1- AI 最强辅助！n8n+crawl4ai 工作流，一键抓取任意网站！搭建 RAG 知识库 +MCP 自动化

1.1- 用到的工具 & 资源

n8n 👉 https://github.com/n8n-io/n8n
crawl4ai 👉 https://github.com/unclecode/crawl4ai
工作流文件 + 操作命令：👉 https://pan.quark.cn/s/632c4d164cce
Cherry Studio 👉 https://pan.quark.cn/s/d1416ba85367
生成 sitemap：👉 https://www.xml-sitemaps.com/

1.2- docker 命令

如果是在 Windows cmd 中，则需要使用 ^ 进行换行

在 PowerShell 中，需要使用反引号 (`) 进行换行

docker run -it --rm \
  --name n8n \
  -p 5678:5678 \
  -v n8n_data:/home/node/.n8n \
  -v ~/Downloads/md:/home/node \
  -e N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true \
  docker.n8n.io/n8nio/n8n //自动下载镜像，如果已存在就不下载

docker pull unclecode/crawl4ai:all-amd64(或all-arm64)

docker run --rm -it \
  -e CRAWL4AI_API_TOKEN=12345 \
  -p 11235:11235 \
  unclecode/crawl4ai:all-amd64

1.2- temple

{
  "name": "My workflow 7",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.1,
      "position": [
        -2880,
        480
      ],
      "id": "d09804e2-33b1-42f0-b45a-31baf26ee405",
      "name": "When chat message received",
      "webhookId": "0f5fbbdf-2d53-4b73-bbba-22622396cf46"
    },
    {
      "parameters": {
        "url": "={{ $json.chatInput }}",
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -2700,
        440
      ],
      "id": "50d24ace-15ad-4753-ae15-616170e0cf5f",
      "name": "HTTP Request"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.xml",
      "typeVersion": 1,
      "position": [
        -2500,
        420
      ],
      "id": "03eb1d75-261b-4b10-aecc-df95eb8841ec",
      "name": "XML"
    },
    {
      "parameters": {
        "fieldToSplitOut": "urlset.url",
        "options": {}
      },
      "type": "n8n-nodes-base.splitOut",
      "typeVersion": 1,
      "position": [
        -2320,
        460
      ],
      "id": "6a0a6c98-a3d5-4c26-9ab6-51c86db5b7b8",
      "name": "Split Out"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-base.limit",
      "typeVersion": 1,
      "position": [
        -2120,
        440
      ],
      "id": "c59e41cc-3961-49c2-bf97-0a8f9b6f66e0",
      "name": "Limit"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.splitInBatches",
      "typeVersion": 3,
      "position": [
        -1920,
        420
      ],
      "id": "e6d5c36d-8d0d-47fa-b9d5-00dde67604c3",
      "name": "Loop Over Items"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://host.docker.internal:11235/crawl",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "urls",
              "value": "={{ $json.loc }}"
            },
            {
              "name": "priority",
              "value": "10"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -1640,
        440
      ],
      "id": "c4e4e8e6-0c7a-425b-9c37-457910ccf2df",
      "name": "HTTP Request1",
      "credentials": {
        "httpHeaderAuth": {
          "id": "57vY2EUtpziMydLC",
          "name": "Header Auth account 2"
        }
      }
    },
    {
      "parameters": {
        "amount": 6
      },
      "type": "n8n-nodes-base.wait",
      "typeVersion": 1.1,
      "position": [
        -1200,
        420
      ],
      "id": "6d8dfa71-f81a-449c-bab1-441a439958e2",
      "name": "Wait",
      "webhookId": "c8186be7-9578-4621-b806-25036f990025"
    },
    {
      "parameters": {
        "url": "=http://host.docker.internal:11235/task/{{ $json.task_id }}",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        -1000,
        380
      ],
      "id": "493eb051-d2b3-4753-8236-434a19c8ab9b",
      "name": "HTTP Request2",
      "credentials": {
        "httpHeaderAuth": {
          "id": "57vY2EUtpziMydLC",
          "name": "Header Auth account 2"
        }
      }
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict",
            "version": 2
          },
          "conditions": [
            {
              "id": "807b8fa3-6760-4a9e-aeb3-6c891e0a01b8",
              "leftValue": "={{ $json.status }}",
              "rightValue": "completed",
              "operator": {
                "type": "string",
                "operation": "equals",
                "name": "filter.operator.equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "type": "n8n-nodes-base.if",
      "typeVersion": 2.2,
      "position": [
        -760,
        420
      ],
      "id": "224c43f8-6848-4631-b49b-3ab80707632c",
      "name": "If"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "=角色设定：\n你是一名信息结构化和知识库开发的专家，请始终保持专业态度。你的任务是将 markdown 数据整理为适合 LLM 驱动的 RAG 知识库的结构化、易读格式。\n\n任务要求：  \n\n1. 内容解析  \n   - 识别 markdown 数据中的关键内容和主要结构。  \n\n2. 结构化整理  \n   - 以清晰的标题和分层逻辑组织信息，使其易于检索和理解。  \n   - 保留所有可能对回答用户查询有价值的细节。  \n\n3. 创建 FAQ（如适用）  \n   - 根据内容提炼出常见问题，并提供清晰、直接的解答。  \n\n4. 提升可读性  \n   - 采用项目符号、编号列表、段落分隔等格式优化排版，使内容更直观。  \n\n5. 优化输出  \n   - 严格去除 AI 生成的附加说明，仅保留清理后的核心数据。 \n\n响应规则：  \n\n1. 完整性：确保所有相关信息完整保留，避免丢失对搜索和理解有价值的内容。  \n2. 精准性：FAQ 需紧密围绕内容，确保清晰、简洁且符合用户需求。  \n3. 结构优化：确保最终输出便于分块存储、向量化处理，并支持高效检索。\n\n数据输入：\n<markdown>{{ $json.result.markdown }}</markdown>\n",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.8,
      "position": [
        -580,
        280
      ],
      "id": "702abaf7-42bb-4c5f-8515-4004e48c4e15",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "5bb8dde4-4808-4005-94a3-56a8e88567a4",
              "name": "task_id",
              "value": "={{ $('HTTP Request1').item.json.task_id }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        -600,
        500
      ],
      "id": "1dce6569-d835-4f7a-9f1d-e9ffae461b1a",
      "name": "Edit Fields"
    },
    {
      "parameters": {
        "operation": "toText",
        "sourceProperty": "output",
        "options": {
          "fileName": "={{new Date().toISOString()}}.md"
        }
      },
      "type": "n8n-nodes-base.convertToFile",
      "typeVersion": 1.1,
      "position": [
        -200,
        120
      ],
      "id": "f6328bbf-a99f-49fc-8773-6e58279e034b",
      "name": "Convert to File"
    },
    {
      "parameters": {
        "operation": "write",
        "fileName": "=/home/node/{{new Date().toISOString()}}.md",
        "options": {}
      },
      "type": "n8n-nodes-base.readWriteFile",
      "typeVersion": 1,
      "position": [
        0,
        0
      ],
      "id": "35b693a2-6594-4864-ac7a-9f8d9bf467b2",
      "name": "Read/Write Files from Disk"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-base.wait",
      "typeVersion": 1.1,
      "position": [
        -1480,
        520
      ],
      "id": "93f64e97-b9e8-403b-8853-82f278bd968a",
      "name": "Wait1",
      "webhookId": "ea1444ec-e5d8-44b5-9fed-22e72793c219"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "=把{{ $json.output }}写入/home/node/{{new Date().toISOString()}}.md文件中",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.8,
      "position": [
        -180,
        -420
      ],
      "id": "5092c114-9c11-4ca6-a9a5-0f01a19872a3",
      "name": "AI Agent1"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-mcp.mcpClientTool",
      "typeVersion": 1,
      "position": [
        100,
        -180
      ],
      "id": "e1c475d2-6fa2-495c-b586-bf5f29cedb9f",
      "name": "MCP Client",
      "credentials": {
        "mcpClientApi": {
          "id": "kSc1ABvxzdmYzMz4",
          "name": "MCP Client (STDIO) account"
        }
      }
    },
    {
      "parameters": {
        "operation": "executeTool",
        "toolName": "=write_file",
        "toolParameters": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Tool_Parameters', ``, 'json') }}"
      },
      "type": "n8n-nodes-mcp.mcpClientTool",
      "typeVersion": 1,
      "position": [
        -40,
        -180
      ],
      "id": "fc80f903-b284-4a33-bcd3-6421eb674b70",
      "name": "MCP Client1",
      "credentials": {
        "mcpClientApi": {
          "id": "kSc1ABvxzdmYzMz4",
          "name": "MCP Client (STDIO) account"
        }
      }
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatDeepSeek",
      "typeVersion": 1,
      "position": [
        -460,
        500
      ],
      "id": "f3ee5841-27a7-4a37-ab2a-8bae52baed67",
      "name": "DeepSeek Chat Model",
      "credentials": {
        "deepSeekApi": {
          "id": "r18ROW1LYH3RRIFM",
          "name": "DeepSeek account"
        }
      }
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatDeepSeek",
      "typeVersion": 1,
      "position": [
        -200,
        -200
      ],
      "id": "48650f4b-05a5-430a-b104-11f1de1d5a3c",
      "name": "DeepSeek Chat Model1",
      "credentials": {
        "deepSeekApi": {
          "id": "r18ROW1LYH3RRIFM",
          "name": "DeepSeek account"
        }
      }
    }
  ],
  "pinData": {},
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "HTTP Request",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request": {
      "main": [
        [
          {
            "node": "XML",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "XML": {
      "main": [
        [
          {
            "node": "Split Out",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Out": {
      "main": [
        [
          {
            "node": "Limit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Limit": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "HTTP Request1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request1": {
      "main": [
        [
          {
            "node": "Wait",
            "type": "main",
            "index": 0
          },
          {
            "node": "Wait1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait": {
      "main": [
        [
          {
            "node": "HTTP Request2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "HTTP Request2": {
      "main": [
        [
          {
            "node": "If",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "If": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Edit Fields",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Edit Fields": {
      "main": [
        [
          {
            "node": "Wait",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "Convert to File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert to File": {
      "main": [
        [
          {
            "node": "Read/Write Files from Disk",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait1": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client": {
      "ai_tool": [
        [
          {
            "node": "AI Agent1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client1": {
      "ai_tool": [
        [
          {
            "node": "AI Agent1",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "DeepSeek Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "DeepSeek Chat Model1": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent1",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "1498fc4c-9ee2-428c-9ffa-ce07331f5447",
  "meta": {
    "templateCredsSetupCompleted": true,
    "instanceId": "842e089ebeca6cebf71676a6a2ba2cddf5a9039b264a25f6a7ee9230b3376b1b"
  },
  "id": "q45hhPQpfRuXDqqp",
  "tags": []
}