ビング・データとGemini AIを使ってBing Copilot検索結果を抽出・要約
上級
これはAI分野の自動化ワークフローで、19個のノードを含みます。主にIf, Set, Wait, 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。 Gemini AIとBright Dataを使ってBing Copilot検索性別結果を抽出し、要約する
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 (19)
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
{
"id": "AnbedV2Ntx97sfed",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "Extract & Summarize Bing Copilot Search Results with Gemini AI and Bright Data",
"tags": [
{
"id": "Kujft2FOjmOVQAmJ",
"name": "Engineering",
"createdAt": "2025-04-09T01:31:00.558Z",
"updatedAt": "2025-04-09T01:31:00.558Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
}
],
"nodes": [
{
"id": "5f358132-63bd-4c66-80da-4fb9911f607f",
"name": "ワークフローをクリックしてテスト",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-1140,
400
],
"parameters": {},
"typeVersion": 1
},
{
"id": "43a157f6-2fb8-4c90-bf5d-92fc64c9df10",
"name": "Google Gemini チャットモデル",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"notes": "Gemini Experimental Model",
"position": [
760,
580
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-thinking-exp-01-21"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "f2d34617-ea34-4163-b9d5-a35fed807dbb",
"name": "デフォルトデータローダー",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
940,
580
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "707fdb4a-f534-4984-b97d-1839db1afc03",
"name": "再帰的文字テキストスプリッター",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1040,
800
],
"parameters": {
"options": {},
"chunkOverlap": 100
},
"typeVersion": 1
},
{
"id": "0440b1dd-ca72-467c-a27a-76609ae08fcf",
"name": "条件分岐",
"type": "n8n-nodes-base.if",
"position": [
-220,
400
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "6a7e5360-4cb5-4806-892e-5c85037fa71c",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $('Check Snapshot Status').item.json.status }}",
"rightValue": "ready"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "a23f3c86-200a-4d3c-a762-51cce158c4dd",
"name": "スナップショットID設定",
"type": "n8n-nodes-base.set",
"position": [
-700,
400
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "2c3369c6-9206-45d7-9349-f577baeaf189",
"name": "snapshot_id",
"type": "string",
"value": "={{ $json.snapshot_id }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "cee238ff-f725-4a24-8117-540be1c66a56",
"name": "スナップショットダウンロード",
"type": "n8n-nodes-base.httpRequest",
"position": [
140,
200
],
"parameters": {
"url": "=https://api.brightdata.com/datasets/v3/snapshot/{{ $json.snapshot_id }}",
"options": {
"timeout": 10000
},
"sendQuery": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"queryParameters": {
"parameters": [
{
"name": "format",
"value": "json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "kdbqXuxIR8qIxF7y",
"name": "Header Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "6bb33d11-7176-4dc7-89fe-1ee794793d3e",
"name": "Google Gemini チャットモデル1",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
380,
380
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "b2309938-eaaf-4d63-b8c8-53666cd57dac",
"name": "構造化出力パーサー",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
540,
380
],
"parameters": {
"jsonSchemaExample": "[{\n \"city\": \"string\",\n \"hotels\": [\n {\n \"name\": \"string\",\n \"address\": \"string\",\n \"description\": \"string\",\n \"website\": \"string\",\n \"area\": \"string (optional)\"\n }\n ]\n}\n]\n"
},
"typeVersion": 1.2
},
{
"id": "747b1e50-1cae-4efb-86d3-9221438701cd",
"name": "エラー確認",
"type": "n8n-nodes-base.if",
"position": [
-20,
20
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b267071c-7102-407b-a98d-f613bcb1a106",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.errors.toString() }}",
"rightValue": "0"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "0bf63795-1f1d-4d6b-90c1-1effae83fd40",
"name": "付箋ノート",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1140,
80
],
"parameters": {
"width": 400,
"height": 220,
"content": "## Note\n\nDeals with the Bing Copilot Search using the Bright Data Web Scraper API.\n\nThe Basic LLM Chain and summarization is done to demonstrate the usage of the N8N AI capabilities.\n\n**Please make sure to update the Webhook Notification URL**"
},
"typeVersion": 1
},
{
"id": "3872fb7a-382a-446d-8cb0-6ac5a282a801",
"name": "付箋ノート1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-620,
80
],
"parameters": {
"width": 420,
"height": 220,
"content": "## LLM Usages\n\nGoogle Gemini Flash Exp model is being used.\n\nBasic LLM Chain makes use of the Output formatter for formatting the response\n\nSummarization Chain is being used for summarization of the content"
},
"typeVersion": 1
},
{
"id": "a1453c72-fef3-4cec-967a-858b28ba31d8",
"name": "スナップショットステータス確認",
"type": "n8n-nodes-base.httpRequest",
"position": [
-460,
400
],
"parameters": {
"url": "=https://api.brightdata.com/datasets/v3/progress/{{ $json.snapshot_id }}",
"options": {},
"sendHeaders": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "kdbqXuxIR8qIxF7y",
"name": "Header Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "5750853b-a07d-455e-b630-977dd733613e",
"name": "構造化データ抽出器",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
360,
200
],
"parameters": {
"text": "=Extract the content as a structured JSON.\n\nHere's the content - {{ $json.answer_text }}",
"messages": {
"messageValues": [
{
"message": "You are an expert data formatter"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.6
},
{
"id": "a86f935f-fe57-40ea-9197-5f20e3002899",
"name": "簡潔な要約作成器",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
760,
200
],
"parameters": {
"options": {
"summarizationMethodAndPrompts": {
"values": {
"prompt": "=Write a concise summary of the following:\n\n\n{{ $('Download Snapshot').item.json.answer_text }}\n\n",
"combineMapPrompt": "=Write a concise summary of the following:\n\n\n\n\n\nCONCISE SUMMARY: {{ $('Download Snapshot').item.json.answer_text }}"
}
}
},
"operationMode": "documentLoader"
},
"typeVersion": 2
},
{
"id": "848ce4b1-0aed-4af2-bf55-bcdb30bbc88a",
"name": "30秒待機",
"type": "n8n-nodes-base.wait",
"position": [
-280,
660
],
"webhookId": "f2aafd71-61f2-4aa4-8290-fa3bbe3d46b9",
"parameters": {
"amount": 30
},
"typeVersion": 1.1
},
{
"id": "5467a870-0734-457b-909e-be425a432ebf",
"name": "構造化データ Webhook 通知器",
"type": "n8n-nodes-base.httpRequest",
"position": [
760,
0
],
"parameters": {
"url": "https://webhook.site/bc804ce5-4a45-4177-a68a-99c80e5c86e6",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "response",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "bf8a4868-ead7-411e-97ba-9faea308d836",
"name": "要約 Webhook 通知器",
"type": "n8n-nodes-base.httpRequest",
"position": [
1140,
200
],
"parameters": {
"url": "https://webhook.site/bc804ce5-4a45-4177-a68a-99c80e5c86e6",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "response",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "60a59b93-9a7c-4d22-ab66-2249fb9ed27e",
"name": "Bing Copilotリクエスト実行",
"type": "n8n-nodes-base.httpRequest",
"position": [
-920,
400
],
"parameters": {
"url": "https://api.brightdata.com/datasets/v3/trigger",
"method": "POST",
"options": {},
"jsonBody": "[\n {\n \"url\": \"https://copilot.microsoft.com/chats\",\n \"prompt\": \"Top hotels in New York\"\n }\n]",
"sendBody": true,
"sendQuery": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"queryParameters": {
"parameters": [
{
"name": "dataset_id",
"value": "gd_m7di5jy6s9geokz8w"
},
{
"name": "include_errors",
"value": "true"
}
]
},
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "kdbqXuxIR8qIxF7y",
"name": "Header Auth account"
}
},
"typeVersion": 4.2
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "4462ae6e-4ecd-4f64-aad8-4aa9e65982b6",
"connections": {
"0440b1dd-ca72-467c-a27a-76609ae08fcf": {
"main": [
[
{
"node": "747b1e50-1cae-4efb-86d3-9221438701cd",
"type": "main",
"index": 0
}
],
[
{
"node": "848ce4b1-0aed-4af2-bf55-bcdb30bbc88a",
"type": "main",
"index": 0
}
]
]
},
"a23f3c86-200a-4d3c-a762-51cce158c4dd": {
"main": [
[
{
"node": "a1453c72-fef3-4cec-967a-858b28ba31d8",
"type": "main",
"index": 0
}
]
]
},
"cee238ff-f725-4a24-8117-540be1c66a56": {
"main": [
[
{
"node": "5750853b-a07d-455e-b630-977dd733613e",
"type": "main",
"index": 0
}
]
]
},
"747b1e50-1cae-4efb-86d3-9221438701cd": {
"main": [
[
{
"node": "cee238ff-f725-4a24-8117-540be1c66a56",
"type": "main",
"index": 0
}
]
]
},
"f2d34617-ea34-4163-b9d5-a35fed807dbb": {
"ai_document": [
[
{
"node": "a86f935f-fe57-40ea-9197-5f20e3002899",
"type": "ai_document",
"index": 0
}
]
]
},
"848ce4b1-0aed-4af2-bf55-bcdb30bbc88a": {
"main": [
[
{
"node": "a1453c72-fef3-4cec-967a-858b28ba31d8",
"type": "main",
"index": 0
}
]
]
},
"a1453c72-fef3-4cec-967a-858b28ba31d8": {
"main": [
[
{
"node": "0440b1dd-ca72-467c-a27a-76609ae08fcf",
"type": "main",
"index": 0
}
]
]
},
"a86f935f-fe57-40ea-9197-5f20e3002899": {
"main": [
[
{
"node": "bf8a4868-ead7-411e-97ba-9faea308d836",
"type": "main",
"index": 0
}
]
]
},
"43a157f6-2fb8-4c90-bf5d-92fc64c9df10": {
"ai_languageModel": [
[
{
"node": "a86f935f-fe57-40ea-9197-5f20e3002899",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"b2309938-eaaf-4d63-b8c8-53666cd57dac": {
"ai_outputParser": [
[
{
"node": "5750853b-a07d-455e-b630-977dd733613e",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"6bb33d11-7176-4dc7-89fe-1ee794793d3e": {
"ai_languageModel": [
[
{
"node": "5750853b-a07d-455e-b630-977dd733613e",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"5750853b-a07d-455e-b630-977dd733613e": {
"main": [
[
{
"node": "a86f935f-fe57-40ea-9197-5f20e3002899",
"type": "main",
"index": 0
},
{
"node": "5467a870-0734-457b-909e-be425a432ebf",
"type": "main",
"index": 0
}
]
]
},
"60a59b93-9a7c-4d22-ab66-2249fb9ed27e": {
"main": [
[
{
"node": "a23f3c86-200a-4d3c-a762-51cce158c4dd",
"type": "main",
"index": 0
}
]
]
},
"707fdb4a-f534-4984-b97d-1839db1afc03": {
"ai_textSplitter": [
[
{
"node": "f2d34617-ea34-4163-b9d5-a35fed807dbb",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"5f358132-63bd-4c66-80da-4fb9911f607f": {
"main": [
[
{
"node": "60a59b93-9a7c-4d22-ab66-2249fb9ed27e",
"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 - 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
Amazon製品の価格下落をBright Dataで抽出・要約・分析
Bright DataとGoogle GeminiでAmazonの価格下落情報を抽出・要約・分析
Set
Wait
Merge
+
Set
Wait
Merge
26 ノードRanjan Dailata
人工知能
Bright Data と Google Gemini を使用した LinkedIn から企業ストーリーの生成
Bright DataとGoogle Geminiを使ってLinkedInから企業のストーリー生成
If
Set
Wait
+
If
Set
Wait
19 ノードRanjan Dailata
営業
Bright Data、Gemini、Pinecone を使用して LLM 向けに AI 対応のベクトルデータセットを作成
Bright Data、Gemini、Pinecone を使用して LLM 向け AI 就緒のベクトルデータセットを作成
Set
Http Request
Manual Trigger
+
Set
Http Request
Manual Trigger
21 ノードRanjan Dailata
ビルディングブロック
Indeed社データスクレイピングとAirtable、Bright Data、Google Geminiの統合
Airtable、Bright Data、Google Geminiを用いたIndeedデータのスクレイピングと集約
If
Set
Wait
+
If
Set
Wait
19 ノードRanjan Dailata
人事
ビング・データとGoogle Geminiを使ってYelpの店舗口コミを抽出し、要約
Bright DataとGoogle Geminiを使ってYelpの商家レビューを抽出し、要約する
Set
Merge
Http Request
+
Set
Merge
Http Request
12 ノードRanjan Dailata
人工知能
Bright Data MCPとGoogle Geminiを使用した法の事例研究抽出ツール、データマイニングツール
Bright Data MCPとGoogle Geminiを使用した法のケーススタディ抽出データマイニングツール
Set
Code
Wait
+
Set
Code
Wait
22 ノードRanjan Dailata
人工知能
