Vector DB Loader from Google Drive

工作流概述

这是一个包含15个节点的复杂工作流，主要用于自动化处理各种任务。

工作流源代码

下载 
{
  "id": "WceMkVib0VLlF1BZ",
  "meta": {
    "instanceId": "ecc960f484e18b0e09045fd93acf0d47f4cfff25cc212ea348a08ac3aae81850",
    "templateCredsSetupCompleted": true
  },
  "name": "Vector DB Loader from Google Drive",
  "tags": [
    {
      "id": "6rb8rVhKZj4t0Kne",
      "name": "Current",
      "createdAt": "2025-02-04T18:13:17.427Z",
      "updatedAt": "2025-02-04T18:13:17.427Z"
    }
  ],
  "nodes": [
    {
      "id": "6652e41a-d14a-4e17-9dcd-34df114d219a",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        1240,
        1100
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "8ae38b72-52fd-46bc-ab47-50bebe5ac4ee",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        1320,
        1300
      ],
      "parameters": {
        "options": {},
        "chunkOverlap": 50
      },
      "typeVersion": 1
    },
    {
      "id": "57ce64af-88d4-4dc4-8c8e-01717c1bd47d",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        1120,
        1100
      ],
      "parameters": {
        "model": "text-embedding-3-small",
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "fzLcLisovaZjIqma",
          "name": "AlexK OpenAi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "e6bed8bc-f629-41fd-aa6e-9158b1cbc323",
      "name": "Postgres PGVector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
      "position": [
        1140,
        880
      ],
      "parameters": {
        "mode": "insert",
        "options": {
          "collection": {
            "values": {
              "useCollection": true,
              "collectionName": "n8n_wfs"
            }
          }
        },
        "tableName": "n8n_vectors_wfs"
      },
      "credentials": {
        "postgres": {
          "id": "UkNm7VVkmuXOwMVa",
          "name": "KBB Postgres account"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "96fbc1f3-920d-44c9-9314-742efa3a698a",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -280,
        740
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "4cd7a934-04cc-47b5-a771-db554680ba77",
      "name": "Loop Over Items",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        160,
        740
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "778593d8-fe1c-4eb9-865a-e6ce9ed5f900",
      "name": "Move File",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        1500,
        880
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $('Loop Over Items').item.json.id }}"
        },
        "driveId": {
          "__rl": true,
          "mode": "list",
          "value": "My Drive"
        },
        "folderId": {
          "__rl": true,
          "mode": "list",
          "value": "1Re6vg-PZxBoUU6sTRDbGs-77bAJ40u8F",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1Re6vg-PZxBoUU6sTRDbGs-77bAJ40u8F",
          "cachedResultName": "vectorized"
        },
        "operation": "move"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "kxXwhBLKOmB8CkBW",
          "name": "AlexK Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "3a6584f5-ed86-4900-9177-40ffe82d0ad3",
      "name": "Download File",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        380,
        680
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {},
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "kxXwhBLKOmB8CkBW",
          "name": "AlexK Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "e1931ab6-4391-46c3-9d7d-22cbfbf90327",
      "name": "Search Folder",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -60,
        740
      ],
      "parameters": {
        "filter": {
          "folderId": {
            "__rl": true,
            "mode": "list",
            "value": "1mBHrP8UzUnfn3dj_3QS1r0XhQQyVPAGX",
            "cachedResultUrl": "https://drive.google.com/drive/folders/1mBHrP8UzUnfn3dj_3QS1r0XhQQyVPAGX",
            "cachedResultName": "n8n Workflow JSON Files"
          },
          "whatToSearch": "files"
        },
        "options": {},
        "resource": "fileFolder",
        "returnAll": true
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "kxXwhBLKOmB8CkBW",
          "name": "AlexK Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "95134ab4-806f-4c47-96a6-e261b3176ebf",
      "name": "Schedule Trigger",
      "type": "n8n-nodes-base.scheduleTrigger",
      "position": [
        -280,
        940
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "triggerAtHour": 3
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "0fe604ed-e886-4aa3-856f-c46fb79ce0de",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1700,
        960
      ],
      "parameters": {
        "color": 7,
        "width": 380,
        "height": 240,
        "content": "## Creative Commons License
*License*: **Creative Commons Attribution-ShareAlike 4.0 International** (CC BY-SA 4.0)

*Author*: **AlexK1919**
You are free to use, adapt, and share this workflow—even commercially—under the terms of this license.

Full license details: https://creativecommons.org/licenses/by-sa/4.0/"
      },
      "typeVersion": 1
    },
    {
      "id": "f8055452-b487-46c7-92fe-14b3c88d193f",
      "name": "Switch",
      "type": "n8n-nodes-base.switch",
      "position": [
        560,
        680
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "outputKey": "pdf",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "7b4e792b-ab6d-4b9b-88a1-d8e51bea6853",
                    "operator": {
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{$binary[\"data\"].mimeType}}",
                    "rightValue": "application/pdf"
                  }
                ]
              },
              "renameOutput": true
            },
            {
              "outputKey": "text",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "09b7d7c5-5353-4719-b4e2-072e4da39948",
                    "operator": {
                      "name": "filter.operator.equals",
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{$binary[\"data\"].mimeType}}",
                    "rightValue": "text/plain"
                  }
                ]
              },
              "renameOutput": true
            },
            {
              "outputKey": "json",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "d2763a45-a592-47c8-868f-59dfcd17a71c",
                    "operator": {
                      "name": "filter.operator.equals",
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{$binary[\"data\"].mimeType}}",
                    "rightValue": "application/json"
                  }
                ]
              },
              "renameOutput": true
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.2
    },
    {
      "id": "c704f48e-a1f5-4539-bde2-545862d21bc6",
      "name": "Extract from PDF",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        780,
        480
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "63b3a751-5726-4821-8379-72af15226584",
      "name": "Extract from Text",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        780,
        680
      ],
      "parameters": {
        "options": {},
        "operation": "text"
      },
      "typeVersion": 1
    },
    {
      "id": "44a5980a-17aa-4a09-8040-a7d9804c7998",
      "name": "Extract from JSON",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        780,
        880
      ],
      "parameters": {
        "options": {},
        "operation": "fromJson"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "timezone": "America/Los_Angeles",
    "callerPolicy": "workflowsFromSameOwner",
    "errorWorkflow": "lYgdNzdEapw2W8gK",
    "executionOrder": "v1"
  },
  "versionId": "4f54c70a-b18b-4e4c-8959-ace70dd41218",
  "connections": {
    "Switch": {
      "main": [
        [
          {
            "node": "Extract from PDF",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract from Text",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract from JSON",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Move File": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Download File": {
      "main": [
        [
          {
            "node": "Switch",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Search Folder": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "Download File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from PDF": {
      "main": [
        [
          {
            "node": "Postgres PGVector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Schedule Trigger": {
      "main": [
        [
          {
            "node": "Search Folder",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings OpenAI": {
      "ai_embedding": [
        [
          {
            "node": "Postgres PGVector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Extract from JSON": {
      "main": [
        [
          {
            "node": "Postgres PGVector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from Text": {
      "main": [
        [
          {
            "node": "Postgres PGVector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Postgres PGVector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Postgres PGVector Store": {
      "main": [
        [
          {
            "node": "Move File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Recursive Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Search Folder",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

功能特点

  • 自动检测新邮件
  • AI智能内容分析
  • 自定义分类规则
  • 批量处理能力
  • 详细的处理日志

技术分析

节点类型及作用

  • @N8N/N8N Nodes Langchain.Documentdefaultdataloader
  • @N8N/N8N Nodes Langchain.Textsplitterrecursivecharactertextsplitter
  • @N8N/N8N Nodes Langchain.Embeddingsopenai
  • @N8N/N8N Nodes Langchain.Vectorstorepgvector
  • Manualtrigger

复杂度评估

配置难度：
★★★★☆
维护难度：
★★☆☆☆
扩展性：
★★★★☆

实施指南

前置条件

  • 有效的Gmail账户
  • n8n平台访问权限
  • Google API凭证
  • AI分类服务订阅

配置步骤

  1. 在n8n中导入工作流JSON文件
  2. 配置Gmail节点的认证信息
  3. 设置AI分类器的API密钥
  4. 自定义分类规则和标签映射
  5. 测试工作流执行
  6. 配置定时触发器（可选）

关键参数

参数名称 默认值 说明
maxEmails 50 单次处理的最大邮件数量
confidenceThreshold 0.8 分类置信度阈值
autoLabel true 是否自动添加标签

最佳实践

优化建议

  • 定期更新AI分类模型以提高准确性
  • 根据邮件量调整处理批次大小
  • 设置合理的分类置信度阈值
  • 定期清理过期的分类规则

安全注意事项

  • 妥善保管API密钥和认证信息
  • 限制工作流的访问权限
  • 定期审查处理日志
  • 启用双因素认证保护Gmail账户

性能优化

  • 使用增量处理减少重复工作
  • 缓存频繁访问的数据
  • 并行处理多个邮件分类任务
  • 监控系统资源使用情况

故障排除

常见问题

邮件未被正确分类

检查AI分类器的置信度阈值设置，适当降低阈值或更新训练数据。

Gmail认证失败

确认Google API凭证有效且具有正确的权限范围，重新进行OAuth授权。

调试技巧

  • 启用详细日志记录查看每个步骤的执行情况
  • 使用测试邮件验证分类逻辑
  • 检查网络连接和API服务状态
  • 逐步执行工作流定位问题节点

错误处理

工作流包含以下错误处理机制：

  • 网络超时自动重试（最多3次）
  • API错误记录和告警
  • 处理失败邮件的隔离机制
  • 异常情况下的回滚操作