8
n8n 中文网amn8n.com

从网站获取所有页面内容并存储至Pinecone的Gemini嵌入

高级

这是一个Document Extraction, AI RAG领域的自动化工作流，包含 16 个节点。主要使用 Xml, Code, Html, Wait, Merge 等节点。 从网站获取所有页面内容并存储至Pinecone的Gemini嵌入

前置要求
  • •可能需要目标 API 的认证凭证
  • •Pinecone API Key

使用的节点 (16)

Xml
Code
Html
Wait
Merge
Switch
StickyNote
FormTrigger
HttpRequest
SplitInBatches
RemoveDuplicates
VectorStorePinecone
EmbeddingsGoogleGemini
DocumentDefaultDataLoader

分类

文档提取
AI RAG 检索增强
工作流预览
可视化展示节点连接关系，支持缩放和平移
React Flow
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
  "nodes": [
    {
      "id": "5ad6a510-3c4a-47e4-b8ff-c0e565e25d25",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        368,
        944
      ],
      "parameters": {
        "width": 832,
        "height": 816,
        "content": "此 n8n 工作流从网站内容构建 Pinecone 知识库，同时处理站点地图和直接 URL 输入。"
      },
      "typeVersion": 1
    },
    {
      "id": "3ff777b7-24bd-420c-af38-62a395f52a1a",
      "name": "提取页面 URL",
      "type": "n8n-nodes-base.code",
      "position": [
        1936,
        1392
      ],
      "parameters": {
        "jsCode": "const items = []\nfor (const item of $input.first().json.urlset.url) {\n  items.push({ url: item.loc })\n}\n\nreturn items;"
      },
      "typeVersion": 2
    },
    {
      "id": "6176e651-cef5-44e8-abed-0f6f6b81517b",
      "name": "XML 转换",
      "type": "n8n-nodes-base.xml",
      "position": [
        1792,
        1392
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "cca1e7e7-32f6-42fd-b23c-3c2586344a50",
      "name": "获取站点地图",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1632,
        1392
      ],
      "parameters": {
        "url": "={{ $json['Sitemap URL'] }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "520e131d-b5f2-4857-aebd-5724da2a8083",
      "name": "拆分页面 URL",
      "type": "n8n-nodes-base.code",
      "position": [
        1792,
        1216
      ],
      "parameters": {
        "jsCode": "function addTrailingSlash(str) {\n  if (typeof str !== 'string') {\n    return str; // Or throw an error, handle non-string inputs\n  }\n  if (!str.endsWith('/')) {\n    return str + '/';\n  }\n  return str;\n}\n\nconst urls = []\nfor (const item of $input.first().json['Page URLs'].split(',')) {\n  urls.push({ url: addTrailingSlash(item).trim()})\n}\n\nreturn urls;"
      },
      "typeVersion": 2
    },
    {
      "id": "7e7fe528-8748-470b-b627-a0c79b5aface",
      "name": "合并 URL",
      "type": "n8n-nodes-base.merge",
      "position": [
        2128,
        1232
      ],
      "parameters": {},
      "typeVersion": 3.2
    },
    {
      "id": "a0517aaf-6ccd-481d-b97e-b183d305451b",
      "name": "移除重复 URL",
      "type": "n8n-nodes-base.removeDuplicates",
      "position": [
        2272,
        1232
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 2
    },
    {
      "id": "72c85ccf-a9d6-42b1-85a7-76800ba831e5",
      "name": "循环处理页面 URL",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        2480,
        1232
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "73aebd19-60ae-40d1-a747-0b9537d9d67c",
      "name": "提取内容",
      "type": "n8n-nodes-base.html",
      "position": [
        2672,
        1136
      ],
      "parameters": {
        "options": {
          "cleanUpText": true
        },
        "operation": "extractHtmlContent",
        "extractionValues": {
          "values": [
            {
              "key": "content",
              "cssSelector": "body",
              "skipSelectors": "img"
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "0dbf70c1-cb57-4691-916f-2a2aa9a4cec0",
      "name": "获取页面 HTML 内容",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        2672,
        1328
      ],
      "parameters": {
        "url": "={{ $json.url }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "fa1c18c6-6c29-4e71-905e-0945909af99b",
      "name": "等待 5 秒",
      "type": "n8n-nodes-base.wait",
      "position": [
        2832,
        1328
      ],
      "webhookId": "9d87e60f-9df8-4a13-9c22-e3e5a5bb9c0e",
      "parameters": {},
      "typeVersion": 1.1
    },
    {
      "id": "2bf3ad7f-a2fd-44f9-b6af-5a500ef80591",
      "name": "数据加载器",
      "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
      "position": [
        3264,
        1344
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "a86d4c2e-559c-4942-ac0d-2ddcc7eb7f39",
      "name": "Gemini 嵌入",
      "type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
      "position": [
        3072,
        1344
      ],
      "parameters": {
        "modelName": "models/gemini-embedding-001"
      },
      "typeVersion": 1
    },
    {
      "id": "f46188bd-c0a2-4d49-9b67-0937f891ae36",
      "name": "Pinecone 知识库",
      "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
      "position": [
        3072,
        1136
      ],
      "parameters": {
        "mode": "insert",
        "options": {
          "clearNamespace": true
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "4f5dc6e3-8f75-46ab-b3e1-49deb7695469",
      "name": "输入站点地图或页面 URL",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        1296,
        1376
      ],
      "webhookId": "ab54a2cd-2eda-4cf7-b822-8fb49ecb257e",
      "parameters": {
        "options": {},
        "formTitle": "Agent Knowledge Base Input",
        "formFields": {
          "values": [
            {
              "fieldLabel": "Sitemap URL",
              "placeholder": "https://website.com/page-sitemap.xml"
            },
            {
              "fieldType": "textarea",
              "fieldLabel": "Page URLs",
              "placeholder": "https://website.com/about, https://website.com/contact"
            }
          ]
        },
        "formDescription": "This form is to input the page sitemap or pages of your website"
      },
      "typeVersion": 2.2
    },
    {
      "id": "67f6e98a-946c-4460-93d4-707511deb4f5",
      "name": "条件分支",
      "type": "n8n-nodes-base.switch",
      "position": [
        1440,
        1376
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "2af7e15b-2e56-40e5-addc-74bd0b4de214",
                    "operator": {
                      "type": "string",
                      "operation": "notEmpty",
                      "singleValue": true
                    },
                    "leftValue": "={{ $json['Page URLs'] }}",
                    "rightValue": ""
                  }
                ]
              }
            },
            {
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "02899ab6-0c0b-4c0f-89ad-ec5787da36eb",
                    "operator": {
                      "type": "string",
                      "operation": "endsWith"
                    },
                    "leftValue": "={{ $json['Sitemap URL'] }}",
                    "rightValue": "xml"
                  }
                ]
              }
            }
          ]
        },
        "options": {
          "allMatchingOutputs": true
        }
      },
      "typeVersion": 3.2
    }
  ],
  "connections": {
    "Switch": {
      "main": [
        [
          {
            "node": "Split Pages URL",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Fetch Sitemap",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Merge URLs": {
      "main": [
        [
          {
            "node": "Remove Duplicate URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait 5 sec": {
      "main": [
        [
          {
            "node": "Loop Over Page URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Data Loader": {
      "ai_document": [
        [
          {
            "node": "Pinecone KnowledgeBase",
            "type": "ai_document",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Sitemap": {
      "main": [
        [
          {
            "node": "XML Conversion",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "XML Conversion": {
      "main": [
        [
          {
            "node": "Extract Page URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Content": {
      "main": [
        [
          {
            "node": "Pinecone KnowledgeBase",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Pages URL": {
      "main": [
        [
          {
            "node": "Merge URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Page URLs": {
      "main": [
        [
          {
            "node": "Merge URLs",
            "type": "main",
            "index": 1
          }
        ]
      ]
    },
    "Gemini Embeddings": {
      "ai_embedding": [
        [
          {
            "node": "Pinecone KnowledgeBase",
            "type": "ai_embedding",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Page URLs": {
      "main": [
        [
          {
            "node": "Extract Content",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Fetch Page HTML For content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Remove Duplicate URLs": {
      "main": [
        [
          {
            "node": "Loop Over Page URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Input Sitemap or page urls": {
      "main": [
        [
          {
            "node": "Switch",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Page HTML For content": {
      "main": [
        [
          {
            "node": "Wait 5 sec",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
常见问题

如何使用这个工作流？

复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。

这个工作流适合什么场景？

高级 - 文档提取, AI RAG 检索增强

需要付费吗？

本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。

相关工作流推荐

基于AI的WhatsApp支持机器人（Google Sheets工单创建）
基于AI的WhatsApp支持机器人（Google Sheets工单创建）
Set
Xml
Code
+20
35 节点Zain Khan
客服机器人
在可视化参考库中探索n8n节点
在可视化参考库中探索n8n节点
If
Ftp
Set
+93
113 节点I versus AI
其他
PDF 转订单
使用AI将PDF采购订单自动化转换为Adobe Commerce销售订单
If
Set
Code
+19
96 节点JKingma
文档提取
API架构提取器
API架构提取器
If
Set
Code
+22
88 节点Polina Medvedieva
工程
使用GPT-4.1、Outlook和Mem.ai自动化Microsoft Teams会议分析
使用GPT-4.1、Outlook和Mem.ai自动化Microsoft Teams会议分析
If
Set
Code
+19
61 节点Wayne Simpson
人力资源
WordPress博客自动化专业版（深度研究）v2.1市场
使用GPT-4o、Perplexity AI和多语言支持自动化SEO优化的博客创建
If
Set
Xml
+27
125 节点Daniel Ng
内容创作
工作流信息
难度等级
高级
节点数量16
分类2
节点类型14
难度说明

适合高级用户，包含 16+ 个节点的复杂工作流

作者
Zain Khan

Zain Khan

@zain

I partner with businesses to streamline processes and accelerate growth through intelligent AI automation and Web/mobile Development. Leveraging deep expertise in GPT-4, LangChain, and n8n, I develop AI-powered agents and sophisticated LLM pipelines.

外部链接
在 n8n.io 查看 →

分享此工作流