Assistant Telegram
Ceci est unContent Creation, Multimodal AIworkflow d'automatisation du domainecontenant 15 nœuds.Utilise principalement des nœuds comme Set, Switch, Telegram, Agent, TelegramTrigger. Construire un bot Telegram pour les réponses texte et image, intégrant Google Gemini 2.5 Flash
- •Token Bot Telegram
- •Clé API Google Gemini
Nœuds utilisés (15)
Catégorie
{
"id": "pl3YbOUdHMsDTYFE",
"meta": {
"instanceId": "f21041c58ebe9ae27fd386689e649a871f62f45682ca1c57f2ff2f2e3c9a5999"
},
"name": "TelegramBOT",
"tags": [],
"nodes": [
{
"id": "sticky-note-main",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1100,
-300
],
"parameters": {
"color": 4,
"width": 460,
"height": 640,
"content": "## 📋 TELEGRAM AI BOT - SETUP GUIDE\n\n### 🎯 What This Workflow Does:\nThis is an intelligent Telegram bot that can:\n- Answer text messages using AI\n- Analyze images sent by users\n- Maintain conversation context/memory\n- Provide formatted, attractive responses\n\n### 🔧 Required Setup:\n\n**1. Telegram Bot Token:**\n - Create a bot via @BotFather on Telegram\n - Get your bot token\n - Add credentials in n8n (Telegram account)\n\n**2. Google Gemini API Key:**\n - Go to Google AI Studio (ai.google.dev)\n - Create API key\n - Add credentials in n8n (Google Gemini API account)\n\n**3. Webhook Configuration:**\n - Activate the workflow\n - The webhook URL will be automatically set\n\n### 📊 Workflow Flow:\n1. **Telegram Trigger** receives messages\n2. **Route Types** checks if message is text or image\n3. For text: Direct to AI agent\n4. For images: Download → Analyze → Send to AI agent\n5. **AI Agent** processes with memory context\n6. Response sent back to user\n\n### ⚠️ Important Notes:\n- Memory is per message ID (20 message context)\n- Image analysis uses Gemini 2.5 Flash\n- Responses are formatted for Telegram readability"
},
"typeVersion": 1
},
{
"id": "sticky-note-trigger",
"name": "Note adhésive 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-820,
-80
],
"parameters": {
"color": 5,
"width": 280,
"height": 160,
"content": "## 🚀 TRIGGER\nStarts when user sends a message to your Telegram bot.\n\nCaptures both text messages and images."
},
"typeVersion": 1
},
{
"id": "sticky-note-router",
"name": "Note adhésive 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-600,
-80
],
"parameters": {
"color": 6,
"width": 260,
"height": 140,
"content": "## 🔀 ROUTING\nChecks message type:\n- TEXT: Route to text mapper\n- IMAGE: Route to image handler"
},
"typeVersion": 1
},
{
"id": "sticky-note-image",
"name": "Note adhésive 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-380,
160
],
"parameters": {
"color": 3,
"width": 360,
"height": 380,
"content": "## 🖼️ IMAGE PROCESSING\n1. Download image from Telegram\n2. Analyze with Gemini Vision\n3. Combine description + caption"
},
"typeVersion": 1
},
{
"id": "sticky-note-agent",
"name": "Note adhésive 4",
"type": "n8n-nodes-base.stickyNote",
"position": [
280,
-80
],
"parameters": {
"color": 2,
"width": 300,
"height": 180,
"content": "## 🤖 AI AGENT\nGoogle Gemini processes the request with:\n- Conversation memory (20 messages)\n- Context-aware responses\n- Telegram-friendly formatting"
},
"typeVersion": 1
},
{
"id": "568a5011-79b3-4660-88d9-c8b4c7c4519d",
"name": "Agent de base de connaissances",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
352,
64
],
"parameters": {
"text": "=Use these Descriptions to reply with a message to the user according to his question simply, shortly, and make sure he understand the thing he attaches:\n\n\"\" {{ $json.text }} \"\"\n\n\nI need your output message to be well spaced and formatted and look as attractive as possible for a telegram response!",
"options": {
"systemMessage": ""
},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "0c3f40bf-3773-4f7b-8b88-404e872d1188",
"name": "Mémoire simple",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
400,
464
],
"parameters": {
"sessionKey": "=memory_{{ $('Telegram Trigger').item.json.message.message_id }}",
"sessionIdType": "customKey",
"contextWindowLength": 20
},
"typeVersion": 1.3
},
{
"id": "74a1218b-fb53-450c-8462-ccad268ad7ee",
"name": "Mapper l'invite d'image",
"type": "n8n-nodes-base.set",
"position": [
128,
272
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "48af2dcc-4ce9-45fc-abfc-54f803930092",
"name": "text",
"type": "string",
"value": "=User image description:\n\n{{ $json.content.parts[0].text }}\n\nUser image caption: {{ $('Telegram Trigger').item.json.message.caption }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "85b4e665-2468-40c1-aa99-bd67e048d9fb",
"name": "Mapper l'invite texte",
"type": "n8n-nodes-base.set",
"position": [
-96,
-208
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "38aec976-a32c-4b0e-85f4-c90adc16abc9",
"name": "text",
"type": "string",
"value": "={{ $json.messages[0].text.body }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "482edd25-6a05-45cd-bb1f-c11d451938f5",
"name": "Router les types",
"type": "n8n-nodes-base.switch",
"position": [
-544,
64
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "2fc5c912-629b-4cbe-b5e3-7e3f0651c628",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.text }}",
"rightValue": "text"
}
]
},
"renameOutput": true
},
{
"outputKey": "Image",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "840b95b8-6559-4fb7-b32c-651451d6d0d2",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.photo[2] }}",
"rightValue": "image"
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "5cf1706c-cd33-4def-a99d-958d51654088",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
240,
464
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"id": "dBVkcKvaggEaTZ3w",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "46fd3fa6-5261-4fcf-b148-52a7ce0b2c43",
"name": "Analyser l'image",
"type": "@n8n/n8n-nodes-langchain.googleGemini",
"position": [
-96,
272
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "models/gemini-2.5-flash",
"cachedResultName": "models/gemini-2.5-flash"
},
"options": {},
"resource": "image",
"inputType": "binary",
"operation": "analyze"
},
"credentials": {
"googlePalmApi": {
"id": "dBVkcKvaggEaTZ3w",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "5b5f176c-7d2d-4db2-9f55-cc4dc18f6d4a",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-768,
64
],
"webhookId": "049da2eb-7ce1-4efd-820f-6a700adea8b6",
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"typeVersion": 1.2,
"alwaysOutputData": false
},
{
"id": "6489c29a-2c59-4362-916a-605f3e63c866",
"name": "Obtenir un fichier",
"type": "n8n-nodes-base.telegram",
"position": [
-320,
272
],
"webhookId": "d1b193c3-236e-4bed-be47-d0e156960d35",
"parameters": {
"fileId": "={{ $json.message.photo[2].file_id }}",
"resource": "file",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "Q0bwwwn2wzmbamLh",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "7b1b528f-4e3e-48d3-bc33-638fa4a3f446",
"name": "Envoyer un message texte",
"type": "n8n-nodes-base.telegram",
"position": [
704,
64
],
"webhookId": "53b5dc25-a9ea-47b4-87b7-274984c1115d",
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"id": "Q0bwwwn2wzmbamLh",
"name": "Telegram account"
}
},
"typeVersion": 1.2
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "332b36b7-0523-4d91-9ec6-0cb0b948d7f2",
"connections": {
"6489c29a-2c59-4362-916a-605f3e63c866": {
"main": [
[
{
"node": "46fd3fa6-5261-4fcf-b148-52a7ce0b2c43",
"type": "main",
"index": 0
}
]
]
},
"482edd25-6a05-45cd-bb1f-c11d451938f5": {
"main": [
[
{
"node": "85b4e665-2468-40c1-aa99-bd67e048d9fb",
"type": "main",
"index": 0
}
],
[
{
"node": "6489c29a-2c59-4362-916a-605f3e63c866",
"type": "main",
"index": 0
}
]
]
},
"46fd3fa6-5261-4fcf-b148-52a7ce0b2c43": {
"main": [
[
{
"node": "74a1218b-fb53-450c-8462-ccad268ad7ee",
"type": "main",
"index": 0
}
]
]
},
"0c3f40bf-3773-4f7b-8b88-404e872d1188": {
"ai_memory": [
[
{
"node": "568a5011-79b3-4660-88d9-c8b4c7c4519d",
"type": "ai_memory",
"index": 0
}
]
]
},
"85b4e665-2468-40c1-aa99-bd67e048d9fb": {
"main": [
[
{
"node": "568a5011-79b3-4660-88d9-c8b4c7c4519d",
"type": "main",
"index": 0
}
]
]
},
"74a1218b-fb53-450c-8462-ccad268ad7ee": {
"main": [
[
{
"node": "568a5011-79b3-4660-88d9-c8b4c7c4519d",
"type": "main",
"index": 0
}
]
]
},
"5b5f176c-7d2d-4db2-9f55-cc4dc18f6d4a": {
"main": [
[
{
"node": "482edd25-6a05-45cd-bb1f-c11d451938f5",
"type": "main",
"index": 0
}
]
]
},
"568a5011-79b3-4660-88d9-c8b4c7c4519d": {
"main": [
[
{
"node": "7b1b528f-4e3e-48d3-bc33-638fa4a3f446",
"type": "main",
"index": 0
}
]
]
},
"5cf1706c-cd33-4def-a99d-958d51654088": {
"ai_languageModel": [
[
{
"node": "568a5011-79b3-4660-88d9-c8b4c7c4519d",
"type": "ai_languageModel",
"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 - Création de contenu, 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
Ahmed Sherif
@asherif08Partager ce workflow