AIによる計画、Linkup検索、GPT-5を使って研究支援記事を作成
上級
これはContent Creation, Miscellaneous, AI RAG, Multimodal 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Set, SplitOut, Aggregate, FormTrigger, HttpRequestなどのノードを使用。 AIによる計画、Linkup検索、GPT-5を使って研究支援記事を作成
前提条件
- •ターゲットAPIの認証情報が必要な場合あり
- •OpenAI API Key
使用ノード (19)
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
{
"nodes": [
{
"id": "954ed22b-db88-4708-82f8-63beed6317de",
"name": "新規記事フォーム",
"type": "n8n-nodes-base.formTrigger",
"position": [
-944,
-704
],
"webhookId": "61cdfeab-f3ce-4b9a-925b-63f813c267f9",
"parameters": {
"options": {},
"formTitle": "New article",
"formFields": {
"values": [
{
"fieldLabel": "Article title",
"placeholder": "10 ways to do Influencer Marketing in 2025",
"requiredField": true
},
{
"fieldLabel": "Article guidelines",
"placeholder": "Promote xyz and write in British English...",
"requiredField": true
}
]
},
"formDescription": "Fill in this form to trigger the generation of a new article."
},
"typeVersion": 2.3
},
{
"id": "4d44933f-1e99-46cf-919d-0942acb2ccb7",
"name": "フォーム値の準備",
"type": "n8n-nodes-base.set",
"position": [
-688,
-704
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "ec4734ed-654f-478a-ab90-91bfcee1e208",
"name": "Title",
"type": "string",
"value": "={{ $json['Article title'] }}"
},
{
"id": "c034402e-a7b9-4c91-aaed-f24a838c3d91",
"name": "Guidelines",
"type": "string",
"value": "={{ $json['Article guidelines'] }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "5553922c-69d4-4de7-8a07-a38c37238b50",
"name": "構造化出力パーサー",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-256,
-480
],
"parameters": {
"jsonSchemaExample": "[\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua, ut enim ad minim veniam?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur?\"\n }\n]"
},
"typeVersion": 1.2
},
{
"id": "2b5dee40-df1b-41cb-8691-bf43158ff50e",
"name": "GPT 5 mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-384,
-480
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-mini",
"cachedResultName": "gpt-5-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "dMiSy27YCK6c6rra",
"name": "Duv's OpenAI"
}
},
"typeVersion": 1.2
},
{
"id": "4e25660b-428e-416c-91a0-63cc04104196",
"name": "質問の分割",
"type": "n8n-nodes-base.splitOut",
"position": [
16,
-704
],
"parameters": {
"options": {},
"fieldToSplitOut": "output"
},
"typeVersion": 1
},
{
"id": "39c18e8e-5d8f-4f54-9b0c-009fa3f4b966",
"name": "質問のループ処理",
"type": "n8n-nodes-base.splitInBatches",
"position": [
272,
-720
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "924c6121-8fd7-413b-9a77-9b77054dd481",
"name": "GPT 5 chat",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
864,
-1056
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-5-chat-latest",
"cachedResultName": "gpt-5-chat-latest"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "dMiSy27YCK6c6rra",
"name": "Duv's OpenAI"
}
},
"typeVersion": 1.2
},
{
"id": "a9f80b58-8767-49ce-a1b3-b310a39f40dc",
"name": "記事結果",
"type": "n8n-nodes-base.set",
"position": [
1200,
-1280
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "d3b8c4bc-27d9-4d57-b8d6-3a40b84d7b7d",
"name": "Article",
"type": "string",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "a0c64516-6639-4164-8271-600a35a7eda2",
"name": "付箋",
"type": "n8n-nodes-base.stickyNote",
"position": [
544,
-720
],
"parameters": {
"color": 7,
"width": 224,
"height": 352,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nConnect your linkup.so credentials (adding your API key in the header or using \"generic credentials\" that you've stored for Linkup)."
},
"typeVersion": 1
},
{
"id": "04528097-0fdb-432d-9847-5741eef25624",
"name": "研究内容の統合",
"type": "n8n-nodes-base.aggregate",
"position": [
528,
-1072
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData",
"destinationFieldName": "Content to leverage"
},
"typeVersion": 1
},
{
"id": "45d07062-280c-41f4-a6ec-f1d50ce3ac22",
"name": "付箋1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1680,
-1008
],
"parameters": {
"width": 544,
"height": 752,
"content": "# AI Article Research & Writing Team\n\nThis workflow mimics a professional writing process to create high-quality, sourced articles. It doesn't just write; it plans, researches, and then drafts the content.\n\n## How it works\n1. **Plan:** An AI planner breaks your article topic into a series of sub-questions.\n2. **Research:** It uses **Linkup** to search the web for sourced insights on each sub-question.\n3. **Write:** A final AI writer composes the article based *only* on the sourced research, complete with hyperlinks.\n\n## How to use\n1. **Connect Linkup:** Add your Linkup API Key to the `Query Linkup for insights` node.\n2. **Connect AI Provider:** Connect your AI credentials to the two LLM nodes (we recommend a small model for planning and a large one for writing).\n3. **Run:** Use the form to enter a title and guidelines to generate your sourced article.\n\n\n\n*This template was created by Guillaume Duvernay*"
},
"typeVersion": 1
},
{
"id": "7fa303e2-3f58-4c34-b4ae-d7d17a4062b7",
"name": "付箋2",
"type": "n8n-nodes-base.stickyNote",
"position": [
176,
-848
],
"parameters": {
"color": 6,
"width": 976,
"height": 608,
"content": "## Retrieving insights from the web for each sub-question"
},
"typeVersion": 1
},
{
"id": "59d256ae-0dee-4e9a-aeef-d674f97473bb",
"name": "付箋3",
"type": "n8n-nodes-base.stickyNote",
"position": [
720,
-1440
],
"parameters": {
"color": 5,
"width": 368,
"height": 512,
"content": "## AI step writing the final article based on the insights and initial request"
},
"typeVersion": 1
},
{
"id": "61489602-8823-4dc7-87aa-16870a543dcc",
"name": "付箋4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-528,
-848
],
"parameters": {
"color": 6,
"width": 480,
"height": 608,
"content": "## Breaking down the topic into sub-questions"
},
"typeVersion": 1
},
{
"id": "653763b7-3438-4085-8888-fb332a6d3cd2",
"name": "付箋5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1024,
-832
],
"parameters": {
"color": 4,
"width": 272,
"height": 304,
"content": "## Fill in this form to request a new article"
},
"typeVersion": 1
},
{
"id": "148a3000-ed6b-42a9-9c18-d7595cc1b754",
"name": "Linkupからの洞察検索",
"type": "n8n-nodes-base.httpRequest",
"position": [
608,
-672
],
"parameters": {
"url": "https://api.linkup.so/v1/search",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "q",
"value": "=Find 5 specific and meaningful insights about the topic:\n\n\"{{ $json.question }}\" \n\nthat would strengthen an article paragraph. Each insight should be a concrete finding, statistic, research result, or illustrative example (not just generic background), and should come from a robust source."
},
{
"name": "depth",
"value": "standard"
},
{
"name": "outputType",
"value": "structured"
},
{
"name": "structuredOutputSchema",
"value": "={\n \"type\": \"object\",\n \"properties\": {\n \"insights\": {\n \"description\": \"A list of 5 insights about the topic\",\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"insight\": {\n \"description\": \"A one-sentence key insight, finding, or example about the topic\",\n \"type\": \"string\"\n },\n \"url\": {\n \"description\": \"The URL of the source where the insight is from\",\n \"type\": \"string\"\n },\n \"title\": {\n \"description\": \"The title of the page containing the insight\",\n \"type\": \"string\"\n }\n },\n \"required\": [\"insight\", \"url\", \"title\"]\n }\n }\n }\n}"
},
{
"name": "fromDate",
"value": "={{ \n $now\n .minus($json['News from last x days'], 'days')\n .startOf('day')\n .toISO()\n}}"
},
{
"name": "includeImages",
"value": "false"
}
]
},
"genericAuthType": "httpBearerAuth"
},
"credentials": {
"httpBearerAuth": {
"id": "W7AgeoVOv60DlvyS",
"name": "Linkup - web search AI"
}
},
"typeVersion": 4.2
},
{
"id": "1af07cce-2414-4cfb-9320-099fe697e9ae",
"name": "質問と洞察のフォーマット",
"type": "n8n-nodes-base.set",
"position": [
960,
-464
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "1e33a1f4-a1a2-4962-ac72-cc518d7ff043",
"name": "Question",
"type": "string",
"value": "={{ $('Loop Over Questions').item.json.question }}"
},
{
"id": "903bcf38-13dd-48fb-8eb3-83f7a232aa53",
"name": "Insights",
"type": "array",
"value": "={{ $json.insights }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7d217bf4-1209-4e0c-bdf8-0c4dce7b7f82",
"name": "研究質問の生成",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
-384,
-704
],
"parameters": {
"text": "=Content title: {{ $json.Title }}\n\nArticle guidelines: {{ $json.Guidelines }}\n\n",
"messages": {
"messageValues": [
{
"message": "=You will receive a content title and an angle. Return 3–5 non-overlapping questions in JSON array format that cover everything needed to write excellent content as it breaks down the topic into sub-questions.\n\nGuidelines: \n- Start with simple, short broad questions for example to define the terms (e.g., What is X?, Why is X important?, How to do X?). \n- Then move into more specific, advanced, or analytical questions. \n- Ensure questions together form a complete coverage of the topic. \n\n## Output format:\n\nYou'll return the questions in such a JSON ARRAY:\n\n[\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua, ut enim ad minim veniam?\"\n },\n {\n \"question\": \"Lorem ipsum dolor sit amet, consectetur?\"\n }\n]"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.5
},
{
"id": "083922d8-71ec-4f1f-9451-f5b18cbc0880",
"name": "AI出力の生成",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
784,
-1280
],
"parameters": {
"text": "=Article title:\n\n{{ $('Prepare form values').first().json.Title }}\n\nArticle guidelines:\n\n{{ $('Prepare form values').first().json.Guidelines }}\n\n\nInsighs to leverage:\n\nThis Q&Insights research provides high-quality insights, and sources for your content. Be sure to include source links in your output whenever a source was used.\n\n{{ JSON.stringify($json['Content to leverage'], null, 2) }}\n",
"messages": {
"messageValues": [
{
"message": "=# Role\n\nYour role is to write an article based on the request in the user message.\n\n# What the user message contains\n\nThe user message includes the article title, any guidelines to follow, and a comprehensive set of insights. These insights should be smoothly integrated within the article's content to fact-base it and ensure is qualitative through the leverage of multiple sources. \nInterate the source links smoothly as hyperlinks in the article.\n\n# How to write good articles\n\nYou excel at writing articles by making sure that they deliver value, are concise, seem like they are human-written, not using typical AI useless sentence formulations.\n\n# Your output format\n\nOutput only the full article.\n\n* Begin with a `# H1` title.\n* Use subheadings throughout the article."
}
]
},
"promptType": "define"
},
"typeVersion": 1.5
}
],
"connections": {
"924c6121-8fd7-413b-9a77-9b77054dd481": {
"ai_languageModel": [
[
{
"node": "083922d8-71ec-4f1f-9451-f5b18cbc0880",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"2b5dee40-df1b-41cb-8691-bf43158ff50e": {
"ai_languageModel": [
[
{
"node": "7d217bf4-1209-4e0c-bdf8-0c4dce7b7f82",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"954ed22b-db88-4708-82f8-63beed6317de": {
"main": [
[
{
"node": "4d44933f-1e99-46cf-919d-0942acb2ccb7",
"type": "main",
"index": 0
}
]
]
},
"39c18e8e-5d8f-4f54-9b0c-009fa3f4b966": {
"main": [
[
{
"node": "04528097-0fdb-432d-9847-5741eef25624",
"type": "main",
"index": 0
}
],
[
{
"node": "148a3000-ed6b-42a9-9c18-d7595cc1b754",
"type": "main",
"index": 0
}
]
]
},
"4d44933f-1e99-46cf-919d-0942acb2ccb7": {
"main": [
[
{
"node": "7d217bf4-1209-4e0c-bdf8-0c4dce7b7f82",
"type": "main",
"index": 0
}
]
]
},
"4e25660b-428e-416c-91a0-63cc04104196": {
"main": [
[
{
"node": "39c18e8e-5d8f-4f54-9b0c-009fa3f4b966",
"type": "main",
"index": 0
}
]
]
},
"083922d8-71ec-4f1f-9451-f5b18cbc0880": {
"main": [
[
{
"node": "a9f80b58-8767-49ce-a1b3-b310a39f40dc",
"type": "main",
"index": 0
}
]
]
},
"5553922c-69d4-4de7-8a07-a38c37238b50": {
"ai_outputParser": [
[
{
"node": "7d217bf4-1209-4e0c-bdf8-0c4dce7b7f82",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"148a3000-ed6b-42a9-9c18-d7595cc1b754": {
"main": [
[
{
"node": "1af07cce-2414-4cfb-9320-099fe697e9ae",
"type": "main",
"index": 0
}
]
]
},
"04528097-0fdb-432d-9847-5741eef25624": {
"main": [
[
{
"node": "083922d8-71ec-4f1f-9451-f5b18cbc0880",
"type": "main",
"index": 0
}
]
]
},
"7d217bf4-1209-4e0c-bdf8-0c4dce7b7f82": {
"main": [
[
{
"node": "4e25660b-428e-416c-91a0-63cc04104196",
"type": "main",
"index": 0
}
]
]
},
"1af07cce-2414-4cfb-9320-099fe697e9ae": {
"main": [
[
{
"node": "39c18e8e-5d8f-4f54-9b0c-009fa3f4b966",
"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 - コンテンツ作成, その他, AI RAG検索拡張, マルチモーダルAI
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
LookioとOpenAI GPTを使用して知識源から事実に基づく記事を作成
Lookio と OpenAI GPT を使って、知识源から基礎のな記事を作成する
Set
Split Out
Aggregate
+
Set
Split Out
Aggregate
19 ノードGuillaume Duvernay
コンテンツ作成
Super RAGとGPT-5を使用して知識源から事実に基づく記事を作成
Super RAG と GPT-5 を使って、知识源から基礎のな記事を作成する
Set
Split Out
Aggregate
+
Set
Split Out
Aggregate
19 ノードGuillaume Duvernay
AI RAG検索拡張
動のAIネットワークリサーチャー:プレーンTextからカスタムCSV
GPT-4とLinkupを活用したカスタムCSVへのテキスト変換を実現する動のAIウェブリサーチャー
Set
Code
Split Out
+
Set
Code
Split Out
16 ノードGuillaume Duvernay
その他
WordPressブログの自動化プロフェッショナル版(先端研究)v2.1マーケットプラグイン
GPT-4o、Perplexity AI、そして多言語対応を使ったSEO最適化ブログ作成の自動化
If
Set
Xml
+
If
Set
Xml
125 ノードDaniel Ng
コンテンツ作成
Lookio、Linkup、そして GPT-5 を使って二源エキスパート記事の作成
Lookio、Linkup、GPT-5 を使用して二来源の専門記事を作成
Set
Split Out
Aggregate
+
Set
Split Out
Aggregate
21 ノードGuillaume Duvernay
コンテンツジェネレーター v3
AI驱动ブログ自動化:使用GPT-4生成并公開SEO記事至WordPressとTwitter
If
Set
Code
+
If
Set
Code
144 ノードJay Emp0
コンテンツ作成