Modérateur de commentaires Facebook
Avancé
Ceci est unAI Chatbot, Multimodal AIworkflow d'automatisation du domainecontenant 23 nœuds.Utilise principalement des nœuds comme If, Code, Merge, Notion, HttpRequest. utilisationNotionetGeminideFacebook评论AI审核器
Prérequis
- •Clé API Notion
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
- •Informations d'identification Facebook Graph API
- •Clé API Google Gemini
Nœuds utilisés (23)
Catégorie
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
"id": "oWTmtu5Euv0y5n13",
"meta": {
"instanceId": "7f1a0694161455be3a7e71f1e0dea04908b0376a1a81e3a0c1e5ac879d48f83a"
},
"name": "Facebook Comments Moderator",
"tags": [],
"nodes": [
{
"id": "01df470c-f637-4065-af99-291dc56f4796",
"name": "Agent IA",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1312,
224
],
"parameters": {
"text": "=You are a helpful, friendly, and empathetic customer support agent for [COMPANY_NAME], a [COMPANY_TYPE] company in [COUNTRY]. \n\nYour job is to read the customer's comment and reply in [TARGET_LANGUAGE] in a natural, unisex, and humanized way that feels warm and personal. \n\nGuidelines for your replies:\n- Always reply as if you are a [NATIONALITY] person talking naturally. \n- Keep the tone friendly, respectful, and caring. \n- Use short, conversational sentences (don't sound like a machine). \n- Mention [COMPANY_NAME] naturally when relevant. \n- Always write in a *unisex style*. \n- Match the *tone of the customer's comment*. \n- Never use [FORBIDDEN_EXPRESSIONS]. Always use [PREFERRED_EXPRESSIONS] instead. \n- The word \"[SPECIFIC_FORBIDDEN_WORD]\" is strictly forbidden. Never use it in replies. Always use \"[PREFERRED_ALTERNATIVE]\" or another [TARGET_LANGUAGE] greeting instead.\n\n Whenever the customer asks about products, prices, or descriptions, use the Knowledge Base \"\" {{ $('KB Arrange').item.json.knowledgeContext }}\"\" to look up the correct information **before replying**. \n If the Knowledge Base does not contain the answer, reply politely and naturally without inventing details. \n\nHere is the customer's comment: \n\"\"{{ \n $('Last Post Fetcher').first().json.data\n .sort((a, b) => new Date(b.created_time) - new Date(a.created_time))[0].message || \"\"\n}}\n\"\" \n\nNow generate a reply in [TARGET_LANGUAGE] only.\n",
"options": {},
"promptType": "define"
},
"typeVersion": 2.1
},
{
"id": "6c83bfa2-e7b6-4846-97c5-c21f62a6f56e",
"name": "Modèle de chat IA",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1232,
464
],
"parameters": {
"options": {
"temperature": 0.2
},
"modelName": "[AI_MODEL_NAME]"
},
"typeVersion": 1
},
{
"id": "189eb862-ad36-4ea4-992e-e5111a0767f3",
"name": "Déclencheur planifié",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-656,
224
],
"parameters": {
"rule": {
"interval": [
{
"field": "seconds",
"secondsInterval": 10
}
]
}
},
"typeVersion": 1.2
},
{
"id": "27f33e5c-06ac-44f0-a6e0-44c6f376ba82",
"name": "Fusion",
"type": "n8n-nodes-base.merge",
"position": [
336,
224
],
"parameters": {},
"typeVersion": 3.2
},
{
"id": "7a18fcb5-df50-46f6-a8aa-de653b070786",
"name": "Base de connaissances",
"type": "n8n-nodes-base.notion",
"position": [
80,
368
],
"parameters": {
"options": {},
"resource": "databasePage",
"operation": "getAll",
"returnAll": true,
"databaseId": {
"__rl": true,
"mode": "list",
"value": "[KNOWLEDGE_BASE_DATABASE_ID]",
"cachedResultUrl": "[KNOWLEDGE_BASE_URL]",
"cachedResultName": "Knowledge Base"
}
},
"typeVersion": 2.2
},
{
"id": "829dd83a-58f8-44cd-a961-a1a0e2bd5c6e",
"name": "Récupérateur de dernier post",
"type": "n8n-nodes-base.httpRequest",
"position": [
-240,
224
],
"parameters": {
"url": "=https://graph.facebook.com/v21.0/{{$json[\"data\"][0].id}}/comments?access_token=[FACEBOOK_ACCESS_TOKEN]",
"options": {},
"authentication": "predefinedCredentialType",
"nodeCredentialType": "facebookGraphApi"
},
"typeVersion": 4.2
},
{
"id": "eb84d700-a32e-43a3-b4a9-781274635bab",
"name": "Vérificateur d'ID de commentaire",
"type": "n8n-nodes-base.notion",
"position": [
80,
96
],
"parameters": {
"filters": {
"conditions": [
{
"key": "Comment ID|rich_text",
"condition": "equals",
"richTextValue": "={{ $('Last Post Fetcher').first().json.data .sort((a, b) => new Date(b.created_time) - new Date(a.created_time))[0].id }}"
}
]
},
"options": {},
"resource": "databasePage",
"operation": "getAll",
"databaseId": {
"__rl": true,
"mode": "list",
"value": "[PROCESSED_COMMENTS_DATABASE_ID]",
"cachedResultUrl": "[PROCESSED_COMMENTS_DATABASE_URL]",
"cachedResultName": "Processed Facebook Comments"
},
"filterType": "manual"
},
"typeVersion": 2.2,
"alwaysOutputData": true
},
{
"id": "b81bc886-a42c-4c7d-9e99-844340dc205d",
"name": "Organisateur de base de connaissances",
"type": "n8n-nodes-base.code",
"position": [
544,
224
],
"parameters": {
"jsCode": "// Get the Knowledge Base data from the Notion node\nconst kbPages = $input.all().map(item => item.json);\n\n// Helper function to extract text from Notion properties\nfunction extractText(property) {\n if (!property) return '';\n \n // Handle rich_text properties\n if (property.rich_text && property.rich_text.length > 0) {\n return property.rich_text[0].plain_text || '';\n }\n \n // Handle title properties\n if (property.title && property.title.length > 0) {\n return property.title[0].plain_text || '';\n }\n \n // Handle select properties\n if (property.select) {\n return property.select.name || '';\n }\n \n // Handle number properties\n if (property.number) {\n return property.number.toString();\n }\n \n return '';\n}\n\n// Create a linear array of knowledge base entries\nconst knowledgeArray = kbPages.map(page => {\n const properties = page.properties || {};\n \n // Extract information based on your actual Notion properties\n const productName = page.property_products || '';\n const price = page.property_prices || '';\n const description = page.property_description || '';\n const name = page.name || '';\n \n // Create a formatted knowledge entry\n const knowledgeEntry = {\n name: name,\n product: productName,\n price: price,\n description: description,\n // Create a searchable text string\n searchableText: [name, productName, price, description]\n .filter(Boolean)\n .join(' | ')\n };\n \n return knowledgeEntry;\n}).filter(entry => entry.name || entry.product); // Only include entries with names or products\n\n// Create a simple string array for easy searching\nconst knowledgeStrings = knowledgeArray.map(entry => \n `NAME: ${entry.name || 'N/A'}` +\n (entry.product ? ` | PRODUCT: ${entry.product}` : '') +\n (entry.price ? ` | PRICE: ${entry.price}` : '') +\n (entry.description ? ` | DESCRIPTION: ${entry.description}` : '')\n);\n\n// Output the processed data\nreturn [{\n json: {\n // Original data passthrough\n ...($input.first()?.json || {}),\n \n // Structured knowledge base data\n knowledgeBase: {\n entries: knowledgeArray,\n searchableStrings: knowledgeStrings,\n totalProducts: knowledgeArray.length\n },\n \n // Simple concatenated string for memory context\n knowledgeContext: knowledgeStrings.join('\\n\\n'),\n \n // Alternative: Create a more concise version for memory\n compactKnowledge: knowledgeArray.map(entry => \n `${entry.name || entry.product}: ${entry.description || 'No description'} (${entry.price || 'Price not available'})`\n ).join('\\n')\n }\n}];"
},
"typeVersion": 2
},
{
"id": "91e25c71-a594-4bdc-a33c-c66857b62751",
"name": "Conditionneur de nouveau commentaire",
"type": "n8n-nodes-base.if",
"position": [
784,
224
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "e566ada9-1a12-41b8-aa9a-55bb7e14a10c",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.property_comment_id }}",
"rightValue": ""
}
]
},
"looseTypeValidation": true
},
"typeVersion": 2.2
},
{
"id": "83aa9b95-6671-4813-90e8-3820202324e6",
"name": "Dernier commentaire",
"type": "n8n-nodes-base.facebookGraphApi",
"position": [
1024,
240
],
"parameters": {
"edge": "comments",
"node": "={{ \n $('Last Post Fetcher').first().json.data\n .sort((a, b) => new Date(b.created_time) - new Date(a.created_time))[0].id \n}}",
"options": {},
"graphApiVersion": "v23.0"
},
"typeVersion": 1
},
{
"id": "c0420da3-170b-4741-a71d-69998b34b13b",
"name": "Rédacteur de réponse",
"type": "n8n-nodes-base.facebookGraphApi",
"position": [
1712,
224
],
"parameters": {
"edge": "comments",
"node": "={{ \n $('Last Post Fetcher').first().json.data\n .sort((a, b) => new Date(b.created_time) - new Date(a.created_time))[0].id \n}}",
"options": {
"queryParameters": {
"parameter": [
{
"name": "message",
"value": "={{ $('AI Agent').first().json.output }}"
}
]
}
},
"graphApiVersion": "v23.0",
"httpRequestMethod": "POST"
},
"typeVersion": 1
},
{
"id": "15eb2020-9963-4ae8-adf4-445d5506ae07",
"name": "ID de commentaire vers base de données",
"type": "n8n-nodes-base.notion",
"position": [
1968,
224
],
"parameters": {
"options": {},
"resource": "databasePage",
"databaseId": {
"__rl": true,
"mode": "list",
"value": "[PROCESSED_COMMENTS_DATABASE_ID]",
"cachedResultUrl": "[PROCESSED_COMMENTS_DATABASE_URL]",
"cachedResultName": "Processed Facebook Comments"
},
"propertiesUi": {
"propertyValues": [
{
"key": "Comment ID|rich_text",
"textContent": "={{ $('Last Post Fetcher').first().json.data .sort((a, b) => new Date(b.created_time) - new Date(a.created_time))[0].id }}"
},
{
"key": "Response Status|status",
"statusValue": "Done"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "1cbe6d39-f106-4320-b9a0-7520e7ea4a17",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-512,
128
],
"parameters": {
"color": 4,
"width": 214,
"content": "Initiates the workflow by retrieving all posts from the specified Facebook Page via the Graph API."
},
"typeVersion": 1
},
{
"id": "db015463-5489-4b59-aca8-8f648a6dc40e",
"name": "Note adhésive 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-272,
128
],
"parameters": {
"color": 5,
"width": 176,
"content": "Processes the list of posts to isolate the most recently published one."
},
"typeVersion": 1
},
{
"id": "a3a44851-6263-47b0-bd4e-e1e931cd9033",
"name": "Note adhésive 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
0
],
"parameters": {
"color": 4,
"width": 256,
"content": "Queries a database to verify if the latest comment's unique ID has already been processed, preventing duplicate replies."
},
"typeVersion": 1
},
{
"id": "8d5f94d9-f8d1-44d5-baba-683c8d2d625e",
"name": "Note adhésive 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
16,
288
],
"parameters": {
"color": 5,
"width": 230,
"height": 192,
"content": "Fetches the complete, up-to-date product information and knowledge base from the connected Notion database."
},
"typeVersion": 1
},
{
"id": "a7c140a5-42cb-4709-a761-077ea5aacf4c",
"name": "Note adhésive 4",
"type": "n8n-nodes-base.stickyNote",
"position": [
448,
144
],
"parameters": {
"color": 5,
"content": "Transforms the raw knowledge base data into a structured and easily searchable format for the AI model."
},
"typeVersion": 1
},
{
"id": "2c1e6e91-6bf3-4b11-bc89-da414ee8709c",
"name": "Note adhésive 5",
"type": "n8n-nodes-base.stickyNote",
"position": [
720,
128
],
"parameters": {
"color": 4,
"width": 224,
"height": 192,
"content": " A conditional gate; it only allows the workflow to proceed if the comment is new"
},
"typeVersion": 1
},
{
"id": "2eee31fa-d437-4c18-9328-1f447b447d9a",
"name": "Note adhésive 6",
"type": "n8n-nodes-base.stickyNote",
"position": [
976,
144
],
"parameters": {
"color": 5,
"width": 208,
"content": "Extracts the full content and metadata of the most recent comment from the latest post."
},
"typeVersion": 1
},
{
"id": "8ce9e8cb-b20f-4efa-97b2-eba6e3c47ede",
"name": "Note adhésive 7",
"type": "n8n-nodes-base.stickyNote",
"position": [
1280,
112
],
"parameters": {
"color": 6,
"width": 288,
"height": 208,
"content": "The core processing unit. It analyzes the customer's comment, consults the knowledge base for factual responses, and generates a personalized, empathetic reply in the target language."
},
"typeVersion": 1
},
{
"id": "101a2030-dbd0-44af-8116-9bd1bf1a874d",
"name": "Note adhésive 8",
"type": "n8n-nodes-base.stickyNote",
"position": [
1616,
144
],
"parameters": {
"color": 4,
"content": "Takes the AI-generated response and posts it as a reply to the customer's comment on Facebook."
},
"typeVersion": 1
},
{
"id": "5104091f-7597-4413-a5b6-28da90821b66",
"name": "Note adhésive 9",
"type": "n8n-nodes-base.stickyNote",
"position": [
1888,
128
],
"parameters": {
"color": 5,
"width": 272,
"height": 208,
"content": " Logs the ID of the newly processed comment into the database to mark it as complete and prevent reprocessing in the future."
},
"typeVersion": 1
},
{
"id": "c2a5a6cb-79a4-4c7b-9475-4681b45bd3d3",
"name": "Récupérateur de posts",
"type": "n8n-nodes-base.httpRequest",
"position": [
-432,
224
],
"parameters": {
"url": "=https://graph.facebook.com/v21.0/[FACEBOOK_PAGE_ID]/posts?access_token=[FACEBOOK_ACCESS_TOKEN]\n",
"options": {},
"authentication": "predefinedCredentialType",
"nodeCredentialType": "facebookGraphApi"
},
"credentials": {
"facebookGraphApi": {
"id": "C41mPQIciSciFLKJ",
"name": "Facebook Graph account"
}
},
"typeVersion": 4.2
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "0e48350f-f5ab-4cdd-83e8-5b4b16974fdd",
"connections": {
"27f33e5c-06ac-44f0-a6e0-44c6f376ba82": {
"main": [
[
{
"node": "b81bc886-a42c-4c7d-9e99-844340dc205d",
"type": "main",
"index": 0
}
]
]
},
"01df470c-f637-4065-af99-291dc56f4796": {
"main": [
[
{
"node": "c0420da3-170b-4741-a71d-69998b34b13b",
"type": "main",
"index": 0
}
]
]
},
"b81bc886-a42c-4c7d-9e99-844340dc205d": {
"main": [
[
{
"node": "91e25c71-a594-4bdc-a33c-c66857b62751",
"type": "main",
"index": 0
}
]
]
},
"c0420da3-170b-4741-a71d-69998b34b13b": {
"main": [
[
{
"node": "15eb2020-9963-4ae8-adf4-445d5506ae07",
"type": "main",
"index": 0
}
]
]
},
"6c83bfa2-e7b6-4846-97c5-c21f62a6f56e": {
"ai_languageModel": [
[
{
"node": "01df470c-f637-4065-af99-291dc56f4796",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"c2a5a6cb-79a4-4c7b-9475-4681b45bd3d3": {
"main": [
[
{
"node": "829dd83a-58f8-44cd-a961-a1a0e2bd5c6e",
"type": "main",
"index": 0
}
]
]
},
"7a18fcb5-df50-46f6-a8aa-de653b070786": {
"main": [
[
{
"node": "27f33e5c-06ac-44f0-a6e0-44c6f376ba82",
"type": "main",
"index": 1
}
]
]
},
"83aa9b95-6671-4813-90e8-3820202324e6": {
"main": [
[
{
"node": "01df470c-f637-4065-af99-291dc56f4796",
"type": "main",
"index": 0
}
]
]
},
"189eb862-ad36-4ea4-992e-e5111a0767f3": {
"main": [
[
{
"node": "c2a5a6cb-79a4-4c7b-9475-4681b45bd3d3",
"type": "main",
"index": 0
}
]
]
},
"eb84d700-a32e-43a3-b4a9-781274635bab": {
"main": [
[
{
"node": "27f33e5c-06ac-44f0-a6e0-44c6f376ba82",
"type": "main",
"index": 0
}
]
]
},
"829dd83a-58f8-44cd-a961-a1a0e2bd5c6e": {
"main": [
[
{
"node": "eb84d700-a32e-43a3-b4a9-781274635bab",
"type": "main",
"index": 0
},
{
"node": "7a18fcb5-df50-46f6-a8aa-de653b070786",
"type": "main",
"index": 0
}
]
]
},
"91e25c71-a594-4bdc-a33c-c66857b62751": {
"main": [
[],
[
{
"node": "83aa9b95-6671-4813-90e8-3820202324e6",
"type": "main",
"index": 0
}
]
]
}
}
}Foire aux questions
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 ?
Avancé - Chatbot IA, IA Multimodale
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
Webhook et modèle de message pour le modérateur Facebook
Assistant pour les commentaires et messages privés de Facebook (intégration Notion) alimenté par Gemini
If
Set
Code
+
If
Set
Code
23 NœudsAbdullah Alshiekh
Chatbot IA
Pouls des forums Telegram : surveillance communautaire avec les modèles d'IA Gemini et Groq
Pouls des forums Telegram : surveillance de la communauté avec Gemini et les modèles d'IA Groq
If
Set
Code
+
If
Set
Code
59 NœudsNguyen Thieu Toan
Divers
Agrégation de contenu
Automatiser la publication de publications sur les réseaux sociaux à partir d'articles de site web vers LinkedIn et X/Twitter avec Gemini AI
If
Set
Xml
+
If
Set
Xml
34 NœudsVadim
Création de contenu
Cashback JotForm (modèle)
utilisation JotForm、Gemini 2.5 et Notion deautomatisation返现收据traitement
If
Code
Gmail
+
If
Code
Gmail
25 NœudsAbdullah Alshiekh
Résumé sportif quotidien
Utiliser Google Gemini, Kokoro TTS et FFmpeg pour convertir des sources RSS en podcasts
If
Set
Code
+
If
Set
Code
34 NœudsJonas
Création de contenu
Assistant scraper pour la recherche de biens immobiliers
Utiliser PropertyFinder.ae, OpenRouter et SerpAPI pour répondre aux questions sur l'immobilier via l'IA
If
Set
Code
+
If
Set
Code
18 NœudsGeorge Zargaryan
Divers
Informations sur le workflow
Niveau de difficulté
Avancé
Nombre de nœuds23
Catégorie2
Types de nœuds10
Description de la difficulté
Auteur
Abdullah Alshiekh
@abdullah01🚀 Automation pro building AI-powered workflows with n8n. 💼 Special focus on real use cases 🔧 Love clean, flexible, and business-ready automations.
Liens externes
Voir sur n8n.io →
Partager ce workflow