Erstellung eines RAG-Vektordatenbanks aus Google Drive-Dokumenten mit Gemini und Supabase

Experte

Dies ist ein Document Extraction, AI RAG-Bereich Automatisierungsworkflow mit 16 Nodes. Hauptsächlich werden Code, Postgres, GoogleDrive, SplitInBatches, ExecuteWorkflowTrigger und andere Nodes verwendet. Erstellen Sie einen RAG-Vektordatenbank aus Google Drive-Dokumenten mit Gemini und Supabase

Voraussetzungen
  • PostgreSQL-Datenbankverbindungsdaten
  • Google Drive API-Anmeldedaten
  • Supabase URL und 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
{
  "meta": {
    "instanceId": "a243f35537ecbb3a29ba49c4cf2200720075b362bcc7d02523f79748238bcfd6"
  },
  "nodes": [
    {
      "id": "97927b62-d8b9-4c98-b3d1-160c81c524e5",
      "name": "Embeddings Google Gemini4",
      "type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
      "position": [
        208,
        320
      ],
      "parameters": {},
      "credentials": {
        "googlePalmApi": {
          "id": "VCZQfcHNj0rHxcNf",
          "name": "GEMINI_API_KUDDUS"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "a9afa4ed-5e53-423c-9521-a79b17dbdde1",
      "name": "Standard-Datenlader2",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        384,
        304
      ],
      "parameters": {
        "options": {},
        "dataType": "binary"
      },
      "typeVersion": 1.1
    },
    {
      "id": "478d1053-af37-451e-9baf-7708f43653fa",
      "name": "Eine SQL-Abfrage ausführen",
      "type": "n8n-nodes-base.postgres",
      "position": [
        -624,
        48
      ],
      "parameters": {
        "query": "DROP TABLE IF EXISTS documents CASCADE;\n\nCREATE EXTENSION IF NOT EXISTS vector;\n\nCREATE TABLE IF NOT EXISTS documents (\n  id bigserial PRIMARY KEY,\n  content text,\n  metadata jsonb,\n  embedding vector(768)\n);\n\nCREATE OR REPLACE FUNCTION match_documents(\n  query_embedding vector(768),\n  match_count int DEFAULT NULL,\n  filter jsonb DEFAULT '{}'::jsonb\n)\nRETURNS TABLE (\n  id bigint,\n  content text,\n  metadata jsonb,\n  similarity double precision\n)\nLANGUAGE sql\nAS $$\n  SELECT\n    d.id,\n    d.content,\n    d.metadata,\n    1 - (d.embedding <=> query_embedding) AS similarity\n  FROM documents d\n  WHERE (filter = '{}'::jsonb OR d.metadata @> filter)\n  ORDER BY d.embedding <=> query_embedding\n  LIMIT match_count;\n$$;\n",
        "options": {},
        "operation": "executeQuery"
      },
      "credentials": {
        "postgres": {
          "id": "KbYSAyR6T3ljhFKn",
          "name": "Postgres account"
        }
      },
      "typeVersion": 2.6
    },
    {
      "id": "7e4395b7-b822-41b6-aac3-0d4c2e3a749b",
      "name": "Code in JavaScript",
      "type": "n8n-nodes-base.code",
      "position": [
        -848,
        48
      ],
      "parameters": {
        "jsCode": "// Get the Drive_Folder_link from the workflow input\nconst driveUrl = $input.first().json.Drive_Folder_link;\n\n// Extract Google Drive folder/file ID from URL\nfunction getDriveId(url) {\n  const folderMatch = url.match(/\\/folders\\/([a-zA-Z0-9_-]+)/);\n  const fileMatch = url.match(/\\/file\\/d\\/([a-zA-Z0-9_-]+)/);\n  return folderMatch ? folderMatch[1] : (fileMatch ? fileMatch[1] : null);\n}\n\n// Process input items\nreturn items.map(item => {\n  const chatInput = item.json.chatInput || driveUrl || '';\n  const driveId = getDriveId(chatInput);\n\n  return {\n    json: {\n      originalInput: chatInput,\n      folderId: driveId,\n      driveId: driveId\n    }\n  };\n});\n"
      },
      "typeVersion": 2
    },
    {
      "id": "3a4041d1-25ac-4ab4-974e-a5460c9a8ffa",
      "name": "Bei Ausführung durch einen anderen Workflow",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "position": [
        -1056,
        48
      ],
      "parameters": {
        "inputSource": "jsonExample",
        "jsonExample": "{\n  \"Drive_Folder_link\": \"https://drive.google.com/drive/folders/example\"\n}"
      },
      "typeVersion": 1.1
    },
    {
      "id": "92141102-016e-4e8a-b69f-f09d0522924d",
      "name": "Notizzettel1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1504,
        -128
      ],
      "parameters": {
        "color": 5,
        "width": 368,
        "height": 512,
        "content": "# 📁 Drive to Supabase Vector Store for Study RAG\n\nProcesses Google Drive folder files into Supabase vector embeddings for RAG applications.\n\n**Flow:** Drive URL → Parse ID → Init DB → Fetch Files → Loop → Download → Embed → Store\n\n**Requirements:**\n- Google Drive OAuth2\n- Supabase + Postgres credentials\n- Google Gemini API key\n\n**Input:** `{\"Drive_Folder_link\": \"your_drive_url\"}`\n**Output:** Vector embeddings in Supabase documents table\n"
      },
      "typeVersion": 1
    },
    {
      "id": "6960ace8-fd01-4f9e-acfc-05185a0b197f",
      "name": "Notizzettel",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1104,
        208
      ],
      "parameters": {
        "width": 176,
        "height": 128,
        "content": "**Trigger Node** - Starts workflow when called from another n8n workflow. Accepts Drive folder URL as input.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "2befa4d1-ded3-4eeb-93ec-acdc9a9e22fb",
      "name": "Notizzettel2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -864,
        208
      ],
      "parameters": {
        "width": 150,
        "height": 128,
        "content": "**Extract Folder ID** - Parses Google Drive URL using regex to extract folder/file ID for API calls.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "e71b4968-43de-477f-9de6-474cd471c405",
      "name": "Notizzettel3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -656,
        208
      ],
      "parameters": {
        "width": 176,
        "content": "**Initialize Database** - Creates Supabase vector table with pgvector extension and match_documents search function. ⚠️ Drops existing table!\n"
      },
      "typeVersion": 1
    },
    {
      "id": "4ac27951-096f-44ba-8e66-be73b3c0d380",
      "name": "Über Elemente iterieren",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        -192,
        48
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "d556d5eb-6216-4e39-bf8f-07a948fcbb0d",
      "name": "Dateien und Ordner durchsuchen",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -416,
        48
      ],
      "parameters": {
        "filter": {
          "folderId": {
            "__rl": true,
            "mode": "id",
            "value": "={{ $('Code in JavaScript').item.json.folderId }}"
          }
        },
        "options": {},
        "resource": "fileFolder"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "CVN95k3ctbjWs60e",
          "name": "Google_Drive_gaming"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "db2f57b6-1aa9-4926-a211-7362d5d4533e",
      "name": "In Supabase Vectorstore einfügen",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
      "position": [
        256,
        48
      ],
      "parameters": {
        "mode": "insert",
        "options": {
          "queryName": "match_documents"
        },
        "tableName": {
          "__rl": true,
          "mode": "list",
          "value": "documents",
          "cachedResultName": "documents"
        }
      },
      "credentials": {
        "supabaseApi": {
          "id": "OweRv8RLSfhKJyfg",
          "name": "Supabase account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "09addf62-6c1a-4af4-a5d5-6b2323f64886",
      "name": "Datei herunterladen",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        48,
        64
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {
          "googleFileConversion": {
            "conversion": {
              "docsToFormat": "text/plain"
            }
          }
        },
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "CVN95k3ctbjWs60e",
          "name": "Google_Drive_gaming"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "0c929411-a2d2-49ff-ab92-09aeece9d892",
      "name": "Notizzettel4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -432,
        224
      ],
      "parameters": {
        "width": 176,
        "height": 128,
        "content": "**List Drive Files** - Retrieves all files from the specified Google Drive folder using extracted folder ID.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "b2b6df82-5145-4719-b3bc-a5501e31ed08",
      "name": "Notizzettel5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        16,
        -112
      ],
      "parameters": {
        "width": 150,
        "content": "**List Drive Files** - Retrieves all files from the specified Google Drive folder using extracted folder ID.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "0d6c2252-f11a-4a12-978c-b121c68c8663",
      "name": "Notizzettel6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        240,
        -208
      ],
      "parameters": {
        "color": 7,
        "height": 240,
        "content": "**Store Embeddings** - Generates 768-dim vectors via Gemini and inserts documents into Supabase for semantic search.\n**AI Embeddings** - Converts text to 768-dimensional vectors using Google Gemini text-embedding-004 model.\n**Document Loader** - Extracts and formats text from binary files for the embedding generator.\n"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "09addf62-6c1a-4af4-a5d5-6b2323f64886": {
      "main": [
        [
          {
            "node": "db2f57b6-1aa9-4926-a211-7362d5d4533e",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "4ac27951-096f-44ba-8e66-be73b3c0d380": {
      "main": [
        [],
        [
          {
            "node": "09addf62-6c1a-4af4-a5d5-6b2323f64886",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "7e4395b7-b822-41b6-aac3-0d4c2e3a749b": {
      "main": [
        [
          {
            "node": "478d1053-af37-451e-9baf-7708f43653fa",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "478d1053-af37-451e-9baf-7708f43653fa": {
      "main": [
        [
          {
            "node": "d556d5eb-6216-4e39-bf8f-07a948fcbb0d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "a9afa4ed-5e53-423c-9521-a79b17dbdde1": {
      "ai_document": [
        [
          {
            "node": "db2f57b6-1aa9-4926-a211-7362d5d4533e",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "d556d5eb-6216-4e39-bf8f-07a948fcbb0d": {
      "main": [
        [
          {
            "node": "4ac27951-096f-44ba-8e66-be73b3c0d380",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "97927b62-d8b9-4c98-b3d1-160c81c524e5": {
      "ai_embedding": [
        [
          {
            "node": "db2f57b6-1aa9-4926-a211-7362d5d4533e",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "db2f57b6-1aa9-4926-a211-7362d5d4533e": {
      "main": [
        [
          {
            "node": "4ac27951-096f-44ba-8e66-be73b3c0d380",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "3a4041d1-25ac-4ab4-974e-a5460c9a8ffa": {
      "main": [
        [
          {
            "node": "7e4395b7-b822-41b6-aac3-0d4c2e3a749b",
            "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?

Experte - Dokumentenextraktion, KI RAG

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 Nodes16
Kategorie2
Node-Typen9
Schwierigkeitsbeschreibung

Für fortgeschrittene Benutzer, komplexe Workflows mit 16+ Nodes

Autor
Mantaka Mahir

Mantaka Mahir

@mantakamahir

Al Automation Expert || Al Agents || n8n || Python || LangChain || Helping businesses scale revenue and reduce costs with Al driven automation .

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34