Dokumenten-Frage-System mit Google Drive, Pinecone und OpenAI RAG erstellen

Experte

Dies ist ein Automatisierungsworkflow mit 19 Nodes. Hauptsächlich werden GoogleDrive, Agent, GoogleDriveTrigger, ChatTrigger, LmChatOpenAi und andere Nodes verwendet. Ein Dokumenten-Frage-Antwort-System mit Google Drive, Pinecone und OpenAI RAG erstellen

Voraussetzungen
  • Google Drive API-Anmeldedaten
  • OpenAI API Key
  • Pinecone API Key

Kategorie

-
Workflow-Vorschau
Visualisierung der Node-Verbindungen, mit Zoom und Pan
Workflow exportieren
Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n
{
  "meta": {
    "instanceId": "79fe07f045222b356cf5ca430fe39cdf11b9fe024467e3b6b3e1a64d1a92c94f"
  },
  "nodes": [
    {
      "id": "56745855-bde9-45f2-bb9a-37c8a5544056",
      "name": "Google Drive Trigger",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        -112,
        592
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "id",
          "value": "=Choose your folder"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "31b61802-30e6-4898-8a3b-881ddc96c127",
      "name": "Datei herunterladen",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        160,
        592
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "url",
          "value": "=Choose your folder"
        },
        "options": {},
        "operation": "download"
      },
      "typeVersion": 3
    },
    {
      "id": "4d6b1ba5-38eb-4db1-a43c-e508ad192ff3",
      "name": "Pinecone Vektorspeicher",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        432,
        592
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "id",
          "value": "=Choose you index"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "3b3adc2c-f566-4c6d-8dad-2bff56fdc83d",
      "name": "Einbettungen OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        160,
        1024
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.2
    },
    {
      "id": "3b3b0ebc-7972-4d4b-88fd-a7d9df5a30d8",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        608,
        848
      ],
      "parameters": {
        "options": {},
        "textSplittingMode": "custom"
      },
      "typeVersion": 1.1
    },
    {
      "id": "a95ab7b7-8624-4fb7-8238-45147bf8acd3",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        464,
        1056
      ],
      "parameters": {
        "options": {},
        "chunkOverlap": 100
      },
      "typeVersion": 1
    },
    {
      "id": "fd460847-a8aa-4c2d-946f-7deddfc2c64e",
      "name": "Wenn Chat-Nachricht empfangen",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        1040,
        672
      ],
      "webhookId": "9be55aab-2133-42ad-ab75-2c43888786b7",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.3
    },
    {
      "id": "f796fa38-a472-4c68-81b7-78874d6b47fa",
      "name": "OpenAI-Chat-Modell",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1264,
        896
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "typeVersion": 1.2
    },
    {
      "id": "7f2d4746-be6c-4dc3-bbf8-979a0e2cf2b5",
      "name": "Simple Speicher",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        1392,
        896
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "677e0550-9d7f-4d55-a18e-694ca2d9ae55",
      "name": "Pinecone Vektorspeicher1",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        1520,
        896
      ],
      "parameters": {
        "mode": "retrieve-as-tool",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "databases",
          "cachedResultName": "databases"
        },
        "toolDescription": "Use this as a knowledge base to answer the user message"
      },
      "typeVersion": 1.3
    },
    {
      "id": "22033102-58b8-4ec5-899c-8fc4ba290782",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -192,
        528
      ],
      "parameters": {
        "color": 5,
        "width": 1056,
        "height": 688,
        "content": "## Document inserting"
      },
      "typeVersion": 1
    },
    {
      "id": "4a3f3dc6-e6f7-4357-b0ce-538ad5c4af7b",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        96,
        960
      ],
      "parameters": {
        "color": 4,
        "width": 208,
        "height": 208,
        "content": "## Embeddings"
      },
      "typeVersion": 1
    },
    {
      "id": "ef37ed33-f7b8-412c-b534-0c949d48a0e1",
      "name": "Haftnotiz2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        384,
        544
      ],
      "parameters": {
        "width": 320,
        "height": 176,
        "content": "## Storing"
      },
      "typeVersion": 1
    },
    {
      "id": "69048fc8-1479-4efe-980d-5a40b71c2fc2",
      "name": "Haftnotiz3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        880,
        528
      ],
      "parameters": {
        "width": 992,
        "height": 560,
        "content": "## Test here\n\n* you can change the trigger as you need."
      },
      "typeVersion": 1
    },
    {
      "id": "843bcd47-d995-4a77-b6ac-7e81dd35b0d8",
      "name": "Haftnotiz4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1504,
        832
      ],
      "parameters": {
        "color": 7,
        "width": 288,
        "height": 192,
        "content": "## Get the Database"
      },
      "typeVersion": 1
    },
    {
      "id": "b5fbdc8b-c696-417f-8e51-f03e0b65bbd8",
      "name": "Haftnotiz5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -640,
        528
      ],
      "parameters": {
        "width": 432,
        "height": 704,
        "content": "## Credential Setup (Critical)\n\nYou'll need to create credentials for the following services. Click the link next to each one for the full setup guide from the n8n documentation:\n\nGoogle Drive OAuth2 API (Used by: Google Drive Trigger, Download file):\n\nLink: https://docs.n8n.io/integrations/builtin/credentials/google/oauth-generic/\n\nAction: You need to set up an OAuth application in the Google Cloud Console to grant n8n access to your Google Drive files.\n\nPinecone API (Used by: Pinecone Vector Store, Pinecone Vector Store1):\n\nLink: https://docs.n8n.io/integrations/builtin/credentials/pinecone/\n\nAction: You'll need to get your API Key and Environment from your Pinecone account dashboard and enter them into the n8n credential setup.\n\nOpenAI API (Used by: Embeddings OpenAI, OpenAI Chat Model):\n\nLink: https://docs.n8n.io/integrations/builtin/credentials/openai/\n\nAction: You'll need to generate a Secret API Key from your OpenAI account to use for embeddings and the chat model.\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "aafc6b73-18de-4934-b61b-e55556f12cd6",
      "name": "Haftnotiz6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -640,
        176
      ],
      "parameters": {
        "color": 4,
        "width": 672,
        "height": 336,
        "content": "### **RAG system**\n\n### **How It Works**\n\n* **Summarize the Flow:** Distill the function of your entire workflow into a few high-level, easy-to-understand steps.\n\n### **Set Up Steps**\n\n* **Set Expectations:** Give users a clear idea of how long the setup will take.\n* **Keep It Concise:** Don't describe every minute detail in the main setup guide.\n* **Use Sticky Notes:** Place all detailed descriptions and complex instructions within **sticky notes** directly inside the n8n workflow itself, keeping the main documentation clean and brief."
      },
      "typeVersion": 1
    },
    {
      "id": "b99dc201-c075-4b5c-9433-2a8e69c86404",
      "name": "Haftnotiz7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -640,
        80
      ],
      "parameters": {
        "color": 6,
        "width": 224,
        "height": 80,
        "content": "## workflow builder [Abdullah Ahmed](https://www.youtube.com/@gureyosman06)"
      },
      "typeVersion": 1
    },
    {
      "id": "56750d09-170d-4bcb-9831-7ee9e2f8d61b",
      "name": "KI-Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        1328,
        672
      ],
      "parameters": {
        "options": {
          "systemMessage": "You are a helpful assistant"
        },
        "hasOutputParser": true
      },
      "typeVersion": 2.2
    }
  ],
  "pinData": {},
  "connections": {
    "31b61802-30e6-4898-8a3b-881ddc96c127": {
      "main": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_embedding",
            "index": 0
          },
          {
            "node": "Pinecone Vector Store1",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "3b3b0ebc-7972-4d4b-88fd-a7d9df5a30d8": {
      "ai_document": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "56745855-bde9-45f2-bb9a-37c8a5544056": {
      "main": [
        [
          {
            "node": "31b61802-30e6-4898-8a3b-881ddc96c127",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store1": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "fd460847-a8aa-4c2d-946f-7deddfc2c64e": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "a95ab7b7-8624-4fb7-8238-45147bf8acd3": {
      "ai_textSplitter": [
        [
          {
            "node": "3b3b0ebc-7972-4d4b-88fd-a7d9df5a30d8",
            "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

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 Nodes19
Kategorie-
Node-Typen11
Schwierigkeitsbeschreibung

Für fortgeschrittene Benutzer, komplexe Workflows mit 16+ Nodes

Autor
Abdullahi Ahmed

Abdullahi Ahmed

@abdosman06

I'm an Automation consultant with over 1 year of experience helping businesses to streamline their processes. Use my link to book an initial consultation for custom n8n work.

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34