RAG-basierter LLM-Chatbot

Experte

Dies ist ein AI RAG, Multimodal AI-Bereich Automatisierungsworkflow mit 17 Nodes. Hauptsächlich werden GoogleDrive, Agent, GoogleDriveTrigger, ChatTrigger, LmChatOpenAi und andere Nodes verwendet. Erstellen Sie einen Chatbot für Unternehmensrichtlinien mit RAG, Pinecone-Vektordatenbank und OpenAI

Voraussetzungen
  • Google Drive API-Anmeldedaten
  • OpenAI API Key
  • Pinecone 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": "ijORqghBWmOcVaCd",
  "meta": {
    "instanceId": "87616dfce72ffd690a51f4d408ac3b27a946f12a1119e0e281f5ed271497219e",
    "templateCredsSetupCompleted": true
  },
  "name": "ChatBot For RAG Based LLMs",
  "tags": [],
  "nodes": [
    {
      "id": "93879f6c-0d57-4049-9e42-44d906160eb6",
      "name": "Bei Empfang einer Chat-Nachricht",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -440,
        -300
      ],
      "webhookId": "ba6e0e80-df72-4993-a938-16604c978e0b",
      "parameters": {
        "public": true,
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "688546eb-decc-4d88-b991-e6851d00d3c3",
      "name": "KI-Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -80,
        -300
      ],
      "parameters": {
        "options": {
          "systemMessage": "=You are an AI assistant specialized in analyzing user queries and retreive the data using pine cone vectore store via Vectore store QnA Tool. \n\nYour primary task is to answer questions accurately and precisely using the vector database, which contains relevant documents.\n\nOnly provide information that you retrieve from the documents (or verified expert knowledge). If something is not included in the dataset or is unclear, clearly state that you do not have sufficient information.\n\nStructure of your responses:\n• Concise and to the point\n• Specific numbers and facts, when available\n• Clearly indicate which quarterly tax deduction with the information comes from\n\nObjective:\nProvide users with reliable and quick insights to user questions without unnecessary details."
        }
      },
      "typeVersion": 2
    },
    {
      "id": "47d5f4e0-45e6-4a75-8250-76277a33addd",
      "name": "OpenAI Chat-Modell",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -220,
        -60
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "qlhg6EzexBZ9bwXO",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "c5e00f0e-2494-443d-9ff5-ab476f174fda",
      "name": "Einfacher Speicher",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        20,
        80
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "5bdc6723-18e4-4637-b31e-2b7a722c2d30",
      "name": "Pinecone Vektorspeicher",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        300,
        80
      ],
      "parameters": {
        "options": {
          "pineconeNamespace": "<yourNameSpace>"
        },
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "n8ntest",
          "cachedResultName": "n8ntest"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "PJJqeU0YnPNhhvLk",
          "name": "PineconeApi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "c9325bbd-95ee-49b6-80e3-b8eb18a3044e",
      "name": "Einbettungen OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        320,
        240
      ],
      "parameters": {
        "options": {
          "batchSize": 512,
          "dimensions": 512
        }
      },
      "credentials": {
        "openAiApi": {
          "id": "qlhg6EzexBZ9bwXO",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "1752c787-78f3-4c03-a44a-f619358b002b",
      "name": "Rechner",
      "type": "@n8n/n8n-nodes-langchain.toolCalculator",
      "position": [
        760,
        -120
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "c5130a15-b2fa-4c96-b890-6cda5a5d1e8a",
      "name": "Google Drive-Trigger",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        -1960,
        -240
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "18ElQ-fxK0zXX5Ahx1lk80OXnAJ9NwvHl",
          "cachedResultUrl": "https://drive.google.com/drive/folders/18ElQ-fxK0zXX5Ahx1lk80OXnAJ9NwvHl",
          "cachedResultName": "n8n"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "xFTXDFHVEmRlrR5e",
          "name": "Google Drive account 2"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "e918feee-188e-42c7-8012-09614b6d73a4",
      "name": "Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -1740,
        -240
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "list",
          "value": "1AWznNmqjEyztSOFYG9PgKOYX_GfJvI-P",
          "cachedResultUrl": "https://drive.google.com/file/d/1AWznNmqjEyztSOFYG9PgKOYX_GfJvI-P/view?usp=drivesdk",
          "cachedResultName": "income-tax-bill-2025.pdf"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "xFTXDFHVEmRlrR5e",
          "name": "Google Drive account 2"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "f2da487d-cbda-478d-8a38-b4c2a920dbaf",
      "name": "Standard-Datenlader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        -1140,
        40
      ],
      "parameters": {
        "loader": "pdfLoader",
        "options": {},
        "dataType": "binary"
      },
      "typeVersion": 1
    },
    {
      "id": "0ce84124-e903-4b41-a9dc-2b701efbeeaf",
      "name": "Rekursiver Zeichentext-Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        -1120,
        220
      ],
      "parameters": {
        "options": {
          "splitCode": "markdown"
        },
        "chunkOverlap": 50
      },
      "typeVersion": 1
    },
    {
      "id": "c6fff7f0-d215-4d25-8e4e-bcd5cc200330",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2020,
        -600
      ],
      "parameters": {
        "width": 940,
        "height": 280,
        "content": "## Data Loader\n- #### GDrive - Trigger \n  This node will trigger for every minute and retrieve details for any change to the folder.\n- #### GDrive - Trigger\n  This node will download the latest changes from GDrive and pass them to pin cone vector store\n- #### PineCone Vector Store\n  Here, we are actually storing the files by splitting them by leveraging the capabilities of default data loader. \n\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "abab349f-8cb4-489e-8a94-d369f89db0e0",
      "name": "PineconeVectorStore",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        -1480,
        -240
      ],
      "parameters": {
        "mode": "insert",
        "options": {
          "pineconeNamespace": "[YouNameSpace]"
        },
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "n8ntest",
          "cachedResultName": "n8ntest"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "PJJqeU0YnPNhhvLk",
          "name": "PineconeApi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "9cee9812-3cc7-4d3f-b7be-6d02b8f7ca3e",
      "name": "OpenAI Einbettungen",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        -1480,
        0
      ],
      "parameters": {
        "options": {
          "batchSize": 512,
          "dimensions": 512
        }
      },
      "credentials": {
        "openAiApi": {
          "id": "qlhg6EzexBZ9bwXO",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "401070d0-b61c-4fd4-9139-f82624e4d7fc",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -500,
        -500
      ],
      "parameters": {
        "color": 4,
        "width": 940,
        "height": 180,
        "content": "## Data Retrieval\nWe have an AI Agent that connects to Vector Store and Retrieve the required information to the user questions. \n\nThis connects to Vector Store QnA tool which then further connects to Vector Store to fetch the information and share to Ai Agent for further processing. "
      },
      "typeVersion": 1
    },
    {
      "id": "82fe4b78-b7d9-4ee1-a319-eb6e44d013dd",
      "name": "Vektorspeicher QnA",
      "type": "@n8n/n8n-nodes-langchain.toolVectorStore",
      "position": [
        380,
        -100
      ],
      "parameters": {
        "description": "Returns documents related to company polices and everything important from those policy documents"
      },
      "typeVersion": 1.1
    },
    {
      "id": "84e007f0-7bfe-4788-900b-9a73376a1318",
      "name": "OpenAI Chat-Modell2",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        780,
        60
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "qlhg6EzexBZ9bwXO",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "74b8ed97-4177-4d50-ae41-856da7e16a43",
  "connections": {
    "1752c787-78f3-4c03-a44a-f619358b002b": {
      "ai_tool": [
        [
          {
            "node": "688546eb-decc-4d88-b991-e6851d00d3c3",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "e918feee-188e-42c7-8012-09614b6d73a4": {
      "main": [
        [
          {
            "node": "abab349f-8cb4-489e-8a94-d369f89db0e0",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "c5e00f0e-2494-443d-9ff5-ab476f174fda": {
      "ai_memory": [
        [
          {
            "node": "688546eb-decc-4d88-b991-e6851d00d3c3",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "82fe4b78-b7d9-4ee1-a319-eb6e44d013dd": {
      "ai_tool": [
        [
          {
            "node": "688546eb-decc-4d88-b991-e6851d00d3c3",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "5bdc6723-18e4-4637-b31e-2b7a722c2d30",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "47d5f4e0-45e6-4a75-8250-76277a33addd": {
      "ai_languageModel": [
        [
          {
            "node": "688546eb-decc-4d88-b991-e6851d00d3c3",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Embeddings": {
      "ai_embedding": [
        [
          {
            "node": "abab349f-8cb4-489e-8a94-d369f89db0e0",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "84e007f0-7bfe-4788-900b-9a73376a1318": {
      "ai_languageModel": [
        [
          {
            "node": "82fe4b78-b7d9-4ee1-a319-eb6e44d013dd",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "f2da487d-cbda-478d-8a38-b4c2a920dbaf": {
      "ai_document": [
        [
          {
            "node": "abab349f-8cb4-489e-8a94-d369f89db0e0",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "c5130a15-b2fa-4c96-b890-6cda5a5d1e8a": {
      "main": [
        [
          {
            "node": "e918feee-188e-42c7-8012-09614b6d73a4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "5bdc6723-18e4-4637-b31e-2b7a722c2d30": {
      "ai_vectorStore": [
        [
          {
            "node": "82fe4b78-b7d9-4ee1-a319-eb6e44d013dd",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "93879f6c-0d57-4049-9e42-44d906160eb6": {
      "main": [
        [
          {
            "node": "688546eb-decc-4d88-b991-e6851d00d3c3",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "0ce84124-e903-4b41-a9dc-2b701efbeeaf": {
      "ai_textSplitter": [
        [
          {
            "node": "f2da487d-cbda-478d-8a38-b4c2a920dbaf",
            "type": "ai_textSplitter",
            "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?

Experte - KI RAG, Multimodales KI

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
Experte
Anzahl der Nodes17
Kategorie2
Node-Typen13
Schwierigkeitsbeschreibung

Für fortgeschrittene Benutzer, komplexe Workflows mit 16+ Nodes

Autor
Pramod Kumar Rathoure

Pramod Kumar Rathoure

@prathoure

Design and build custom n8n workflows that:\n ⚡ Eliminate repetitive work 📊 Integrate tools like Google Workspace, CRMs, and APIs ✅ Deliver faster, error-free results I create solutions that save time, boost accuracy, and let teams focus on high-value work. For me, automation isn’t just about technology—it’s about freeing people from busywork so they can do what matters most. let’s talk—I can help you turn them into smooth, automated workflows.

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34