AI学习助手（RAG）：Google Gemini与Drive及Supabase向量搜索

• •PostgreSQL 数据库连接信息
• •Google Drive API 凭证
• •Google Gemini API Key
• •Supabase URL 和 API Key

{
  "meta": {
    "instanceId": "a243f35537ecbb3a29ba49c4cf2200720075b362bcc7d02523f79748238bcfd6",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "0db018d8-693f-4e47-be62-4b34d7b8d77f",
      "name": "嵌入 Google Gemini",
      "type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
      "position": [
        912,
        592
      ],
      "parameters": {},
      "credentials": {
        "googlePalmApi": {
          "id": "VCZQfcHNj0rHxcNf",
          "name": "GEMINI_API_KUDDUS"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "edf2e17e-a730-486b-8e2a-8acaef9e84a3",
      "name": "Supabase 向量存储",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
      "position": [
        912,
        400
      ],
      "parameters": {
        "mode": "retrieve-as-tool",
        "options": {},
        "tableName": {
          "__rl": true,
          "mode": "list",
          "value": "documents",
          "cachedResultName": "documents"
        },
        "toolDescription": "Use this tool to search and retrieve relevant information from the user's study materials stored in the vector database. Query the documents to answer user questions accurately."
      },
      "credentials": {
        "supabaseApi": {
          "id": "OweRv8RLSfhKJyfg",
          "name": "Supabase account"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "1a55495f-44be-4c71-9a9d-f4886a8980a8",
      "name": "Postgres 聊天记忆",
      "type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
      "position": [
        368,
        608
      ],
      "parameters": {
        "sessionKey": "={{ $json.sessionId }}",
        "sessionIdType": "customKey",
        "contextWindowLength": 10
      },
      "credentials": {
        "postgres": {
          "id": "KbYSAyR6T3ljhFKn",
          "name": "Postgres account"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "39d7a9b3-66d8-41fb-8454-6a80885131d1",
      "name": "计算器",
      "type": "@n8n/n8n-nodes-langchain.toolCalculator",
      "position": [
        768,
        464
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "d943532d-4ae7-4829-a381-191cf84ea622",
      "name": "当收到聊天消息时",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        176,
        192
      ],
      "webhookId": "6f7911bb-b08c-40ba-b613-a81d3d26ee18",
      "parameters": {
        "public": true,
        "options": {}
      },
      "typeVersion": 1.3
    },
    {
      "id": "f37c1723-0049-4b1d-8354-3acfd5179cb4",
      "name": "Google Gemini聊天模型",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        256,
        448
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.5-pro"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "VCZQfcHNj0rHxcNf",
          "name": "GEMINI_API_KUDDUS"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "225fb496-37d1-4dd7-b008-179ebb0880cc",
      "name": "文件夹所有文件到向量",
      "type": "@n8n/n8n-nodes-langchain.toolWorkflow",
      "position": [
        576,
        448
      ],
      "parameters": {
        "workflowId": {
          "__rl": true,
          "mode": "list",
          "value": "DXm6uptDmBBGVVWV",
          "cachedResultUrl": "/workflow/DXm6uptDmBBGVVWV",
          "cachedResultName": "Drive folder all file to Supabase Vector Store Database for RAG"
        },
        "workflowInputs": {
          "value": {
            "Drive_Folder_link": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Drive_Folder_link', ``, 'string') }}"
          },
          "schema": [
            {
              "id": "Drive_Folder_link",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "Drive_Folder_link",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [
            "Drive_Folder_link"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "2cec8fcc-a3ed-459e-9e30-1fad8a7b6765",
      "name": "学习助手",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        448,
        192
      ],
      "parameters": {
        "text": "={{ $json.chatInput }}",
        "options": {
          "systemMessage": "You are a Study AI Assistant that helps users interact with their study materials in a natural, conversational way.\n\n## Core Behavior\n\n**Always respond conversationally and helpfully.** You can answer questions, provide information from stored materials, and assist with file uploads - all while maintaining a friendly, natural dialogue.\n\n## Input Handling\n\n### 1. Google Drive Links\nWhen you detect a Google Drive URL (folder or file):\n- **Pattern**: `https://drive.google.com/drive/folders/` or `https://drive.google.com/file/d/`\n- **Action**: Automatically trigger the `DriveFolderToSupabase` workflow\n- **Response**: Confirm the upload is processing: \"I'm uploading your files to the vector store. This will take a moment...\"\n\n### 2. Study Material Queries\nWhen users ask questions about their materials:\n- **Search the vector store** using available retrieval tools\n- **Always check the vector store first** before saying you don't have information\n- Provide clear, helpful answers with citations\n- Include document names, sections, or page numbers when available\n\n### 3. General Conversation\nWhen users engage in general conversation:\n- Respond naturally and helpfully\n- If they're asking about themselves or their materials, **search the vector store**\n- Use context from previous messages in the conversation\n- Be conversational, not robotic\n\n## Critical Rules\n\n1. **Never refuse to search**: If someone asks \"what is in the documents\" or \"tell me about X\", immediately query the vector store with relevant keywords\n2. **Infer intent**: Questions like \"about me\", \"what's my name\", or \"vector database\" should trigger a vector store search for relevant content\n3. **Use broad searches**: When unsure, search with general terms rather than refusing to help\n4. **Acknowledge limitations gracefully**: Only say you can't find information AFTER searching, not before\n5. **Maintain conversation context**: Reference previous exchanges naturally\n\n## Search Strategy\n\nWhen querying the vector store:\n- Use **keywords and concepts** from the user's question\n- Try **multiple related terms** if the first search yields poor results\n- For vague queries like \"tell me what's in the documents\", search with terms like: \"overview\", \"introduction\", \"main topic\", \"summary\"\n- **Always attempt a search** before saying you don't have the information\n\n## Response Format\n\n- **Direct answers** to questions\n- **Cite sources** when providing information from documents\n- **Suggest related topics** when appropriate\n- **Ask clarifying questions** only when absolutely necessary (not as a default)\n\n## Examples\n\n**Bad Response**: \"I need a specific question or topic to search for.\"\n**Good Response**: *[Searches vector store]* \"Based on your uploaded materials, I found information about [topic]. Here's what I can tell you...\"\n\n**Bad Response**: \"I don't have access to personal information like your name.\"\n**Good Response**: *[Searches vector store for personal info]* \"I searched your documents and found [relevant information], or if nothing is found: \"I searched your uploaded materials but didn't find personal information stored. What would you like to know about your study content?\"\n"
        },
        "promptType": "define"
      },
      "typeVersion": 2.2
    },
    {
      "id": "cf65699a-9e5a-4c24-b256-fe3892c154fd",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -224,
        96
      ],
      "parameters": {
        "width": 336,
        "height": 640,
        "content": "# 🤖 AI 学习助手（RAG 聊天）"
      },
      "typeVersion": 1
    },
    {
      "id": "eddf672b-4bd8-45d6-bf4e-29ddd688f1e5",
      "name": "便签 1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        416,
        32
      ],
      "parameters": {
        "color": 4,
        "width": 288,
        "height": 352,
        "content": "**AI Agent（核心）** - 协调所有工具和记忆。处理 Drive 链接、搜索文档、维护上下文，并使用 Gemini 2.5 Pro 自然响应"
      },
      "typeVersion": 1
    },
    {
      "id": "c201dfbd-714c-4629-8a49-9acc006af38a",
      "name": "便签 2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        912,
        256
      ],
      "parameters": {
        "height": 272,
        "content": "**文档搜索工具** - 使用 768 维嵌入的语义相似性搜索从上传的学习材料中检索相关信息"
      },
      "typeVersion": 1
    },
    {
      "id": "e29b5f39-3fcb-40b2-9ba0-02ef7d070f2a",
      "name": "便签 3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        512,
        512
      ],
      "parameters": {
        "height": 208,
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "54a5e290-1ec4-4b97-96ed-d424aaf3c2ca",
      "name": "嵌入 Google Gemini4",
      "type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
      "position": [
        1232,
        1392
      ],
      "parameters": {},
      "credentials": {
        "googlePalmApi": {
          "id": "VCZQfcHNj0rHxcNf",
          "name": "GEMINI_API_KUDDUS"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "7682b868-5215-452d-b110-ff8007f2d059",
      "name": "默认数据加载器2",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        1408,
        1376
      ],
      "parameters": {
        "options": {},
        "dataType": "binary"
      },
      "typeVersion": 1.1
    },
    {
      "id": "ceacbea3-3c6a-47d1-83a6-386cb1166414",
      "name": "执行 SQL 查询",
      "type": "n8n-nodes-base.postgres",
      "position": [
        400,
        1120
      ],
      "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": "90883ae9-8d17-4a72-83be-da4dae013343",
      "name": "JavaScript 代码",
      "type": "n8n-nodes-base.code",
      "position": [
        176,
        1120
      ],
      "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": "1e5ac5c6-ae2c-400d-b531-a18c823a3d07",
      "name": "当由其他工作流执行时",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "position": [
        -32,
        1120
      ],
      "parameters": {
        "inputSource": "jsonExample",
        "jsonExample": "{\n  \"Drive_Folder_link\": \"https://drive.google.com/drive/folders/example\"\n}"
      },
      "typeVersion": 1.1
    },
    {
      "id": "472c0470-a590-476a-b23b-77617b042a39",
      "name": "遍历项目",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        832,
        1120
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "8e8a66a7-9a2c-4ed9-91b3-80d805b1dbab",
      "name": "搜索文件和文件夹",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        608,
        1120
      ],
      "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": "21559a2e-f0d3-40a1-8809-5f2a31cde811",
      "name": "插入到 Supabase Vectorstore",
      "type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
      "position": [
        1280,
        1120
      ],
      "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": "a818d7b0-1c5e-4273-96d1-d72ff2960823",
      "name": "下载文件",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        1072,
        1136
      ],
      "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": "0cf08172-6b3e-44a9-aec7-44a2b5e582ff",
      "name": "便签 4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        592,
        1296
      ],
      "parameters": {
        "width": 176,
        "height": 128,
        "content": "**列出 Drive 文件** - 使用提取的文件夹 ID 从指定的 Google Drive 文件夹检索所有文件"
      },
      "typeVersion": 1
    },
    {
      "id": "98009dab-d49a-4205-9d9b-da29c3560d98",
      "name": "便签 5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1040,
        960
      ],
      "parameters": {
        "width": 150,
        "content": "**列出 Drive 文件** - 使用提取的文件夹 ID 从指定的 Google Drive 文件夹检索所有文件"
      },
      "typeVersion": 1
    },
    {
      "id": "57415dae-d6cd-4c5a-8305-ee9100bec975",
      "name": "便签6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1264,
        864
      ],
      "parameters": {
        "color": 7,
        "height": 240,
        "content": "**存储嵌入** - 通过 Gemini 生成 768 维向量并将文档插入 Supabase 进行语义搜索"
      },
      "typeVersion": 1
    },
    {
      "id": "677fd038-4cd9-483b-84ff-98373a6affb4",
      "name": "便签7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -480,
        944
      ],
      "parameters": {
        "color": 5,
        "width": 368,
        "height": 512,
        "content": "# 📁 Drive 到 Supabase 向量存储用于学习 RAG"
      },
      "typeVersion": 1
    },
    {
      "id": "975c4447-f0fe-48fd-afb9-e4da35b30080",
      "name": "便签8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -80,
        1280
      ],
      "parameters": {
        "width": 176,
        "height": 128,
        "content": "**触发器节点** - 当从另一个 n8N 工作流调用时启动工作流。接受 Drive 文件夹 URL 作为输入"
      },
      "typeVersion": 1
    },
    {
      "id": "a9cdb11e-fbb5-43b8-aa5d-6ea48be4fc85",
      "name": "便签9",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        160,
        1280
      ],
      "parameters": {
        "width": 150,
        "height": 128,
        "content": "**提取文件夹 ID** - 使用正则表达式解析 Google Drive URL 以提取用于 API 调用的文件夹/文件 ID"
      },
      "typeVersion": 1
    },
    {
      "id": "01282543-fd57-4815-af73-bf26a2ff4a12",
      "name": "便签 10",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        368,
        1280
      ],
      "parameters": {
        "width": 176,
        "content": "**初始化数据库** - 使用 pgvector 扩展和 match_documents 搜索函数创建 Supabase 向量表。⚠️ 删除现有表！"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "Calculator": {
      "ai_tool": [
        [
          {
            "node": "Study Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Download File": {
      "main": [
        [
          {
            "node": "Insert into Supabase Vectorstore",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "Download File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Code in JavaScript": {
      "main": [
        [
          {
            "node": "Execute a SQL query",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Execute a SQL query": {
      "main": [
        [
          {
            "node": "Search files and folders",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader2": {
      "ai_document": [
        [
          {
            "node": "Insert into Supabase Vectorstore",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Postgres Chat Memory": {
      "ai_memory": [
        [
          {
            "node": "Study Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Supabase Vector Store": {
      "ai_tool": [
        [
          {
            "node": "Study Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings Google Gemini": {
      "ai_embedding": [
        [
          {
            "node": "Supabase Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Study Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Search files and folders": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings Google Gemini4": {
      "ai_embedding": [
        [
          {
            "node": "Insert into Supabase Vectorstore",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Folder all file to vector": {
      "ai_tool": [
        [
          {
            "node": "Study Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Study Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Insert into Supabase Vectorstore": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When Executed by Another Workflow": {
      "main": [
        [
          {
            "node": "Code in JavaScript",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}