8
n8n 中文网amn8n.com

TyphoonV2.2 多文件与多页面及带AI

中级

这是一个AI Summarization, Multimodal AI领域的自动化工作流，包含 15 个节点。主要使用 Code, Aggregate, GoogleSheets, ManualTrigger, ReadWriteFile 等节点。 使用TyphoonOCR和AI处理泰语文档至Google表格（多页PDF）

前置要求
  • •Google Sheets API 凭证

使用的节点 (15)

Code
Aggregate
StickyNote
GoogleSheets
ManualTrigger
ReadWriteFile
ExecuteCommand
SplitInBatches
ChainLlm
LmChatOpenRouter

分类

AI 摘要总结
多模态 AI
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
{
  "id": "usFtj9NVTTqcIUFw",
  "meta": {
    "instanceId": "ec740af1a2cd76453ffc1c197c5b3c66b8ee9fcd44f7dc2e779efb35ee81469a",
    "templateCredsSetupCompleted": true
  },
  "name": "TyphoonV2.2 多文件与多页面及带 AI",
  "tags": [],
  "nodes": [
    {
      "id": "bcda99fe-5a10-4c43-af9d-3510ff00fb5e",
      "name": "当点击\"测试工作流\"时",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        912,
        208
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "06b15c69-b854-4956-a6fc-3355f1a72427",
      "name": "使用 Typhoon OCR 提取文本",
      "type": "n8n-nodes-base.executeCommand",
      "position": [
        752,
        640
      ],
      "parameters": {
        "command": "=python -c \"import sys, os; os.environ['TYPHOON_OCR_API_KEY'] = '<Please update your Typhoon OCR>'; from typhoon_ocr import ocr_document; sys.stdout.reconfigure(encoding='utf-8'); input_path = sys.argv[1]; text = ocr_document(input_path); print(text)\" \"/doc/tmp/pages/{{$json[\"fileName\"]}}\"",
        "executeOnce": false
      },
      "typeVersion": 1
    },
    {
      "id": "1c8ac652-4ac9-424e-847b-5b845753c621",
      "name": "从文档文件夹加载 PDF",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        1184,
        208
      ],
      "parameters": {
        "options": {},
        "fileSelector": "/doc/multipage/*"
      },
      "typeVersion": 1,
      "alwaysOutputData": true
    },
    {
      "id": "291f466a-3928-47bb-8cfb-48de2ad0256f",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        192,
        176
      ],
      "parameters": {
        "width": 1352,
        "height": 968,
        "content": "## 泰语 OCR 到表格 (V2.2 – 多文件与多页面带 AI)"
      },
      "typeVersion": 1
    },
    {
      "id": "d585efcd-9b42-4bea-b128-1e0042e6b67f",
      "name": "从磁盘读取/写入文件",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        848,
        416
      ],
      "parameters": {
        "options": {},
        "fileName": "/doc/tmp/in.pdf",
        "operation": "write"
      },
      "typeVersion": 1
    },
    {
      "id": "8fff15da-ea36-4b56-83da-011ae227964b",
      "name": "设置输入路径",
      "type": "n8n-nodes-base.code",
      "position": [
        1008,
        416
      ],
      "parameters": {
        "jsCode": "// รับ items จากโหนดก่อนหน้า แล้วเติมฟิลด์ inputPath ให้เรียบร้อย\n// กติกา: ใช้ filePath ถ้ามี; ถ้าไม่มี ให้ประกอบจาก directory + fileName; ถ้าไม่มี directory ก็ใช้ fileName\nreturn items.map(({ json, binary }) => {\n  const filePath =\n    json.filePath\n      ? json.filePath\n      : (json.directory\n          ? `${json.directory.replace(/\\/$/, '')}/${json.fileName}`\n          : json.fileName);\n\n  return {\n    json: {\n      ...json,\n      inputPath: filePath,\n    },\n    binary, // เผื่ออยากพก binary ต่อไปด้วย\n  };\n});\n"
      },
      "typeVersion": 2
    },
    {
      "id": "e4d8e648-e26b-4707-adf5-525e88a09ec8",
      "name": "拆分 PDF 页面",
      "type": "n8n-nodes-base.executeCommand",
      "position": [
        1184,
        416
      ],
      "parameters": {
        "command": "=sh -lc '\nset -e\nIN=\"{{ $json.inputPath }}\"\nOUT=\"/doc/tmp/pages\"\nrm -rf \"$OUT\" && mkdir -p \"$OUT\"\n\n# นับจำนวนหน้า (ต้องมี poppler-utils)\nPAGES=$(pdfinfo \"$IN\" 2>/dev/null | awk -F\": *\" \"/^Pages/{print \\$2}\")\n[ -n \"$PAGES\" ] || { echo \"Cannot detect page count for: $IN\" >&2; exit 1; }\n\npdfseparate -f 1 -l \"$PAGES\" \"$IN\" \"$OUT/page_%d.pdf\"\nls -1 \"$OUT\"/page_*.pdf\n'\n",
        "executeOnce": false
      },
      "typeVersion": 1
    },
    {
      "id": "57bb55c3-07e2-4ace-9678-8fafd5b420c6",
      "name": "读取拆分后的 PDF 页面",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        1360,
        416
      ],
      "parameters": {
        "options": {},
        "fileSelector": "/doc/tmp/pages/*.pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "33589105-6b44-4d83-bd68-50b381d681e1",
      "name": "聚合",
      "type": "n8n-nodes-base.aggregate",
      "position": [
        944,
        640
      ],
      "parameters": {
        "options": {},
        "fieldsToAggregate": {
          "fieldToAggregate": [
            {
              "fieldToAggregate": "stdout"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "a65d7907-3744-4629-a8fa-37c36b31e3f3",
      "name": "遍历项目",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        672,
        400
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "eadb2b7e-4ad3-4a46-8ecd-da1702470f1a",
      "name": "解析 JSON 为表格格式",
      "type": "n8n-nodes-base.code",
      "position": [
        752,
        864
      ],
      "parameters": {
        "mode": "runOnceForEachItem",
        "jsCode": "const raw = $json[\"text\"];\n\n// 1. ลบ ```json และ ``` ที่ LLM อาจใส่มา\nconst cleaned = raw.replace(/```json\\n?|```/g, \"\").trim();\n\nlet parsed;\ntry {\n  // 2. แปลงเป็น object\n  parsed = JSON.parse(cleaned);\n} catch (err) {\n  throw new Error(\"JSON parsing failed: \" + err.message + \"\\n\\nRaw text:\\n\" + cleaned);\n}\n\n// 3. หาก contact เป็น object แยก field ออกมา\nconst contact = parsed.contact || {};\n\nreturn {\n  book_id: parsed.book_id || \"\",\n  date: parsed.date || \"\",\n  subject: parsed.subject || \"\",\n  to: parsed.to || \"\",\n  attach: parsed.attach || \"\",\n  detail: parsed.detail || \"\",\n  signed_by: parsed.signed_by || \"\",\n  signed_by2: parsed.signed_by2 || \"\",\n  contact_phone: contact.phone || \"\",\n  contact_email: contact.email || \"\",\n  contact_fax: contact.fax || \"\",\n  download_url: parsed.download_url || \"\"\n};\n"
      },
      "typeVersion": 2
    },
    {
      "id": "8f2fb4c3-bbb3-49aa-8796-f85219241f47",
      "name": "使用 LLM 将文本结构化为 JSON",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1136,
        640
      ],
      "parameters": {
        "text": "=ข้อความด้านล่างนี้เป็นเนื้อหา OCR จากหนังสือราชการ กรุณาแยกหัวข้อสำคัญออกมาในรูปแบบ JSON:\n\n1. book_id: เลขที่หนังสือ\n2. date: วันที่ในเอกสาร\n3. subject: หัวเรื่อง\n4. to: เรียน\n5. attach: สิ่งที่ส่งมาด้วย\n6. detail: เนื้อความในหนังสือ\n7. signed_by: ผู้ลงนาม\n8. signed_by2: ตำแหน่งผู้ลงนาม\n9. contact: ช่องทางติดต่อ (เช่น เบอร์โทร อีเมล)\n10. download_url: ลิงก์สำหรับดาวน์โหลด (ถ้ามี)\n\nOCR_TEXT:\n\"\"\"\n{{ $json[\"stdout\"] }}\n\"\"\"",
        "promptType": "define"
      },
      "typeVersion": 1.6
    },
    {
      "id": "205beaeb-8532-4768-a2db-e4ab773a2fc8",
      "name": "OpenRouter 聊天模型",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
      "position": [
        1136,
        784
      ],
      "parameters": {
        "model": "openai/gpt-4o-mini",
        "options": {}
      },
      "credentials": {
        "openRouterApi": {
          "id": "JVYq1Px3c4AZWpkk",
          "name": "OpenRouter account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "aa0f180d-9ae8-4a09-ad09-d409d92b4c6b",
      "name": "清理临时文件",
      "type": "n8n-nodes-base.executeCommand",
      "position": [
        1248,
        864
      ],
      "parameters": {
        "command": "=sh -lc '\nset -e\n\n# ลบโฟลเดอร์ temp ที่ใช้เก็บไฟล์ที่ split\nrm -rf /doc/tmp/pages\n\n# ย้ายไฟล์ต้นฉบับ (input PDF) ไปเก็บไว้ใน Completed\nmkdir -p /doc/multipage/Completed\n\n# ใช้ $json.fileName ของ node ต้นทาง (Load PDFs from doc Folder)\n# ถ้า fileName เป็น path อยู่แล้ว ให้ basename ออกมาก่อน\nsrc=\"/doc/multipage/{{ $('Load PDFs from doc Folder').item.json.fileName }}\"\ndst=\"/doc/multipage/Completed/{{ $('Load PDFs from doc Folder').item.json.fileName }}\"\n\nmv \"$src\" \"$dst\"\necho \"Moved $src → $dst\"\n'\n"
      },
      "typeVersion": 1
    },
    {
      "id": "32acc4b4-3bb3-49d7-8a50-984e02f31077",
      "name": "保存到 Google Sheet",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        992,
        864
      ],
      "parameters": {
        "columns": {
          "value": {
            "to": "={{ $json.to }}",
            "date": "={{ $json.date }}",
            "attach": "={{ $json.attach }}",
            "detail": "={{ $json.detail }}",
            "book_id": "={{ $json.book_id }}",
            "subject": "={{ $json.subject }}",
            "signed_by": "={{ $json.signed_by }}",
            "signed_by2": "={{ $json.signed_by2 }}",
            "contact_fax": "={{ $json.contact_fax }}",
            "download_url": "={{ $json.download_url }}",
            "contact_email": "={{ $json.contact_email }}",
            "contact_phone": "={{ $json.contact_phone }}"
          },
          "schema": [
            {
              "id": "book_id",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "book_id",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "date",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "date",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "subject",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "subject",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "to",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "to",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "attach",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "attach",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "detail",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "detail",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "signed_by",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "signed_by",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "signed_by2",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "signed_by2",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "contact_phone",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "contact_phone",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "contact_email",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "contact_email",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "contact_fax",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "contact_fax",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "download_url",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "download_url",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [
            "book_id"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1h70cJyLj5i2j0Ag5kqp93ccZjjhJnqpLmz-ee5r4brU/edit#gid=0",
          "cachedResultName": "Sheet1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1h70cJyLj5i2j0Ag5kqp93ccZjjhJnqpLmz-ee5r4brU",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1h70cJyLj5i2j0Ag5kqp93ccZjjhJnqpLmz-ee5r4brU/edit?usp=drivesdk",
          "cachedResultName": "TyphoonOCR_Extracted_Data"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "ot4XqoGzFPMsgA5P",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.5
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "7166e717-0700-4f73-872d-a771d37b1e65",
  "connections": {
    "Aggregate": {
      "main": [
        [
          {
            "node": "Structure Text to JSON with LLM",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set_Input_Path": {
      "main": [
        [
          {
            "node": "Split PDF page",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split PDF page": {
      "main": [
        [
          {
            "node": "Read Splite PDF Page",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Clear tmp files": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "Read/Write Files from Disk",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Read Splite PDF Page": {
      "main": [
        [
          {
            "node": "Extract Text with Typhoon OCR",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Save to Google Sheet": {
      "main": [
        [
          {
            "node": "Clear tmp files",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenRouter Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Structure Text to JSON with LLM",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Load PDFs from doc Folder": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Parse JSON to Sheet Format": {
      "main": [
        [
          {
            "node": "Save to Google Sheet",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Read/Write Files from Disk": {
      "main": [
        [
          {
            "node": "Set_Input_Path",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Text with Typhoon OCR": {
      "main": [
        [
          {
            "node": "Aggregate",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Structure Text to JSON with LLM": {
      "main": [
        [
          {
            "node": "Parse JSON to Sheet Format",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Load PDFs from doc Folder",
            "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？

中级 - AI 摘要总结, 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。

相关工作流推荐

Typhoon_提交
使用Typhoon OCR和Llama 3.1提取并结构化泰语文档至Google Sheets
Code
Google Sheets
Manual Trigger
+5
8 节点Jaruphat J.
人工智能
每日 WhatsApp 群组智能分析：GPT-4.1 分析与语音消息转录
每日 WhatsApp 群组智能分析：GPT-4.1 分析与语音消息转录
If
Set
Code
+20
52 节点Daniel Lianes
杂项
FalAI_SeeDanceV1.0_英文模板
使用GPT-4o、Fal.AI Seedance和音频从文本提示生成电影级视频
If
Code
Wait
+12
38 节点Jaruphat J.
内容创作
使用 Bright Data API 和 AI 抓取分析 Google 广告并发送邮件报告
使用 Bright Data API 和 AI 抓取分析 Google 广告并发送邮件报告
Set
Code
Gmail
+15
45 节点Zacharia Kimotho
市场调研
自动化新闻监控与Claude 4 AI分析，用于Discord和Google新闻
自动化新闻监控与Claude 4 AI分析，用于Discord和Google新闻
Code
Discord
Aggregate
+8
30 节点Growth AI
杂项
Twitter数据抓取 - n8n Creator
使用Gemini 2.5 Pro自动生成Twitter情报摘要并推送到WhatsApp群组
Set
Code
Wait
+13
39 节点Daniel Lianes
AI 摘要总结
工作流信息
难度等级
中级
节点数量15
分类2
节点类型10
难度说明

适合有一定经验的用户，包含 6-15 个节点的中等复杂度工作流

作者
Jaruphat J.

Jaruphat J.

@jaruphatj

Project Manager who passionate about Automation & AI and continuously explore innovative ways to improve business processes through intelligent workflow automation. Let’s connect and automate the future!

外部链接
在 n8n.io 查看 →

分享此工作流