RAG Workflow For Company Documents stored in Google Drive

工作流概述

这是一个包含18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": "7cXvgkl9170QXzT2",
  "meta": {
    "instanceId": "69133932b9ba8e1ef14816d0b63297bb44feb97c19f759b5d153ff6b0c59e18d",
    "templateCredsSetupCompleted": true
  },
  "name": "RAG Workflow For Company Documents stored in Google Drive",
  "tags": [],
  "nodes": [
    {
      "id": "753455a3-ddc8-4a74-b043-70a0af38ff9e",
      "name": "Pinecone Vector Store",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        680,
        0
      ],
      "parameters": {
        "mode": "insert",
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "company-files",
          "cachedResultName": "company-files"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "bQTNry52ypGLqt47",
          "name": "PineconeApi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "a7c8fa7f-cad2-4497-a295-30aa2e98cacc",
      "name": "Embeddings Google Gemini",
      "type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
      "position": [
        640,
        280
      ],
      "parameters": {
        "modelName": "models/text-embedding-004"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "jLOqyTR4yTT1nYKi",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "215f0519-4359-4e4b-a90c-7e54b1cc52b5",
      "name": "Default Data Loader",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        840,
        220
      ],
      "parameters": {
        "options": {},
        "dataType": "binary",
        "binaryMode": "specificField"
      },
      "typeVersion": 1
    },
    {
      "id": "863d3d1d-1621-406e-8320-688f64b07b09",
      "name": "Recursive Character Text Splitter",
      "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
      "position": [
        820,
        420
      ],
      "parameters": {
        "options": {},
        "chunkOverlap": 100
      },
      "typeVersion": 1
    },
    {
      "id": "5af1efb1-ea69-466e-bb3b-2b7e6b1ceef7",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        420,
        840
      ],
      "parameters": {
        "options": {
          "systemMessage": "You are a helpful HR assistant designed to answer employee questions based on company policies.

Retrieve relevant information from the provided internal documents and provide a concise, accurate, and informative answer to the employee's question.

Use the tool called \"company_documents_tool\" to retrieve any information from the company's documents.

If the answer cannot be found in the provided documents, respond with \"I cannot find the answer in the available resources.\""
        }
      },
      "typeVersion": 1.7
    },
    {
      "id": "825632ac-1edf-4e63-948d-b1a498b2b962",
      "name": "Vector Store Tool",
      "type": "@n8n/n8n-nodes-langchain.toolVectorStore",
      "position": [
        820,
        1060
      ],
      "parameters": {
        "name": "company_documents_tool",
        "description": "Retrieve information from any company documents"
      },
      "typeVersion": 1
    },
    {
      "id": "72d2f685-bcc3-4e62-a5e3-72c0fe65f8e8",
      "name": "Pinecone Vector Store (Retrieval)",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        720,
        1240
      ],
      "parameters": {
        "options": {},
        "pineconeIndex": {
          "__rl": true,
          "mode": "list",
          "value": "company-files",
          "cachedResultName": "company-files"
        }
      },
      "credentials": {
        "pineconeApi": {
          "id": "bQTNry52ypGLqt47",
          "name": "PineconeApi account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "eeff81cb-6aec-4e7f-afe0-432d87085fb2",
      "name": "Embeddings Google Gemini (retrieval)",
      "type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
      "position": [
        700,
        1400
      ],
      "parameters": {
        "modelName": "models/text-embedding-004"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "jLOqyTR4yTT1nYKi",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "8bb6ebb1-1deb-498b-8da4-b809a736e097",
      "name": "Download File From Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        460,
        0
      ],
      "parameters": {
        "fileId": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $json.id }}"
        },
        "options": {
          "fileName": "={{ $json.name }}"
        },
        "operation": "download"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "uixLsi5TmrfwXPeB",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "bd83bacf-dff1-4b7c-af5c-b249fb16c113",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        420,
        660
      ],
      "parameters": {
        "content": "## Chat with company documents"
      },
      "typeVersion": 1
    },
    {
      "id": "7b90daab-0fb2-4c8a-93e6-b138bb04f282",
      "name": "Google Drive File Updated",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        140,
        140
      ],
      "parameters": {
        "event": "fileUpdated",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "1evDIoHePhjw_LgVFZXSZyK1sZm2GHp9W",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1evDIoHePhjw_LgVFZXSZyK1sZm2GHp9W",
          "cachedResultName": "INNOVI PRO"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "uixLsi5TmrfwXPeB",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "3a6c6cef-7a19-42ef-8092-eaf57dae4cdd",
      "name": "Google Drive File Created",
      "type": "n8n-nodes-base.googleDriveTrigger",
      "position": [
        140,
        -120
      ],
      "parameters": {
        "event": "fileCreated",
        "options": {
          "fileType": "all"
        },
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "mode": "list",
          "value": "1evDIoHePhjw_LgVFZXSZyK1sZm2GHp9W",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1evDIoHePhjw_LgVFZXSZyK1sZm2GHp9W",
          "cachedResultName": "INNOVI PRO"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "uixLsi5TmrfwXPeB",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "1e38f1c8-7bd0-4eeb-addc-62339582d350",
      "name": "Window Buffer Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        500,
        1140
      ],
      "parameters": {},
      "typeVersion": 1.3
    },
    {
      "id": "4b0ab858-99b1-4337-8c5c-a223519e3662",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        80,
        840
      ],
      "webhookId": "5f1c0c82-0ff9-40c7-9e2e-b1a96ffe24cd",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "bfb684d1-e5c1-41da-8305-b2606a2eade6",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        440,
        -240
      ],
      "parameters": {
        "width": 320,
        "content": "## Add docuemnts to vector store when updating or creating new documents in Google Drive"
      },
      "typeVersion": 1
    },
    {
      "id": "8f627ec6-4b3f-43ad-a4a3-e2b199a7fe58",
      "name": "Google Gemini Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        320,
        1140
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash-exp"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "jLOqyTR4yTT1nYKi",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "f2133a06-0088-46de-9f74-a3f9fe478f98",
      "name": "Google Gemini Chat Model (retrieval)",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        1080,
        1240
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash-exp"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "jLOqyTR4yTT1nYKi",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "578deb96-8393-4850-9757-fa97b2bc9992",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -540,
        220
      ],
      "parameters": {
        "width": 420,
        "height": 720,
        "content": "## Set up steps

1. Google Cloud Project and Vertex AI API:
* Create a Google Cloud project.
* Enable the Vertex AI API for your project.
2. Google AI API Key:
* Obtain a Google AI API key from Google AI Studio.
3. Pinecone Account:
* Create a free account on the Pinecone website.
Obtain your API key from your Pinecone dashboard.
* Create an index named company-files in your Pinecone project.
4. Google Drive:
* Create a dedicated folder in your Google Drive where company documents will be stored.
5. Credentials in n8n: Configure credentials in your n8n environment for:
* Google Drive OAuth2
* Google Gemini(PaLM) Api (using your Google AI API key)
* Pinecone API (using your Pinecone API key)
5. Import the Workflow:
* Import this workflow into your n8n instance.
6. Configure the Workflow:
* Update both Google Drive Trigger nodes to watch the specific folder you created in your Google Drive.
* Configure the Pinecone Vector Store nodes to use your company-files index."
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "33b252fb-5d87-4a29-a0a7-97308140699c",
  "connections": {
    "AI Agent": {
      "main": [
        []
      ]
    },
    "Vector Store Tool": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Default Data Loader": {
      "ai_document": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Window Buffer Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store": {
      "main": [
        []
      ]
    },
    "Embeddings Google Gemini": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive File Created": {
      "main": [
        [
          {
            "node": "Download File From Google Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive File Updated": {
      "main": [
        [
          {
            "node": "Download File From Google Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Download File From Google Drive": {
      "main": [
        [
          {
            "node": "Pinecone Vector Store",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Pinecone Vector Store (Retrieval)": {
      "ai_vectorStore": [
        [
          {
            "node": "Vector Store Tool",
            "type": "ai_vectorStore",
            "index": 0
          }
        ]
      ]
    },
    "Recursive Character Text Splitter": {
      "ai_textSplitter": [
        [
          {
            "node": "Default Data Loader",
            "type": "ai_textSplitter",
            "index": 0
          }
        ]
      ]
    },
    "Embeddings Google Gemini (retrieval)": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone Vector Store (Retrieval)",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model (retrieval)": {
      "ai_languageModel": [
        [
          {
            "node": "Vector Store Tool",
            "type": "ai_languageModel",
            "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.Vectorstorepinecone
  • @N8N/N8N Nodes Langchain.Embeddingsgooglegemini
  • @N8N/N8N Nodes Langchain.Documentdefaultdataloader
  • @N8N/N8N Nodes Langchain.Textsplitterrecursivecharactertextsplitter
  • @N8N/N8N Nodes Langchain.Agent

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