🛻 물류 주문 처리 AI 대리인(GPT-4o, Gmail, 그리고 구글 시트)

• •Google 계정 및 Gmail API 인증 정보
• •Google Sheets API 인증 정보
• •OpenAI API Key

{
  "meta": {
    "instanceId": "6a5e68bcca67c4cdb3e0b698d01739aea084e1ec06e551db64aeff43d174cb23",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "bc49829b-45f2-4910-9c37-907271982f14",
      "name": "메모3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -140,
        320
      ],
      "parameters": {
        "width": 780,
        "height": 540,
        "content": "### 4. Do you need more details?\nFind a step-by-step guide in this tutorial\n![Guide](https://www.samirsaci.com/content/images/2025/03/Miniature-2.png)\n[🎥 Watch My Tutorial](https://www.youtube.com/watch?v=kQ8dO_30SB0)"
      },
      "typeVersion": 1
    },
    {
      "id": "40c6e16a-3b4f-4e28-b0a1-7066e0efab5d",
      "name": "AI 에이전트",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -460,
        -80
      ],
      "parameters": {
        "text": "=Email Subject:  {{ $json.subject }}\nEmail Body: \n{{ $json.text }}",
        "options": {
          "systemMessage": "=You are an assistant that processes emails related to inbound orders from Hermas.\n\nEach email has the subject line containing a purchase order reference (e.g., \"PO45231\").\nIn the email body, you will find:\n\nAn expected delivery date, typically in formats like 27/03/2025 or 2025-03-27.\n\nOne or more order lines, where each line contains:\n\nAn SKU (e.g., HERM-SHOE-001)\n\nA quantity (e.g., 120)\n\nYour goal is to extract the following fields:\n\npurchase_order: The PO number from the subject line (e.g., PO45231)\n\nexpected_delivery_date: In ISO format (e.g., 2025-03-27)\n\nlines: A list of objects with sku and quantity for each order line\n\nReturn your output strictly as a valid JSON object using the format below."
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 1.8
    },
    {
      "id": "e9cb7bb1-40e7-463e-8b3f-417602338e5c",
      "name": "OpenAI 채팅 모델",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -520,
        120
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "typeVersion": 1.2
    },
    {
      "id": "468bdb39-223f-4bae-8bdb-a72272ab57c3",
      "name": "구조화된 출력 파서",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        -180,
        120
      ],
      "parameters": {
        "jsonSchemaExample": "{\n  \"purchase_order\": \"PO45231\",\n  \"expected_delivery_date\": \"2025-03-27\",\n  \"lines\": [\n    { \"sku\": \"HERM-SHOE-001\", \"quantity\": 120 },\n    { \"sku\": \"HERM-BAG-032\", \"quantity\": 45 },\n    { \"sku\": \"HERM-WATCH-105\", \"quantity\": 30 },\n    { \"sku\": \"HERM-SCARF-018\", \"quantity\": 80 }\n  ]\n}\n"
      },
      "typeVersion": 1.2
    },
    {
      "id": "667a8d43-1ce5-4ec8-871a-26007356a89e",
      "name": "메모1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1000,
        -460
      ],
      "parameters": {
        "color": 7,
        "width": 380,
        "height": 720,
        "content": "### 1. Workflow Trigger with Gmail Trigger\nThe workflow is triggered by a new email received in your Gmail mailbox. \nIf the subject includes the string \"Inbound Order\" we proceed, if not we do nothing.\n\n#### How to setup?\n- **Gmail Trigger Node:** set up your Gmail API credentials\n[Learn more about the Gmail Trigger Node](https://docs.n8n.io/integrations/builtin/trigger-nodes/n8n-nodes-base.gmailtrigger)\n"
      },
      "typeVersion": 1
    },
    {
      "id": "e1e2d95a-9bbd-4bd5-92ec-7a4835db21a2",
      "name": "메모2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -600,
        -460
      ],
      "parameters": {
        "color": 7,
        "width": 660,
        "height": 720,
        "content": "### 2. AI Agent equipped with the query tool\nThe email body and subject are sent to the AI agent for parsing. The results include the **PO Number**, **expected delivery date** and all the order lines with **SKU ID** and **order quantity**. Outputs are formatted by the code node to fit in a Google Sheet.\n\n#### How to setup?\n- **AI Agent with the Chat Model**:\n   1. Add a **chat model** with the required credentials *(Example: Open AI 4o-mini)*\n   2. Adapt the system prompt to the format of your emails\n  [Learn more about the AI Agent Node](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent)"
      },
      "typeVersion": 1
    },
    {
      "id": "53375c17-a36c-431e-9ba6-07a9a84fc4c9",
      "name": "메모4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        80,
        -460
      ],
      "parameters": {
        "color": 7,
        "width": 460,
        "height": 540,
        "content": "### 3. Store the orderlines in a Google Sheet\nThe table generated by the **code node** includes all the order lines with the **PO Number** and the **expected delivery date**. This **Google Sheet Node** loads the content in a Google Sheet.\n\n#### How to setup?\n- **Add Results in Google Sheets**:\n   1. Add your Google Sheet API credentials to access the Google Sheet file\n   2. Select the file using the list, an URL or an ID\n   3. Select the sheet in which the vocabulary list is stored\n   4. Create the columns: **PO_NUMBER, EXPECTED_DELIVERY DATE, SKU_ID, QUANTITY**\n  [Learn more about the Google Sheet Node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googlesheets)"
      },
      "typeVersion": 1
    },
    {
      "id": "776cfc0e-264b-44cc-b534-dc387b0c9fce",
      "name": "Store Purchase Order Lines",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        180,
        -80
      ],
      "parameters": {
        "columns": {
          "value": {
            "SKU_ID": "={{ $json.sku }}",
            "QUANTITY": "={{ $json.quantity }}",
            "PO_NUMBER": "={{ $json.purchase_order }}",
            "EXPECTED_DELIVERY DATE": "={{ $json.expected_delivery_date }}"
          },
          "schema": [
            {
              "id": "PO_NUMBER",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "PO_NUMBER",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "EXPECTED_DELIVERY DATE",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "EXPECTED_DELIVERY DATE",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "SKU_ID",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "SKU_ID",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "QUANTITY",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "QUANTITY",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "=",
          "cachedResultName": "="
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1HnaJJ-DqzqgWJo2YwQDcgB6BgWiU6eMlnGvv4kapubg",
          "cachedResultUrl": "=",
          "cachedResultName": "="
        }
      },
      "notesInFlow": true,
      "typeVersion": 4.5
    },
    {
      "id": "d5c52625-fef2-47a9-b2a4-bf005d8b9e05",
      "name": "이메일 Received",
      "type": "n8n-nodes-base.gmailTrigger",
      "position": [
        -980,
        -80
      ],
      "parameters": {
        "simple": false,
        "filters": {},
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "6dc9e5cc-9ab3-469c-ad93-e0e7817ccbf7",
      "name": "Is PO?",
      "type": "n8n-nodes-base.if",
      "position": [
        -760,
        -80
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "f300ae2b-5de4-4efc-88ae-130a957588cb",
              "operator": {
                "type": "string",
                "operation": "contains"
              },
              "leftValue": "={{ $json.subject }}",
              "rightValue": "Inbound Order"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "385db736-0867-46b9-9274-380e7c255fc4",
      "name": "Format Purchase Order Lines",
      "type": "n8n-nodes-base.code",
      "position": [
        -120,
        -80
      ],
      "parameters": {
        "jsCode": "const {purchase_order, expected_delivery_date, lines} = $input.first().json.output;\n\nreturn lines.map( line => ({\n  json: {\n    purchase_order,\n    expected_delivery_date,\n    sku: line.sku,\n    quantity: line.quantity\n  }\n}))\n"
      },
      "typeVersion": 2
    },
    {
      "id": "b2e39591-70be-4d7f-a5d4-1505741d6310",
      "name": "메모",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1000,
        320
      ],
      "parameters": {
        "width": 780,
        "height": 720,
        "content": "### Test the workflow with this email!\n\n#### How?\n1. Send this email to the Gmail box you set up in your credentials.\n2. Click on Test workflow\n\n### Email\n**Email Subject:** Inbound Order PO45231 – Expected Delivery on 2025-03-27\n\n**Email Body:** \nDear LogiGreen Team,\n\nPlease find below the details of the upcoming inbound order.\n\nPurchase Order: PO45231\nExpected Delivery Date: 27/03/2025\n\nOrder Lines:\n\nSKU: HERM-SHOE-001 — Qty: 120\n\nSKU: HERM-BAG-032 — Qty: 45\n\nSKU: HERM-WATCH-105 — Qty: 30\n\nSKU: HERM-SCARF-018 — Qty: 80\n\nLet us know if you need any additional details.\n\nBest regards,\nSophie Lambert\nAdmin Assistant – Hermas Logistics\n📞 +33 1 23 45 67 89 78 84\n✉️ sophie.lambert@hermas.com\n"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "6dc9e5cc-9ab3-469c-ad93-e0e7817ccbf7": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI Agent": {
      "main": [
        [
          {
            "node": "385db736-0867-46b9-9274-380e7c255fc4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Email Received": {
      "main": [
        [
          {
            "node": "6dc9e5cc-9ab3-469c-ad93-e0e7817ccbf7",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Structured Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "AI Agent",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "385db736-0867-46b9-9274-380e7c255fc4": {
      "main": [
        [
          {
            "node": "776cfc0e-264b-44cc-b534-dc387b0c9fce",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}