8
n8n 中文网amn8n.com

使用GPT-4.1-mini、Firecrawl和Parsera将网站转换为LLM就绪知识库

高级

这是一个Document Extraction, Multimodal AI领域的自动化工作流,包含 31 个节点。主要使用 Set, Switch, SplitOut, FormTrigger, GoogleDrive 等节点。 使用GPT-4.1-mini、Firecrawl和Parsera将网站转换为LLM就绪知识库

前置要求
  • Google Drive API 凭证
  • 可能需要目标 API 的认证凭证
  • OpenAI API Key
工作流预览
可视化展示节点连接关系,支持缩放和平移
导出工作流
复制以下 JSON 配置到 n8n 导入,即可使用此工作流
{
  "meta": {
    "instanceId": "e21602a60af95b2f6a741aeb0ba95f15a50867a8994589d27a7ce1aff165214f",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "3bef4e97-a7da-43fd-8c79-5d8e8e86e758",
      "name": "Firecrawl — 映射 URL",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1360,
        464
      ],
      "parameters": {},
      "typeVersion": 4.2
    },
    {
      "id": "a76a3be4-21b1-44c7-9fea-f50a8907012f",
      "name": "触发器 — 表单(创建 LLM 知识库)",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        576,
        656
      ],
      "webhookId": "68210f53-e28b-4494-846b-826dae5864e8",
      "parameters": {},
      "typeVersion": 2.2
    },
    {
      "id": "1df831e1-a6e6-4c52-82c4-fb6647bafa2d",
      "name": "决策 — 生成对象",
      "type": "n8n-nodes-base.switch",
      "position": [
        1024,
        656
      ],
      "parameters": {},
      "typeVersion": 3.2
    },
    {
      "id": "0fc52950-ee21-4bfc-a1f3-a593c38df6c2",
      "name": "提取 Markdown (Parsera)",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        2176,
        464
      ],
      "parameters": {},
      "executeOnce": false,
      "typeVersion": 4.2
    },
    {
      "id": "8c33ee13-1f85-4273-9bd5-f36c397682cd",
      "name": "提取 Markdown (Parsera - 单文件)",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1456,
        864
      ],
      "parameters": {},
      "executeOnce": false,
      "typeVersion": 4.2
    },
    {
      "id": "3ef6a196-2411-4099-8147-07a411c771ee",
      "name": "批量 URL 处理器",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        1824,
        464
      ],
      "parameters": {},
      "typeVersion": 3
    },
    {
      "id": "7fb54ed0-9454-4424-9c71-47bc1cd9f18b",
      "name": "文件字段(单文件)",
      "type": "n8n-nodes-base.set",
      "position": [
        2208,
        864
      ],
      "parameters": {},
      "typeVersion": 3.4
    },
    {
      "id": "efd237b7-9de2-4822-ad24-b60d9b27910f",
      "name": "转换为 TXT(单文件)",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        2448,
        864
      ],
      "parameters": {},
      "typeVersion": 1.1
    },
    {
      "id": "5a14732e-5b18-48b7-b5a8-efa296a81bc4",
      "name": "Google Drive — 上传到文件夹(批量)",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        3344,
        464
      ],
      "parameters": {},
      "typeVersion": 3
    },
    {
      "id": "0a54f878-809f-48e1-a085-9480130fbd53",
      "name": "Google Drive — 上传到文件夹(单文件)",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        2704,
        864
      ],
      "parameters": {},
      "typeVersion": 3
    },
    {
      "id": "ed0dfad5-cdd1-47ba-9abb-e4e33ab80f02",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        416,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "6ccd544e-e8e2-45f0-b6d9-7d8fc73696aa",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        896,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "9fc35c56-9e4d-437b-bc3a-f387858885c3",
      "name": "便签2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1296,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "3b0aad63-08cd-4d52-9fa7-bb274a2363d8",
      "name": "拆分 URL",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        1584,
        464
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "67f5a789-8b0b-4976-b4ef-3dc7972bc35d",
      "name": "便签3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1744,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "2f361dc6-5b94-4dc8-a038-e4a71272391e",
      "name": "便签4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2064,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "6ff60d34-ad5d-4004-b203-3b8213df8839",
      "name": "便签5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2416,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "b9ca354a-8c4f-4739-8ace-c9b794441b31",
      "name": "文件字段(批量)",
      "type": "n8n-nodes-base.set",
      "position": [
        2864,
        464
      ],
      "parameters": {},
      "typeVersion": 3.4
    },
    {
      "id": "486eb863-6e7a-48a8-8ee7-687a6e08cec8",
      "name": "便签6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2800,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "50a49375-ca0b-4fec-8a9f-eb0502f31d61",
      "name": "便签7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3040,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "cbbbefb9-aea7-45c3-8e69-dec9c7817ce5",
      "name": "转换为 TXT(批量)",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        3104,
        464
      ],
      "parameters": {},
      "typeVersion": 1.1
    },
    {
      "id": "69f11351-b5e4-4354-adc5-1bfb92de0f27",
      "name": "便签8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3280,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "756cc348-42cc-40fc-b8e4-f1eab1412f18",
      "name": "### 替换 Airtable 连接",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1296,
        672
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "bfcc459a-1e67-47fa-8f5a-1178f5e853dd",
      "name": "便签10",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1760,
        672
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "69e8b664-00d4-4333-95ee-aa16c2bdb8bf",
      "name": "LLMs.txt 生成器 (OpenAI - 单文件)",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        1808,
        864
      ],
      "parameters": {},
      "executeOnce": false,
      "typeVersion": 1.8
    },
    {
      "id": "1f21ca3f-73a2-49aa-8b0a-dd0e396b84d5",
      "name": "LLMs.txt 生成器 (OpenAI - 批量)",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        2464,
        464
      ],
      "parameters": {},
      "executeOnce": false,
      "typeVersion": 1.8
    },
    {
      "id": "3ca47f8b-6678-4c81-858c-e63048cc0eb4",
      "name": "便签11",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2144,
        672
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "33a33453-8133-4033-b62e-1cd3323aaff3",
      "name": "便签12",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2384,
        672
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "ac22d369-6197-40dc-8703-46dbc99bbc31",
      "name": "便签13",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2624,
        672
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "8e173347-80c2-4c48-aa4b-4348785a32a7",
      "name": "便签14",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1056,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    },
    {
      "id": "c7cf05cf-d8b7-4350-8778-6ee4fb7bbfd8",
      "name": "便签15",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -576,
        224
      ],
      "parameters": {
        "content": ""
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "Split URLs": {
      "main": [
        [
          {
            "node": "Batch URL Processor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Batch URL Processor": {
      "main": [
        [],
        [
          {
            "node": "Extract Markdown (Parsera)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "File Fields (Batch)": {
      "main": [
        [
          {
            "node": "Convert to TXT (Batch)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "File Fields (Single)": {
      "main": [
        [
          {
            "node": "Convert to TXT (Single)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert to TXT (Batch)": {
      "main": [
        [
          {
            "node": "Google Drive — Upload to folder (Batch)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Firecrawl — Map URLs": {
      "main": [
        [
          {
            "node": "Split URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert to TXT (Single)": {
      "main": [
        [
          {
            "node": "Google Drive — Upload to folder(Single)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Decision — Generate For": {
      "main": [
        [
          {
            "node": "Firecrawl — Map URLs",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract Markdown (Parsera - Single)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Markdown (Parsera)": {
      "main": [
        [
          {
            "node": "LLMs.txt Generator (OpenAI - Batch)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Trigger — Form (Create LLM KB)": {
      "main": [
        [
          {
            "node": "Decision — Generate For",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Markdown (Parsera - Single)": {
      "main": [
        [
          {
            "node": "LLMs.txt Generator (OpenAI - Single)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "LLMs.txt Generator (OpenAI - Batch)": {
      "main": [
        [
          {
            "node": "File Fields (Batch)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "LLMs.txt Generator (OpenAI - Single)": {
      "main": [
        [
          {
            "node": "File Fields (Single)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Drive — Upload to folder (Batch)": {
      "main": [
        [
          {
            "node": "Batch URL Processor",
            "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, 多模态 AI

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。

工作流信息
难度等级
高级
节点数量31
分类2
节点类型10
难度说明

适合高级用户,包含 16+ 个节点的复杂工作流

外部链接
在 n8n.io 查看

分享此工作流