"credentials": {
"googlePalmApi": {
"id": "BB5B0v4OaFQeEt3C",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "1b89dca9-1137-4e0f-b3ff-1b354152c128",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1880,
-260
],
"parameters": {
"text": "={{ $('Loop Over Items').all() }}",
"options": {
"passthroughBinaryImages": true
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "00348203-882f-48da-8127-e57cf30c5b20",
"name": "Unsplash2から画像を取得",
"type": "n8n-nodes-base.httpRequest",
"position": [
1160,
-280
],
"parameters": {
"url": "={{ $json.url }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "1b07777f-954b-4471-ab4b-070c902c0bc1",
"name": "分割出力",
"type": "n8n-nodes-base.splitOut",
"position": [
500,
-280
],
"parameters": {
"options": {},
"fieldToSplitOut": "urls"
},
"typeVersion": 1
},
{
"id": "3646a695-d63b-4e25-93b4-a208592e6eac",
"name": "Unsplash3から画像を取得",
"type": "n8n-nodes-base.httpRequest",
"position": [
720,
0
],
"parameters": {
"url": "={{ $json.urls }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "34ef745b-23c6-422d-9367-de79eeb54e77",
"name": "base64に変換",
"type": "n8n-nodes-base.extractFromFile",
"position": [
940,
0
],
"parameters": {
"options": {},
"operation": "binaryToPropery"
},
"typeVersion": 1
},
{
"id": "762507d2-2093-4ac8-a4d4-2972c53fa839",
"name": "Gemini API1を呼び出す",
"type": "n8n-nodes-base.httpRequest",
"position": [
1160,
0
],
"parameters": {
"url": "=https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent",
"method": "POST",
"options": {},
"jsonBody": "={\n \"contents\": [{\n \"parts\":[\n {\"text\": \"Whats on this image?\"},\n {\n \"inline_data\": {\n \"mime_type\": \"image/jpeg\",\n \"data\": \"{{ $json.data }}\"\n }\n }\n ]\n }]\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth"
},
"credentials": {
"httpQueryAuth": {
"id": "Eh1GI1UjOtJk4CDZ",
"name": "Query Gemini Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "0dfa7ae9-1eda-49ca-8067-c467346c27cb",
"name": "アイテムをループ処理",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1560,
-280
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "c5562d6b-0b56-4f15-bbd0-441359f89d86",
"name": "AI Agent2",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1560,
-700
],
"parameters": {
"text": "whats on the image",
"options": {
"passthroughBinaryImages": true
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "277c44ec-109b-4dfa-bc04-defec26e6581",
"name": "Google Gemini Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1500,
-540
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash"
},
"credentials": {
"googlePalmApi": {
"id": "BB5B0v4OaFQeEt3C",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "c303ab4e-155f-4c36-bf07-4825d0d1fd93",
"name": "Unsplash4から画像を取得",
"type": "n8n-nodes-base.httpRequest",
"position": [
1160,
-700
],
"parameters": {
"url": "=https://plus.unsplash.com/premium_photo-1740023685108-a12c27170d51?q=80&w=2340&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "b786ac03-75d0-4830-849f-ee9ed8e108fa",
"name": "PDFファイルを取得",
"type": "n8n-nodes-base.httpRequest",
"position": [
260,
360
],
"parameters": {
"url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "bb7ba59e-050a-4259-8238-dc25f458e3c4",
"name": "Unsplashから画像を取得",
"type": "n8n-nodes-base.httpRequest",
"position": [
260,
660
],
"parameters": {
"url": "=https://plus.unsplash.com/premium_photo-1740023685108-a12c27170d51?q=80&w=2340&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "65a4cb42-632b-4fbd-8e28-10e36e9f1e00",
"name": "PDFでGemini APIを呼び出す",
"type": "n8n-nodes-base.httpRequest",
"position": [
720,
360
],
"parameters": {
"url": "=https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent",
"method": "POST",
"options": {},
"jsonBody": "={\n \"contents\": [{\n \"parts\":[\n {\"text\": \"Whats on this pdf?\"},\n {\n \"inline_data\": {\n \"mime_type\": \"application/pdf\",\n \"data\": \"{{ $json.data }}\"\n }\n }\n ]\n }]\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth"
},
"credentials": {
"httpQueryAuth": {
"id": "Eh1GI1UjOtJk4CDZ",
"name": "Query Gemini Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "75a13a82-c051-449a-bf52-837256c18f22",
"name": "画像でGemini APIを呼び出す",
"type": "n8n-nodes-base.httpRequest",
"position": [
720,
660
],
"parameters": {
"url": "=https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent",
"method": "POST",
"options": {},
"jsonBody": "={\n \"contents\": [{\n \"parts\":[\n {\"text\": \"Whats on this image?\"},\n {\n \"inline_data\": {\n \"mime_type\": \"image/jpeg\",\n \"data\": \"{{ $json.data }}\"\n }\n }\n ]\n }]\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth"
},
"credentials": {
"httpQueryAuth": {
"id": "Eh1GI1UjOtJk4CDZ",
"name": "Query Gemini Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "55964e8d-ce0a-4157-b536-41862da946ab",
"name": "base64に変換（画像）",
"type": "n8n-nodes-base.extractFromFile",
"position": [
500,
660
],
"parameters": {
"options": {},
"operation": "binaryToPropery"
},
"typeVersion": 1
},
{
"id": "57fc92ee-2a74-4d49-ae7a-6c499a1f380e",
"name": "base64に変換（PDF）",
"type": "n8n-nodes-base.extractFromFile",
"position": [
500,
360
],
"parameters": {
"options": {},
"operation": "binaryToPropery"
},
"typeVersion": 1
},
{
"id": "dc0a5515-1a51-4a11-9b39-ac8b30bcb0ba",
"name": "複数画像URLを定義",
"type": "n8n-nodes-base.set",
"position": [
260,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "95f15b6e-f66a-450a-be19-75d4c339f943",
"name": "urls",
"type": "array",
"value": "=[\n \"https://plus.unsplash.com/premium_photo-1740023685108-a12c27170d51?q=80&w=2340&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D\",\n \"https://images.unsplash.com/photo-1739609579483-00b49437cc45?q=80&w=2342&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D\"\n]\n"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "4f9037a3-adc5-4ada-b977-6ecdf6f58705",
"name": "複数アイテムに分割出力",
"type": "n8n-nodes-base.splitOut",
"position": [
500,
0
],
"parameters": {
"options": {},
"fieldToSplitOut": "urls"
},
"typeVersion": 1
},
{
"id": "0e0bbf58-4c83-4769-9616-c120296ce5e0",
"name": "付箋",
"type": "n8n-nodes-base.stickyNote",
"position": [
-760,
-780
],
"parameters": {
"color": 5,
"width": 440,
"height": 340,
"content": "## When clicking \"Test workflow\"\n\nThis trigger demonstrates five different approaches to analyze media with AI:\n1. Top branch: Single image with automatic binary passthrough\n2. Second branch: Multiple images with custom prompts\n3. Third branch: Standard n8n item processing with direct API\n4. Fourth branch: PDF analysis via direct API\n5. Fifth branch: Image analysis via direct API\n\nEach approach has advantages depending on your use case.\n\n"
},
"typeVersion": 1
},
{
"id": "2a6236b2-c5a3-4feb-883a-b3654ce78278",
"name": "URLとプロンプトを定義",
"type": "n8n-nodes-base.set",
"position": [
260,
-280
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "95f15b6e-f66a-450a-be19-75d4c339f943",
"name": "urls",
"type": "array",
"value": "={{ \n[\n {\n url: \"https://plus.unsplash.com/premium_photo-1740023685108-a12c27170d51?q=80&w=2340&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D\",\n prompt: \"what is special about this image?\",\n process: true\n },\n {\n url: \"https://images.unsplash.com/photo-1739609579483-00b49437cc45?q=80&w=2342&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D\",\n prompt: \"what is the main color?\",\n process: true\n },\n {\n url: \"https://plus.unsplash.com/premium_photo-1740023685108-a12c27170d51?q=80&w=2340&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D\",\n prompt: \"test\", \n process: false\n }\n]\n}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "91dd2eec-3179-4c14-857e-bb65499723be",
"name": "付箋1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1920,
-700
],
"parameters": {
"color": 4,
"width": 440,
"height": 300,
"content": "## METHOD 1: Single image with automatic binary passthrough\n\nThis branch demonstrates the easiest way to analyze a single image with AI:\n1. Fetch an image from Unsplash\n2. Send directly to the AI Agent with \"Automatically Passthrough Binary Images\" enabled\n3. Get AI analysis without any data transformation\n\nBEST FOR: Quick implementation with minimal configuration for single image analysis.\n\n"
},
"typeVersion": 1
},
{
"id": "2b48f2d0-8c55-40da-acf5-0d9267691817",
"name": "フィルター（オプション）",
"type": "n8n-nodes-base.filter",
"position": [
720,
-280
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "51b55272-94af-4761-a42e-5c91f3b8e39e",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.process }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "f9f98d03-99c6-4424-b7cc-fd2ef836173b",
"name": "付箋2",
"type": "n8n-nodes-base.stickyNote",
"position": [
2220,
-260
],
"parameters": {
"color": 3,
"width": 460,
"height": 360,
"content": "## METHOD 2: Multiple images with custom prompts\n\nThis branch shows how to analyze different images with custom instructions:\n1. Prepare data structure with image URLs and their corresponding prompts\n2. Split into individual items and filter if needed\n3. Fetch each image from Unsplash\n4. Process sequentially through the Loop node\n5. Analyze each with its specific prompt using the AI Agent\n\nBEST FOR: When you need different analysis goals for each image (e.g., one for object detection, another for scene description).\n"
},
"typeVersion": 1
},
{
"id": "057ecbfa-3079-451f-9376-eefcdf4ab96a",
"name": "付箋3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1360,
0
],
"parameters": {
"color": 7,
"width": 360,
"height": 380,
"content": "## METHOD 3: Standard n8n item processing with direct API\n\nThis branch demonstrates n8n's standard approach to handling multiple items:\n1. Define multiple image URLs in a single node\n2. Split into individual items for processing\n3. Fetch each image individually\n4. Transform each to base64 format\n5. Make direct API calls to Gemini for each item\n\nBEST FOR: Processing multiple images using n8n's standard item-by-item approach with direct API control.\n\n"
},
"typeVersion": 1
},
{
"id": "3dfbde27-7141-4558-a958-00b2891274ec",
"name": "付箋4",
"type": "n8n-nodes-base.stickyNote",
"position": [
920,
360
],
"parameters": {
"width": 340,
"height": 280,
"content": "## METHOD 4: PDF analysis via direct API\n\nThis branch shows how to analyze PDF documents:\n1. Fetch a PDF file\n2. Transform to base64 format\n3. Send directly to Gemini API for analysis\n\nBEST FOR: Document analysis, text extraction, summarization of PDFs.\n"
},
"typeVersion": 1
},
{
"id": "f50dae19-77e4-4450-a516-7f0e676d161a",
"name": "付箋5",
"type": "n8n-nodes-base.stickyNote",
"position": [
920,
660
],
"parameters": {
"width": 340,
"height": 300,
"content": "## METHOD 5: Image analysis via direct API\n\nThis branch demonstrates direct API control for image analysis:\n1. Fetch an image\n2. Transform to base64 format\n3. Make a customized API call to Gemini\n\nBEST FOR: Advanced users who need precise control over API parameters and response handling.\n"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"1b89dca9-1137-4e0f-b3ff-1b354152c128": {
"main": [
[
{
"node": "0dfa7ae9-1eda-49ca-8067-c467346c27cb",
"type": "main",
"index": 0
}
]
]
},
"1b07777f-954b-4471-ab4b-070c902c0bc1": {
"main": [
[
{
"node": "2b48f2d0-8c55-40da-acf5-0d9267691817",
"type": "main",
"index": 0
}
]
]
},
"b786ac03-75d0-4830-849f-ee9ed8e108fa": {
"main": [
[
{
"node": "57fc92ee-2a74-4d49-ae7a-6c499a1f380e",
"type": "main",
"index": 0
}
]
]
},
"0dfa7ae9-1eda-49ca-8067-c467346c27cb": {
"main": [
[],
[
{
"node": "1b89dca9-1137-4e0f-b3ff-1b354152c128",
"type": "main",
"index": 0
}
]
]
},
"762507d2-2093-4ac8-a4d4-2972c53fa839": {
"main": [
[]
]
},
"2b48f2d0-8c55-40da-acf5-0d9267691817": {
"main": [
[
{
"node": "00348203-882f-48da-8127-e57cf30c5b20",
"type": "main",
"index": 0
}
]
]
},
"34ef745b-23c6-422d-9367-de79eeb54e77": {
"main": [
[
{
"node": "762507d2-2093-4ac8-a4d4-2972c53fa839",
"type": "main",
"index": 0
}
]
]
},
"2a6236b2-c5a3-4feb-883a-b3654ce78278": {
"main": [
[
{
"node": "1b07777f-954b-4471-ab4b-070c902c0bc1",
"type": "main",
"index": 0
}
]
]
},
"bb7ba59e-050a-4259-8238-dc25f458e3c4": {
"main": [
[
{
"node": "55964e8d-ce0a-4157-b536-41862da946ab",
"type": "main",
"index": 0
}
]
]
},
"00348203-882f-48da-8127-e57cf30c5b20": {
"main": [
[
{
"node": "0dfa7ae9-1eda-49ca-8067-c467346c27cb",
"type": "main",
"index": 0
}
]
]
},
"3646a695-d63b-4e25-93b4-a208592e6eac": {
"main": [
[
{
"node": "34ef745b-23c6-422d-9367-de79eeb54e77",
"type": "main",
"index": 0
}
]
]
},
"c303ab4e-155f-4c36-bf07-4825d0d1fd93": {
"main": [
[
{
"node": "c5562d6b-0b56-4f15-bbd0-441359f89d86",
"type": "main",
"index": 0
}
]
]
},
"5276a2cf-3d42-409a-800d-9080aa5e1a09": {
"ai_languageModel": [
[
{
"node": "1b89dca9-1137-4e0f-b3ff-1b354152c128",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"277c44ec-109b-4dfa-bc04-defec26e6581": {
"ai_languageModel": [
[
{
"node": "c5562d6b-0b56-4f15-bbd0-441359f89d86",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"57fc92ee-2a74-4d49-ae7a-6c499a1f380e": {
"main": [
[
{
"node": "65a4cb42-632b-4fbd-8e28-10e36e9f1e00",
"type": "main",
"index": 0
}
]
]
},
"dc0a5515-1a51-4a11-9b39-ac8b30bcb0ba": {
"main": [
[
{
"node": "4f9037a3-adc5-4ada-b977-6ecdf6f58705",
"type": "main",
"index": 0
}
]
]
},
"4f9037a3-adc5-4ada-b977-6ecdf6f58705": {
"main": [
[
{
"node": "3646a695-d63b-4e25-93b4-a208592e6eac",
"type": "main",
"index": 0
}
]
]
},
"55964e8d-ce0a-4157-b536-41862da946ab": {
"main": [
[
{
"node": "75a13a82-c051-449a-bf52-837256c18f22",
"type": "main",
"index": 0
}
]
]
},
"eec7d9b8-d1e3-4a43-9e0d-f6d750e736b5": {
"main": [
[
{
"node": "2a6236b2-c5a3-4feb-883a-b3654ce78278",
"type": "main",
"index": 0
},
{
"node": "dc0a5515-1a51-4a11-9b39-ac8b30bcb0ba",
"type": "main",
"index": 0
},
{
"node": "b786ac03-75d0-4830-849f-ee9ed8e108fa",
"type": "main",
"index": 0
},
{
"node": "bb7ba59e-050a-4259-8238-dc25f458e3c4",
"type": "main",
"index": 0
},
{
"node": "c303ab4e-155f-4c36-bf07-4825d0d1fd93",
"type": "main",
"index": 0
}
]
]
}
}
}よくある質問
このワークフローの使い方は？
上記のJSON設定コードをコピーし、n8nインスタンスで新しいワークフローを作成して「JSONからインポート」を選択、設定を貼り付けて認証情報を必要に応じて変更してください。
このワークフローはどんな場面に適していますか？
上級 - ビルディングブロック, 人工知能
有料ですか？
このワークフローは完全無料です。ただし、ワークフローで使用するサードパーティサービス（OpenAI APIなど）は別途料金が発生する場合があります。
関連ワークフロー
[テンプレート] AIペットショップ v8
AIペットショップアシスタント - GPT-4o、Googleカレンダー、WhatsApp/Instagram/Facebookを統合
If
N8n
Set
+
If
N8n
Set
244 ノードAmanda Benks
営業
納税申告アシスタントの構築：Qdrant、Mistral.ai、OpenAIを使用
税務法アシスタントをQdrant、Mistral.ai、OpenAIで構築
Set
Wait
Filter
+
Set
Wait
Filter
38 ノードJimleuk
財務
正規表現と AI を使って隠れたウェブサイトの API エンドポイントを発見
正規表現とAIを使って隠れたウェブサイトのAPIエンドポイントを発見する
If
Set
Html
+
If
Set
Html
58 ノードYulia
エンジニアリング
n8nノードの探索（可視化リファレンスライブラリ内）
n8nノードを可視化リファレンスライブラリで探索
If
Ftp
Set
+
If
Ftp
Set
113 ノードI versus AI
その他
HN求人広告スクレイピング
Hacker News採用情報のスクレイピングと解析
Set
Code
Limit
+
Set
Code
Limit
20 ノードJulian Kaiser
人事
APIアーキテクチャ抽出ツール
APIアーキテクチャ抽出器
If
Set
Code
+
If
Set
Code
88 ノードPolina Medvedieva
エンジニアリング
ワークフロー情報
難易度
上級
ノード数28
カテゴリー2
ノードタイプ10
作成者
Julian Kaiser
@jksrFull Stack Developer turned AI & Automation Engineer, implementing intelligent solutions with custom code, LLMs & n8n. Use my link to book a consultation on automating your business processes.
外部リンク
n8n.ioで表示 →
このワークフローを共有