✍️ Utiliser GPT-4o pour créer un agent IA de promotion de posts LinkedIn de blog
Ceci est unAI, Marketingworkflow d'automatisation du domainecontenant 13 nœuds.Utilise principalement des nœuds comme Set, Code, Ghost, Merge, GoogleSheets, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. ✍️ utilisationGPT-4ocréationblog推广LinkedIn帖文deAIagent
- •Informations d'identification Google Sheets API
- •Clé API OpenAI
Nœuds utilisés (13)
Catégorie
{
"meta": {
"instanceId": "=",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "4815105b-4175-45ad-85bc-07917de9526c",
"name": "Lors du clic sur 'Tester le workflow'",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-140,
-720
],
"parameters": {},
"typeVersion": 1
},
{
"id": "b8f2a706-4868-4f0d-99a1-c31e1f7022e3",
"name": "Agent IA",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1220,
-580
],
"parameters": {
"text": "=Article Title: {{ $json.title }}\nArticle Link: {{ $json.link }}\nArticle Content: {{ $json.clean_content }}",
"options": {
"systemMessage": "=You are a content marketing assistant. Based on the article metadata (ID, title) and cleaned content, generate a short LinkedIn promotional message for a professional audience.\n\nFollow this structure:\n\nStart with a hook that grabs attention (a bold insight, surprising fact, or thought-provoking question).\n\nBriefly summarize the article’s value — what readers will learn or gain from it.\n\nInclude a clear call-to-action encouraging readers to read the article.\n\nEnd with this author signature and invitation:\n“—\nSamir Saci\nSupply Chain Data Scientist & Founder of LogiGreen\n📩 Contact me: https://logi-green.com/contactus”\n\nUse a professional and engaging tone. Do not include hashtags or Markdown formatting."
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "ac1538f6-67ef-4fd0-b4a9-d44b49149e5f",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1160,
-420
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "bac79ecf-b92d-42ba-bb0f-f1e1f85ca1c9",
"name": "Nettoyer le HTML",
"type": "n8n-nodes-base.code",
"position": [
780,
-620
],
"parameters": {
"jsCode": "const htmlContent = $input.first().json.content;\n\nconst cleanText = htmlContent\n .replace(/<[^>]*>/g, '') // remove tags\n .replace(/\\s+/g, ' ') // normalize spaces\n .replace(/ /g, ' ') // decode common entity\n .trim();\n\nreturn [\n {\n json: {\n clean_content: cleanText\n }\n }\n];\n"
},
"typeVersion": 2
},
{
"id": "fa57b494-370a-4f37-bcbe-38ba6138da76",
"name": "Extraire les articles de blog",
"type": "n8n-nodes-base.ghost",
"position": [
80,
-720
],
"parameters": {
"limit": 3,
"options": {},
"operation": "getAll"
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "dc19b6a4-fa17-41b4-8f8c-352519f07569",
"name": "Extraire le contenu de la publication",
"type": "n8n-nodes-base.set",
"position": [
300,
-720
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "00b337cd-1c61-4f19-8c51-b76f3a8dece1",
"name": "id",
"type": "string",
"value": "={{ $json.id }}"
},
{
"id": "8d38f4bc-bca6-4343-8c5e-5d9fd9cbe178",
"name": "title",
"type": "string",
"value": "={{ $json.title }}"
},
{
"id": "c34ddd76-0db6-4225-82fa-04d5542f9c7c",
"name": "featured_image",
"type": "string",
"value": "={{ $json.feature_image }}"
},
{
"id": "c0f9593c-0d5a-4659-9e25-91b098318bd6",
"name": "excerpt",
"type": "string",
"value": "={{ $json.excerpt }}"
},
{
"id": "0d11d3d5-49f8-473a-8602-b49769f88005",
"name": "content",
"type": "string",
"value": "={{ $json.html }}"
},
{
"id": "ec89a00d-9d76-4594-a8ce-98aa177e6737",
"name": "link",
"type": "string",
"value": "={{ $json.url }}"
}
]
}
},
"notesInFlow": true,
"typeVersion": 3.4
},
{
"id": "45656e13-5f03-48f9-8422-0ea3993e3289",
"name": "Note adhésive 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-180,
-1080
],
"parameters": {
"color": 7,
"width": 200,
"height": 520,
"content": "### 1. Workflow Trigger\nThis workflow uses simple trigger.\n\n#### How to setup?\n*Nothing to do.*\n"
},
"typeVersion": 1
},
{
"id": "7b8c3c49-069f-464b-acd2-a1a047fb2138",
"name": "Note adhésive 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
40,
-1080
],
"parameters": {
"color": 7,
"width": 400,
"height": 520,
"content": "### 2. Extract Blog Posts Content\nThe Ghost node extracts all the posts of your blog with content and metadata. In the second node, we extract description, URL, content and features image url.\n\n#### How to setup?\n- **Ghost Account API**:\n 1. Add your Ghost Blog Account Credentials\n 2. Select the number of Blog Posts you want to collect\n [Learn more about the Ghost Node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.ghost)\n\n"
},
"typeVersion": 1
},
{
"id": "0a5e4045-7df2-4713-a475-509844c58344",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
-1080
],
"parameters": {
"color": 7,
"width": 1520,
"height": 800,
"content": "### 3. Generate a Linkedin Post for each Post with an AI Agent\nThis block loops through all the posts pulled by the Ghost Node, send the content to the AI agent that generates a Linkedin post. The results are combined and pulled in a Google Sheet.\n\n#### How to setup?\n- **AI Agent with the Chat Model**:\n 1. Add a **chat model** with the required credentials *(Example: Open AI 4o-mini)*\n 2. Adapt the system prompt with your **post signature** and additional points you want to add in your posts\n [Learn more about the AI Agent Node](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent)\n- **Record Long Break in the Google Sheet Node**:\n 1. Add your Google Sheet API credentials to access the Google Sheet file\n 2. Select the file using the list, an URL or an ID\n 3. Select the sheet in which you want to record your working sessions\n 4. Map the fields\n [Learn more about the Google Sheet Node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googlesheets)\n\n"
},
"typeVersion": 1
},
{
"id": "29b09c7f-c39c-414d-b9d5-897b0d540328",
"name": "Enregistrer les publications",
"type": "n8n-nodes-base.googleSheets",
"position": [
1840,
-480
],
"parameters": {
"columns": {
"value": {
"id": "={{ $json.id }}",
"title": "={{ $json.title }}",
"content": "={{ $json.content }}",
"excerpt": "={{ $json.excerpt }}",
"clean_content": "={{ $json.clean_content }}",
"linkedin_post": "={{ $json.output }}",
"featured_image": "={{ $json.featured_image }}"
},
"schema": [
{
"id": "id",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "id",
"defaultMatch": true,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "featured_image",
"type": "string",
"display": true,
"required": false,
"displayName": "featured_image",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "excerpt",
"type": "string",
"display": true,
"required": false,
"displayName": "excerpt",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "content",
"type": "string",
"display": true,
"required": false,
"displayName": "content",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "clean_content",
"type": "string",
"display": true,
"required": false,
"displayName": "clean_content",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "linkedin_post",
"type": "string",
"display": true,
"required": false,
"displayName": "linkedin_post",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "=",
"cachedResultName": "="
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "=",
"cachedResultUrl": "=",
"cachedResultName": "="
}
},
"notesInFlow": true,
"typeVersion": 4.5
},
{
"id": "6f1c58db-a4bf-421a-a182-8149dac28725",
"name": "Fusionner Linkedin",
"type": "n8n-nodes-base.merge",
"position": [
1600,
-720
],
"parameters": {
"mode": "combineBySql"
},
"notesInFlow": true,
"typeVersion": 3
},
{
"id": "ebae3ccc-2727-44d9-9309-320c7d8e8349",
"name": "Ajouter le HTML nettoyé",
"type": "n8n-nodes-base.merge",
"position": [
1020,
-720
],
"parameters": {
"mode": "combineBySql"
},
"notesInFlow": true,
"typeVersion": 3
},
{
"id": "d839ca8d-f898-4617-955f-9c6d9a5412b7",
"name": "Boucler sur les publications",
"type": "n8n-nodes-base.splitInBatches",
"position": [
580,
-720
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "7e759203-b524-4cc5-89df-5e113c800504",
"name": "Note adhésive 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-180,
-540
],
"parameters": {
"width": 660,
"height": 460,
"content": "### [📺Complete Tutorial](https://www.youtube.com/watch?v=Lhi6hV6rWEo)\n\n"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"b8f2a706-4868-4f0d-99a1-c31e1f7022e3": {
"main": [
[
{
"node": "6f1c58db-a4bf-421a-a182-8149dac28725",
"type": "main",
"index": 1
}
]
]
},
"bac79ecf-b92d-42ba-bb0f-f1e1f85ca1c9": {
"main": [
[
{
"node": "ebae3ccc-2727-44d9-9309-320c7d8e8349",
"type": "main",
"index": 1
}
]
]
},
"ebae3ccc-2727-44d9-9309-320c7d8e8349": {
"main": [
[
{
"node": "b8f2a706-4868-4f0d-99a1-c31e1f7022e3",
"type": "main",
"index": 0
},
{
"node": "6f1c58db-a4bf-421a-a182-8149dac28725",
"type": "main",
"index": 0
}
]
]
},
"6f1c58db-a4bf-421a-a182-8149dac28725": {
"main": [
[
{
"node": "29b09c7f-c39c-414d-b9d5-897b0d540328",
"type": "main",
"index": 0
}
]
]
},
"d839ca8d-f898-4617-955f-9c6d9a5412b7": {
"main": [
[],
[
{
"node": "bac79ecf-b92d-42ba-bb0f-f1e1f85ca1c9",
"type": "main",
"index": 0
},
{
"node": "ebae3ccc-2727-44d9-9309-320c7d8e8349",
"type": "main",
"index": 0
}
]
]
},
"29b09c7f-c39c-414d-b9d5-897b0d540328": {
"main": [
[
{
"node": "d839ca8d-f898-4617-955f-9c6d9a5412b7",
"type": "main",
"index": 0
}
]
]
},
"ac1538f6-67ef-4fd0-b4a9-d44b49149e5f": {
"ai_languageModel": [
[
{
"node": "b8f2a706-4868-4f0d-99a1-c31e1f7022e3",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"fa57b494-370a-4f37-bcbe-38ba6138da76": {
"main": [
[
{
"node": "dc19b6a4-fa17-41b4-8f8c-352519f07569",
"type": "main",
"index": 0
}
]
]
},
"dc19b6a4-fa17-41b4-8f8c-352519f07569": {
"main": [
[
{
"node": "d839ca8d-f898-4617-955f-9c6d9a5412b7",
"type": "main",
"index": 0
}
]
]
},
"4815105b-4175-45ad-85bc-07917de9526c": {
"main": [
[
{
"node": "fa57b494-370a-4f37-bcbe-38ba6138da76",
"type": "main",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Intelligence Artificielle, Marketing
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Samir Saci
@samirsaciAutomation, AI and Analytics for Supply Chain & Business Optimization Helping businesses streamline operations using n8n, AI agents, and data science to enhance efficiency and sustainability. Linkedin: www.linkedin.com/in/samir-saci
Partager ce workflow