Extraction de données structurées de factures PDF JotForm (OpenAI GPT-4.1-mini)

Name: Extraction de données structurées de factures PDF JotForm (OpenAI GPT-4.1-mini)
Rating: 4.5 (10 reviews)
Author: Ranjan Dailata

Avancé

Ceci est unInvoice Processing, AI Summarizationworkflow d'automatisation du domainecontenant 19 nœuds.Utilise principalement des nœuds comme Webhook, Function, HttpRequest, GoogleSheets, ReadWriteFile. Extraire des données structurées de factures PDF de JotForm vers un tableau avec OpenAI GPT-4.1-mini

Prérequis

•Point de terminaison HTTP Webhook (généré automatiquement par n8n)
•Peut nécessiter les informations d'identification d'authentification de l'API cible
•Informations d'identification Google Sheets API
•Clé API OpenAI

Nœuds utilisés (19)

OutputParserStructured

Catégorie

Traitement des factures

Résumé IA

Aperçu du workflow

Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement

Webhook

Extraction de données structurées formatées

Télécharger la facture

Extraire depuis le fichier

Analyseur de sortie structurée

Extraction de données structurées

Modèle de chat OpenAI pour données structurées

Modèle de chat OpenAI pour analyseur de sortie

Modèle de chat OpenAI pour contenu formaté de données structurées

Écrire un fichier depuis le disque pour le traitement de facture entrante

Ajouter ou mettre à jour une ligne dans la feuille

Écrire la facture structurée sur le disque

Créer une réponse binaire

React Flow

Exporter le workflow

Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow

{
  "id": "QvIVxAgboRsZMMr0",
  "meta": {
    "instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
    "templateCredsSetupCompleted": true
  },
  "name": "Structured Invoice Data Extraction from JotForm PDFs via Open AI GPT-4.1-mini",
  "tags": [
    {
      "id": "Kujft2FOjmOVQAmJ",
      "name": "Engineering",
      "createdAt": "2025-04-09T01:31:00.558Z",
      "updatedAt": "2025-04-09T01:31:00.558Z"
    },
    {
      "id": "ddPkw7Hg5dZhQu2w",
      "name": "AI",
      "createdAt": "2025-04-13T05:38:08.053Z",
      "updatedAt": "2025-04-13T05:38:08.053Z"
    }
  ],
  "nodes": [
    {
      "id": "bcd1e88b-4435-4862-960e-86f284884681",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        -544,
        -32
      ],
      "webhookId": "b3a65dd9-8203-4aff-8005-80d98fb4c030",
      "parameters": {
        "path": "b3a65dd9-8203-4aff-8005-80d98fb4c030",
        "options": {},
        "httpMethod": "POST"
      },
      "typeVersion": 2.1
    },
    {
      "id": "84b85e47-b3aa-4c61-85ce-c17aba383b8e",
      "name": "Extraction de données structurées formatées",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        -352,
        -32
      ],
      "parameters": {
        "text": "= Extract Structured Information in JSON from the provided invoice raw request {{ $('Webhook').item.json.body.rawRequest }}",
        "options": {},
        "schemaType": "fromJson",
        "jsonSchemaExample": "{\n  \"formSubmission\": {\n    \"id\": \"252920932663460\",\n    \"source\": \"form\",\n    \"submittedAt\": \"2025-10-20T11:45:35.950Z\",\n    \"timeToSubmitSeconds\": 20,\n    \"eventId\": \"1760940191615_252920932663460_6BZ73Ag\"\n  },\n  \"user\": {\n    \"name\": {\n      \"first\": \"Ranjan\",\n      \"last\": \"Dailata\"\n    },\n    \"email\": \"ranjancse@gmail.com\"\n  },\n  \"invoice\": {\n    \"number\": \"INV-3337\",\n    \"date\": {\n      \"month\": \"\",\n      \"day\": \"\",\n      \"year\": \"\"\n    },\n    \"description\": \"Sample Invoice\",\n    \"attachments\": [\n      {\n        \"filename\": \"PDF-Invoice-Sample.pdf\",\n        \"url\": \"https://www.jotform.com/uploads/ranjancse/252920932663460/6367495377218625724/PDF-Invoice-Sample.pdf\",\n        \"fileServer\": \"jotformfs-e4f4ece4d0a90#019a0038-65e1-79f6-bdb5-c9281000db56\"\n      }\n    ]\n  },\n  \"system\": {\n    \"uploadServerUrl\": \"https://upload.jotform.com/upload\",\n    \"eventObserverEnabled\": true,\n    \"validatedFields\": {\n      \"new\": 1\n    },\n    \"buildDate\": \"1760940189728\",\n    \"jsExecutionTracker\": {\n      \"buildDate\": \"1760940189728\",\n      \"initStarted\": \"1760940191614\",\n      \"validatorCalled\": \"1760940191680\",\n      \"validatorMounted\": false,\n      \"initComplete\": \"1760940191684\",\n      \"intervalComplete\": \"1760940212688\",\n      \"onSubmitFired\": \"1760940335932\",\n      \"validationPassed\": \"1760940335944\",\n      \"formSubmitted\": \"1760940335950\"\n    }\n  }\n}\n"
      },
      "typeVersion": 1.2
    },
    {
      "id": "f7f77bb3-eb70-4000-aace-061d022e2882",
      "name": "Télécharger la facture",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        0,
        -32
      ],
      "parameters": {
        "url": "={{ $json.output.invoice.attachments[0].url }}",
        "options": {
          "redirect": {
            "redirect": {}
          },
          "response": {
            "response": {
              "responseFormat": "file",
              "outputPropertyName": "=PDF-Invoice-Sample.pdf"
            }
          }
        },
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "headerParameters": {
          "parameters": [
            {}
          ]
        }
      },
      "credentials": {
        "httpBearerAuth": {
          "id": "m17YVh2yJY7Fl9Wx",
          "name": "Thordata SERP Bearer YOUR_TOKEN_HERE Account"
        },
        "httpHeaderAuth": {
          "id": "i2RtoFcQm5F2NqG2",
          "name": "Jotform Api Key"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "cc1a28b8-a287-43c3-9bb3-118a89570562",
      "name": "Extraire depuis le fichier",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        416,
        -32
      ],
      "parameters": {
        "options": {},
        "operation": "pdf",
        "binaryPropertyName": "={{ $('Write File from Disk for Inbound Invoice Processing').item.binary['PDF-Invoice-Sample.pdf']}}"
      },
      "typeVersion": 1
    },
    {
      "id": "e9a4d6af-2efc-4d6b-8f72-5b49f60181ca",
      "name": "Analyseur de sortie structurée",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        736,
        160
      ],
      "parameters": {
        "autoFix": true,
        "schemaType": "manual",
        "inputSchema": "{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"title\": \"Invoice\",\n  \"type\": \"object\",\n  \"properties\": {\n    \"invoiceId\": {\n      \"type\": \"string\",\n      \"description\": \"Unique invoice identifier\"\n    },\n    \"invoiceNumber\": {\n      \"type\": \"string\",\n      \"description\": \"Human-readable invoice number (e.g. INV-2025-001)\"\n    },\n    \"invoiceDate\": {\n      \"type\": \"string\",\n      \"format\": \"date\",\n      \"description\": \"Invoice issue date\"\n    },\n    \"dueDate\": {\n      \"type\": \"string\",\n      \"format\": \"date\",\n      \"description\": \"Payment due date\"\n    },\n    \"company\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"name\": { \"type\": \"string\" },\n        \"address\": { \"type\": \"string\" },\n        \"email\": { \"type\": \"string\" },\n        \"phone\": { \"type\": \"string\" },\n        \"taxId\": { \"type\": \"string\" }\n      },\n      \"required\": [\"name\"]\n    },\n    \"client\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"name\": { \"type\": \"string\" },\n        \"address\": { \"type\": \"string\" },\n        \"email\": { \"type\": \"string\" },\n        \"phone\": { \"type\": \"string\" }\n      },\n      \"required\": [\"name\"]\n    },\n    \"items\": {\n      \"type\": \"array\",\n      \"description\": \"Line items billed on the invoice\",\n      \"items\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"description\": { \"type\": \"string\" },\n          \"quantity\": { \"type\": \"number\" },\n          \"unitPrice\": { \"type\": \"number\" },\n          \"total\": { \"type\": \"number\" },\n          \"taxRate\": { \"type\": \"number\" }\n        },\n        \"required\": [\"description\", \"quantity\", \"unitPrice\"]\n      }\n    },\n    \"subTotal\": {\n      \"type\": \"number\",\n      \"description\": \"Total before tax and discounts\"\n    },\n    \"taxAmount\": {\n      \"type\": \"number\",\n      \"description\": \"Total tax amount applied\"\n    },\n    \"discount\": {\n      \"type\": \"number\",\n      \"description\": \"Discount applied to invoice\"\n    },\n    \"totalAmount\": {\n      \"type\": \"number\",\n      \"description\": \"Final amount due\"\n    },\n    \"currency\": {\n      \"type\": \"string\",\n      \"description\": \"Currency code (e.g. USD, EUR, INR)\"\n    },\n    \"notes\": {\n      \"type\": \"string\",\n      \"description\": \"Optional notes or terms\"\n    },\n    \"payment\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"method\": { \"type\": \"string\", \"description\": \"Payment method (Bank, Card, etc.)\" },\n        \"status\": { \"type\": \"string\", \"description\": \"paid, pending, overdue\" },\n        \"transactionId\": { \"type\": \"string\" },\n        \"paymentDate\": { \"type\": \"string\", \"format\": \"date\" }\n      }\n    },\n    \"attachments\": {\n      \"type\": \"array\",\n      \"description\": \"Links to attached invoice PDFs or receipts\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"uri\"\n      }\n    }\n  }\n}\n"
      },
      "typeVersion": 1.3
    },
    {
      "id": "c60bd005-d03e-4053-93a1-7137c90b8e80",
      "name": "Extraction de données structurées",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        640,
        -32
      ],
      "parameters": {
        "text": "=Parse the below invoice info into a structured data\n\n{{ $json.text }}",
        "batching": {},
        "promptType": "define",
        "hasOutputParser": true
      },
      "retryOnFail": true,
      "typeVersion": 1.7,
      "alwaysOutputData": false
    },
    {
      "id": "2d0f93f5-6372-4c2c-97a0-61275648fc58",
      "name": "Modèle de chat OpenAI pour données structurées",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        576,
        176
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "vPKynKbDzJ5ZU4cU",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "48d81c63-ed97-4229-a63d-ad1a2a8959ae",
      "name": "Modèle de chat OpenAI pour analyseur de sortie",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        672,
        368
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "vPKynKbDzJ5ZU4cU",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "a54f0c84-82ca-439e-8cd8-86dabe04f69b",
      "name": "Modèle de chat OpenAI pour contenu formaté de données structurées",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -352,
        176
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini",
          "cachedResultName": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "vPKynKbDzJ5ZU4cU",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "a21275f7-fc1b-47ab-ba6a-06bcde58875e",
      "name": "Note adhésive",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -608,
        -432
      ],
      "parameters": {
        "color": 7,
        "width": 352,
        "height": 272,
        "content": "![Logo](https://www.jotform.com/resources/assets/logo-nb/min/jotform-logo-white-400x200.png)\n\nUses OpenAI gpt-4.1-mini for structured data extraction of the invoice PDF content"
      },
      "typeVersion": 1
    },
    {
      "id": "569de30c-835b-4ed3-aa7c-21052f4c06c9",
      "name": "Écrire un fichier depuis le disque pour le traitement de facture entrante",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        208,
        -32
      ],
      "parameters": {
        "options": {},
        "fileName": "=c:\\\\PDF-Invoice-Sample.pdf",
        "operation": "write",
        "dataPropertyName": "={{ $json.output.invoice.attachments[0].filename }}"
      },
      "typeVersion": 1
    },
    {
      "id": "9f3662ac-82cf-48fd-b04e-979d8d4d9310",
      "name": "Ajouter ou mettre à jour une ligne dans la feuille",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        1120,
        144
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [
            {
              "id": "output",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "output",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "autoMapInputData",
          "matchingColumns": [
            "output"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "appendOrUpdate",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1WaQUR9Q32uKLbbu77CrvWhM2I_3NXEsxT0RDMGq-Dm0/edit#gid=0",
          "cachedResultName": "Sheet1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1WaQUR9Q32uKLbbu77CrvWhM2I_3NXEsxT0RDMGq-Dm0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1WaQUR9Q32uKLbbu77CrvWhM2I_3NXEsxT0RDMGq-Dm0/edit?usp=drivesdk",
          "cachedResultName": "Jotform Invoice Extraction"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "Zjoxh2BUZ6VXGQhA",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.7
    },
    {
      "id": "707dd08c-6896-4888-9b16-699557d09320",
      "name": "Écrire la facture structurée sur le disque",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        1296,
        -192
      ],
      "parameters": {
        "options": {},
        "fileName": "=C:\\\\{{ $json.output.invoiceId }}-{{ $json.output.invoiceDate }}.json",
        "operation": "write"
      },
      "typeVersion": 1
    },
    {
      "id": "12cb7d07-9233-4081-92d9-11ebbe70270d",
      "name": "Créer une réponse binaire",
      "type": "n8n-nodes-base.function",
      "position": [
        1120,
        -192
      ],
      "parameters": {
        "functionCode": "\n\nitems[0].binary = {\n  data: {\n    data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n  }\n};\nreturn items;"
      },
      "typeVersion": 1
    },
    {
      "id": "077170e7-ca49-49be-a8d9-892b999a6724",
      "name": "Note adhésive 1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -608,
        384
      ],
      "parameters": {
        "color": 7,
        "width": 512,
        "height": 512,
        "content": "### **Purpose:**\nAutomates extraction of structured invoice data (ID, company, client, items, totals, etc.) from uploaded **JotForm PDF invoices** and stores results in **Google Sheets** and as JSON on disk.\n\n**Flow Summary:**\n\n1. **Webhook Trigger** — receives JotForm invoice submission.\n2. **Extract Form Data** — parses raw request and fetches PDF via JotForm API.\n3. **PDF Reader + GPT-4.1-mini** — extracts key invoice fields into structured JSON using AI-powered parsing.\n4. **Structured Output Parser** — validates against custom invoice schema.\n5. **Data Storage** —\n   • Saves structured JSON locally.\n   • Appends structured rows to Google Sheet for reporting.\n\n**Integrations:**\n\n* OpenAI GPT-4.1-mini\n* JotForm API\n* Google Sheets\n* Local File Storage\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "575ee55d-ff5f-4ec1-a9a5-e9f711f2b05c",
      "name": "Note adhésive 2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        368,
        -160
      ],
      "parameters": {
        "color": 5,
        "width": 656,
        "height": 672,
        "content": "## Structured Data Extraction Using OpenAI"
      },
      "typeVersion": 1
    },
    {
      "id": "47621c4a-20cc-455c-b901-d12b93447bb8",
      "name": "Note adhésive 3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1040,
        -288
      ],
      "parameters": {
        "color": 3,
        "width": 400,
        "height": 800,
        "content": "## Export Data Handling"
      },
      "typeVersion": 1
    },
    {
      "id": "73c0cc88-4604-4f19-83a2-10ce1bb9ea40",
      "name": "Note adhésive 4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -608,
        -128
      ],
      "parameters": {
        "color": 4,
        "width": 512,
        "height": 464,
        "content": "## Webhook Receiver & Data Formatting"
      },
      "typeVersion": 1
    },
    {
      "id": "1f92db74-0623-4785-a62b-18ff14405463",
      "name": "Note adhésive 5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -80,
        -128
      ],
      "parameters": {
        "width": 432,
        "height": 464,
        "content": "## Invoice Download & Write to Disk "
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "2b629465-8dc5-4eba-ad21-65f5e50f6280",
  "connections": {
    "bcd1e88b-4435-4862-960e-86f284884681": {
      "main": [
        [
          {
            "node": "84b85e47-b3aa-4c61-85ce-c17aba383b8e",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "f7f77bb3-eb70-4000-aace-061d022e2882": {
      "main": [
        [
          {
            "node": "569de30c-835b-4ed3-aa7c-21052f4c06c9",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "cc1a28b8-a287-43c3-9bb3-118a89570562": {
      "main": [
        [
          {
            "node": "c60bd005-d03e-4053-93a1-7137c90b8e80",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "c60bd005-d03e-4053-93a1-7137c90b8e80": {
      "main": [
        [
          {
            "node": "9f3662ac-82cf-48fd-b04e-979d8d4d9310",
            "type": "main",
            "index": 0
          },
          {
            "node": "12cb7d07-9233-4081-92d9-11ebbe70270d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "12cb7d07-9233-4081-92d9-11ebbe70270d": {
      "main": [
        [
          {
            "node": "707dd08c-6896-4888-9b16-699557d09320",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "e9a4d6af-2efc-4d6b-8f72-5b49f60181ca": {
      "ai_outputParser": [
        [
          {
            "node": "c60bd005-d03e-4053-93a1-7137c90b8e80",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "84b85e47-b3aa-4c61-85ce-c17aba383b8e": {
      "main": [
        [
          {
            "node": "f7f77bb3-eb70-4000-aace-061d022e2882",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "48d81c63-ed97-4229-a63d-ad1a2a8959ae": {
      "ai_languageModel": [
        [
          {
            "node": "e9a4d6af-2efc-4d6b-8f72-5b49f60181ca",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "2d0f93f5-6372-4c2c-97a0-61275648fc58": {
      "ai_languageModel": [
        [
          {
            "node": "c60bd005-d03e-4053-93a1-7137c90b8e80",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "569de30c-835b-4ed3-aa7c-21052f4c06c9": {
      "main": [
        [
          {
            "node": "cc1a28b8-a287-43c3-9bb3-118a89570562",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "a54f0c84-82ca-439e-8cd8-86dabe04f69b": {
      "ai_languageModel": [
        [
          {
            "node": "84b85e47-b3aa-4c61-85ce-c17aba383b8e",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  }
}

Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Avancé - Traitement des factures, Résumé IA

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.