Mein Arbeitsablauf

Fortgeschritten

Dies ist ein Support, AI-Bereich Automatisierungsworkflow mit 10 Nodes. Hauptsächlich werden Telegram, GoogleDocsTool, Agent, TelegramTrigger, LmChatOpenAi und andere Nodes verwendet, kombiniert mit KI-Technologie für intelligente Automatisierung. Erstelle einen Telegram-Kundensupport-Bot mit GPT4-mini und Google Docs-Wissensdatenbank

Voraussetzungen
  • Telegram Bot Token
  • OpenAI API Key
Workflow-Vorschau
Visualisierung der Node-Verbindungen, mit Zoom und Pan
Workflow exportieren
Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n
{
  "id": "",
  "meta": {},
  "name": "My workflow",
  "tags": [],
  "nodes": [
    {
      "id": "f611e34d-0de9-42b7-b438-bc522817f9ba",
      "name": "OpenAI-Chat-Modell",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        180,
        180
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini",
          "cachedResultName": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {},
      "typeVersion": 1.2
    },
    {
      "id": "7c968986-dcc4-4a26-bedf-5a5f9c75d2dc",
      "name": "Simple Speicher",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        340,
        180
      ],
      "parameters": {
        "sessionKey": "={{ $json.message.chat.id }}",
        "sessionIdType": "customKey"
      },
      "typeVersion": 1.3
    },
    {
      "id": "fd291678-8522-4e00-94bc-7033689f14b3",
      "name": "Google Docs",
      "type": "n8n-nodes-base.googleDocsTool",
      "position": [
        480,
        180
      ],
      "parameters": {
        "operation": "get",
        "documentURL": "https://docs.google.com/document/d/1os02TMG0h74DYE_mmv5utPr68LtV946otozP1YZTNr0/edit?tab=t.0"
      },
      "credentials": {},
      "typeVersion": 2
    },
    {
      "id": "d3e871cb-48b9-4921-8376-359f53e40942",
      "name": "Telegram-Trigger",
      "type": "n8n-nodes-base.telegramTrigger",
      "position": [
        -100,
        0
      ],
      "webhookId": "d546870e-898a-4d37-b290-a4b3e3eac311",
      "parameters": {
        "updates": [
          "message"
        ],
        "additionalFields": {}
      },
      "credentials": {},
      "typeVersion": 1.2
    },
    {
      "id": "8deb9aa3-4b45-4737-a6a5-4311fb460b04",
      "name": "Telegram",
      "type": "n8n-nodes-base.telegram",
      "position": [
        680,
        0
      ],
      "webhookId": "cfeeb7fc-6dad-4482-b8c7-73998bfc613f",
      "parameters": {
        "text": "={{ $json.output }}",
        "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
        "additionalFields": {
          "appendAttribution": false
        }
      },
      "credentials": {},
      "typeVersion": 1.2
    },
    {
      "id": "eac2e88c-0c0f-4451-bbe2-915de6e9ab1a",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -200,
        -100
      ],
      "parameters": {
        "width": 300,
        "height": 500,
        "content": "Telegram Trigger"
      },
      "typeVersion": 1
    },
    {
      "id": "c99be9a9-7368-4b22-be65-26108f8dc23a",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        120,
        -100
      ],
      "parameters": {
        "color": 4,
        "width": 500,
        "height": 500,
        "content": "Telegram Trigger"
      },
      "typeVersion": 1
    },
    {
      "id": "ba596aa6-e6fb-4df4-9bdb-7b75536cfbf6",
      "name": "Haftnotiz2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        640,
        -100
      ],
      "parameters": {
        "color": 3,
        "width": 280,
        "height": 500,
        "content": "Telegram Trigger"
      },
      "typeVersion": 1
    },
    {
      "id": "ccf10ec2-eae2-47be-9be7-7bf7b3d974cb",
      "name": "Customer Support KI-Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        220,
        0
      ],
      "parameters": {
        "text": "={{ $json.message.text }}",
        "options": {
          "systemMessage": "You are a helpful Customer Support Agent, cross-reference the Google Doc for any customer queries for relevant information. If relevant information is not found, do not make up facts. Plainly let the user know that the information isn't available. \n\n#Tonality\nFriendly, casual and helpful. if user or customer says hi, inform them that you are a Friendly Customer Support Agent"
        },
        "promptType": "define"
      },
      "typeVersion": 2
    },
    {
      "id": "ac9ffbcd-0b7a-421e-92f4-5e367d6ba4c9",
      "name": "Haftnotiz6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -600,
        -100
      ],
      "parameters": {
        "color": 5,
        "width": 360,
        "height": 500,
        "content": "🤖 AI Customer Support Agent with Google Docs Knowledge (Telegram + OpenAI)\n\nThis no-code workflow turns your Telegram bot into an intelligent, always-on AI support agent that references your business documentation in Google Docs to respond to customer queries—instantly and accurately.\n\nWatch full step-by-step video tutorial of the build here:\nhttps://www.youtube.com/@Automatewithmarc\n\n🔧 How it works:\nTelegram Trigger – Captures incoming messages from users on your Telegram bot\n\nLangchain AI Agent (OpenAI GPT) – Interprets the message and uses RAG (retrieval-augmented generation) techniques to craft an answer\n\nGoogle Docs Tool – Connects to and retrieves context from your specified Google Doc (e.g. FAQ, SOPs, policies)\n\nMemory Buffer – Keeps track of recent chat history for more human-like conversations\n\nTelegram Reply Node – Sends the AI-generated response back to the user\n\n💡 Use Cases:\nE-commerce customer service\n\nSaaS product onboarding\n\nInternal helpdesk bot for teams\n\nWhatsApp-style support for digital businesses\n\n🧠 What makes this powerful:\nSupports complex questions by referencing a live Google Doc knowledge base\n\nWorks in plain conversational language (no buttons or forms needed)\n\nRuns 24/7 with zero code\n\nEasily extendable to Slack, WhatsApp, or email support\n\n🛠️ Tools used:\nTelegram Node (trigger + send)\n\nLangchain Agent with OpenAI GPT\n\nGoogle Docs Tool\n\nMemory Buffer\n\nSticky Notes for easy understanding"
      },
      "typeVersion": 1
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "",
  "connections": {
    "fd291678-8522-4e00-94bc-7033689f14b3": {
      "ai_tool": [
        [
          {
            "node": "Customer Support AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "Customer Support AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Telegram Trigger": {
      "main": [
        [
          {
            "node": "Customer Support AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Customer Support AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Customer Support AI Agent": {
      "main": [
        [
          {
            "node": "8deb9aa3-4b45-4737-a6a5-4311fb460b04",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Häufig gestellte Fragen

Wie verwende ich diesen Workflow?

Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.

Für welche Szenarien ist dieser Workflow geeignet?

Fortgeschritten - Support, Künstliche Intelligenz

Ist es kostenpflichtig?

Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.

Workflow-Informationen
Schwierigkeitsgrad
Fortgeschritten
Anzahl der Nodes10
Kategorie2
Node-Typen7
Schwierigkeitsbeschreibung

Für erfahrene Benutzer, mittelkomplexe Workflows mit 6-15 Nodes

Autor
Automate With Marc

Automate With Marc

@marconi

Automating Start-Up and Business processes. Helping non-techies understand and leverage Agentic AI with easy to understand step-by-step tutorials. Check out my educational content: https://www.youtube.com/@Automatewithmarc

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34