Entwicklung abgeschlossen - FAX-Inhaltsextraktion
Dies ist ein Content Creation, Multimodal AI-Bereich Automatisierungsworkflow mit 18 Nodes. Hauptsächlich werden Set, Code, FormTrigger, GoogleDrive, HttpRequest und andere Nodes verwendet. Arbeitsablauf für Fax- und PDF-Datenextraktion: Google Gemini und Google Sheets
- •Google Drive API-Anmeldedaten
- •Möglicherweise sind Ziel-API-Anmeldedaten erforderlich
- •Google Sheets API-Anmeldedaten
- •Google Gemini API Key
Verwendete Nodes (18)
Kategorie
{
"id": "CACB2vgfyxBJE30X",
"meta": {
"instanceId": "{YOUR_INSTANCE_ID}",
"templateCredsSetupCompleted": true
},
"name": "Development Done - FAX Content Extraction",
"tags": [
{
"id": "m1paRrANi4GrQXxX",
"name": "AI Internal",
"createdAt": "2025-09-18T04:05:25.667Z",
"updatedAt": "2025-09-18T04:05:25.667Z"
}
],
"nodes": [
{
"id": "5be36f47-e7ed-464a-bf73-6573abed5fc6",
"name": "Aus Datei extrahieren",
"type": "n8n-nodes-base.extractFromFile",
"position": [
-336,
160
],
"parameters": {
"options": {},
"operation": "binaryToPropery"
},
"typeVersion": 1
},
{
"id": "4e9b17d5-0ded-4edb-baa5-b7eae5d0ecfa",
"name": "Google Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
-528,
160
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Upload file').item.json.id }}"
},
"options": {},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "{YOUR_GOOGLE_DRIVE_CREDENTIAL_ID}",
"name": "Google Drive Account"
}
},
"typeVersion": 3
},
{
"id": "579a0a77-34bd-4f38-a22a-dfc68421b0b9",
"name": "Call Gemini 2.0 Flash with PDF Capabilities",
"type": "n8n-nodes-base.httpRequest",
"position": [
-96,
160
],
"parameters": {
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent",
"method": "POST",
"options": {},
"jsonBody": "={\n \"contents\": [\n {\n \"parts\": [\n {\n \"inline_data\": {\n \"mime_type\": \"application/pdf\",\n \"data\": \"{{ $json.data }}\"\n }\n },\n {\n \"text\": \"{{ $('Define Prompt').item.json.prompt }}\"\n }\n ]\n }\n ]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "googlePalmApi"
},
"credentials": {
"googlePalmApi": {
"id": "{YOUR_GEMINI_CREDENTIAL_ID}",
"name": "Gemini API Account"
}
},
"typeVersion": 4.2
},
{
"id": "07953a5f-115a-4697-9961-f5d7046ec6db",
"name": "Prompt definieren",
"type": "n8n-nodes-base.set",
"position": [
-768,
160
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "dba23ef5-95df-496a-8e24-c7c1544533d2",
"name": "prompt",
"type": "string",
"value": "You are an expert document analyzer. Your task is to read a fax document that may contain a medical or administrative form with multiple fields, tables, and notes. The document may contain both filled and unfilled fields. Instructions: 1. Extract only the filled or relevant fields from the form. 2. Ignore empty fields, irrelevant boilerplate text, transmission details, or formatting artifacts. 3. Present the extracted information in a clean structured format. 4. Capture key details such as: - Patient Information (ID, Name, DOB, Sex, Address, Diagnosis, Allergies, Functional Limitations, Mental Status, etc.) - Provider Information (Provider Name, Address, Physician Name, Certification Dates, Provider No.) - Medical Data (Diagnosis codes, Medications, Procedures, Treatments, Orders, Prognosis, Safety Measures, Activities Permitted, Goals) - Certification / Signatures (Physician signature, Date signed, Certification statement) - Any explicit instructions, precautions, or urgent notes. 5. If the document contains critical health conditions, precautions, or deadlines, highlight them separately. 6. Do not alter or interpret the medical data—extract it exactly as written. "
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e570291a-6ca2-49f4-be02-a837be4444f6",
"name": "Datei hochladen",
"type": "n8n-nodes-base.googleDrive",
"position": [
-1072,
160
],
"parameters": {
"name": "Fax test",
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive",
"cachedResultUrl": "https://drive.google.com/drive/my-drive",
"cachedResultName": "My Drive"
},
"options": {},
"folderId": {
"__rl": true,
"mode": "list",
"value": "{YOUR_GOOGLE_DRIVE_FOLDER_ID}",
"cachedResultUrl": "https://drive.google.com/drive/folders/{YOUR_GOOGLE_DRIVE_FOLDER_ID}",
"cachedResultName": "FAX Test"
},
"inputDataFieldName": "Upload_File"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "{YOUR_GOOGLE_DRIVE_CREDENTIAL_ID}",
"name": "Google Drive Account"
}
},
"typeVersion": 3
},
{
"id": "37801239-6daf-4445-9004-01523094018a",
"name": "Zeile in Sheet anhängen",
"type": "n8n-nodes-base.googleSheets",
"position": [
848,
160
],
"parameters": {
"columns": {
"value": {
"Gender": "={{ $json.output.Gender }}",
"SOC Date": "={{ $json.output.SOCDate }}",
"Allergies": "={{ $json.output.Allergies }}",
"Prognosis": "={{ $json.output.Prognosis }}",
"Patient ID": "={{ $json.output.PatientID }}",
"Date Signed": "={{ $json.output.DateSigned }}",
"Patient Name": "={{ $json.output.PatientName }}",
"Provider No.": "={{ $json.output.ProviderNo }}",
"Date of Birth": "={{ $json.output.DateOfBirth }}",
"Mental Status": "={{ $json.output['Mental Status'] }}",
"Medical Record": "={{ $json.output.MedicalRecord }}",
"Patient Address": "={{ $json.output.PatientAddress }}",
"Safety Measures": "={{ $json.output.SafetyMeasures }}"
},
"schema": [
{
"id": "Patient ID",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Patient ID",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "SOC Date",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "SOC Date",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Medical Record",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Medical Record",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Provider No.",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Provider No.",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Patient Name",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Patient Name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Patient Address",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Patient Address",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Date of Birth",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Date of Birth",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Safety Measures",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Safety Measures",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Allergies",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Allergies",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Gender",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Gender",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Mental Status",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Mental Status",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Prognosis",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Prognosis",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Date Signed",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Date Signed",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"Information"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/{YOUR_GOOGLE_SHEET_ID}/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "{YOUR_GOOGLE_SHEET_ID}",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/{YOUR_GOOGLE_SHEET_ID}/edit?usp=drivesdk",
"cachedResultName": "Fax Test Extracted"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "{YOUR_GOOGLE_SHEETS_CREDENTIAL_ID}",
"name": "Google Sheets Account"
}
},
"typeVersion": 4.7
},
{
"id": "ca632b40-621b-4359-9e80-31706f374831",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
384,
160
],
"parameters": {
"text": "==You are a strict JSON parser.\nReturn ONLY valid JSON that matches this schema. \nNo markdown, no comments, no extra text.\n\nSchema:\n{\n \"PatientID\": \"string or null\",\n \"SOCDate\": \"string or null\",\n \"MedicalRecord\": \"string or null\",\n \"ProviderNo\": \"string or null\",\n \"PatientName\": \"string or null\",\n \"PatientAddress\": \"string or null\",\n \"DateOfBirth\": \"string or null\",\n \"SafetyMeasures\": \"string or null\",\n \"Allergies\": \"string or null\",\n \"Gender\": \"string or null\",\n \"Mental Status\": \"string or null\",\n \"Prognosis\": \"string or null\",\n \"DateSigned\": \"string or null\"\n}\n\nRules:\n- Include **all** keys, even if null.\n- Do not add markdown (like ```json).\n- Do not add extra text.\n\nExtracted Fax Text:\n\"\"\"\n{{ $json.extractedText }}\n\"\"\"\n",
"batching": {},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.7
},
{
"id": "0330fa20-6915-42c5-8769-0f2658f5b035",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
368,
336
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"id": "{YOUR_GEMINI_CREDENTIAL_ID}",
"name": "Gemini API Account"
}
},
"typeVersion": 1
},
{
"id": "d022685e-fe91-4980-b257-0ec2e7989491",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
544,
336
],
"parameters": {
"jsonSchemaExample": "{\n \"PatientID\": \"ID - 123\",\n \"SOCDate\": \"10/12/2026\",\n \"MedicalRecord\": \"No\",\n \"ProviderNo\": \"MR - 000\",\n \"PatientName\": \"Tom Cruise\",\n \"PatientAddress\": \"F-19 Lamine Street, Barcelona, Spain\",\n \"DateOfBirth\": \"09/11/2020\",\n \"SafetyMeasures\": \"Precaution\",\n \"Allergies\": \"Nose Allergy\",\n \"Gender\": \"F\",\n \"Mental Status\": \"Agitated\",\n \"Prognosis\": \"Fair\",\n \"DateSigned\": \"25/09/2025\"\n}\n"
},
"typeVersion": 1.3
},
{
"id": "bea9b647-0e25-47ee-9eab-c952f512b03f",
"name": "Bei Formularübermittlung",
"type": "n8n-nodes-base.formTrigger",
"position": [
-1376,
160
],
"webhookId": "{YOUR_WEBHOOK_ID}",
"parameters": {
"options": {},
"formTitle": "Fax File",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "Upload File",
"multipleFiles": false,
"requiredField": true
}
]
},
"formDescription": "User can Upload the Fax PDF directly here!"
},
"typeVersion": 2.2
},
{
"id": "a452a474-38ee-426b-b225-fd8f65bbd878",
"name": "Code",
"type": "n8n-nodes-base.code",
"position": [
176,
160
],
"parameters": {
"jsCode": "// Function to clean and extract plain text\nreturn $input.all().map(item => {\n const candidates = item.json.candidates || [];\n const firstCandidate = candidates[0] || {};\n const parts = firstCandidate.content?.parts || [];\n let extractedText = parts[0]?.text || \"\";\n\n // Clean markdown-like artifacts\n extractedText = extractedText\n .replace(/\\*\\*/g, \"\") // remove bold markers\n .replace(/\\*/g, \"\") // remove list markers\n .trim();\n\n return {\n json: {\n extractedText\n }\n };\n});\n"
},
"typeVersion": 2
},
{
"id": "26f7cfb0-39bb-47f8-8f6c-4d5e87dd999c",
"name": "Haftnotiz",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1456,
-16
],
"parameters": {
"color": 4,
"width": 272,
"height": 320,
"content": "## 1. Start Here: Form Trigger \n* This is the entry point for the workflow.\n* It creates a web form where a user can upload the FAX PDF file."
},
"typeVersion": 1
},
{
"id": "43885ab6-67d3-4d46-8202-83e3228d68b2",
"name": "Haftnotiz1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1152,
-32
],
"parameters": {
"color": 5,
"width": 288,
"height": 336,
"content": "## 2. Configure: Upload to Google Drive\n* Select your Google Drive account from the 'Credentials' dropdown.\n* Change the Folder ID to the specific Google Drive folder where you want to save the faxes."
},
"typeVersion": 1
},
{
"id": "c0e958e2-f39b-4463-8ef1-a46ae0a129d7",
"name": "Haftnotiz2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-832,
-16
],
"parameters": {
"color": 6,
"width": 224,
"height": 320,
"content": "## 3. Customize AI Brain (Part 1)\n* You can edit the *prompt* value here to change the extraction rules or ask for different information."
},
"typeVersion": 1
},
{
"id": "8c973931-b16b-4c81-888d-5869b52544e8",
"name": "Haftnotiz3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-176,
-16
],
"parameters": {
"color": 2,
"width": 272,
"height": 320,
"content": "## 4. First AI Call: PDF Extraction\n* **ACTION REQUIRED**: You must select your \"Google Palm API\" credentials from the dropdown for this node to work."
},
"typeVersion": 1
},
{
"id": "1bc9982f-4880-4552-88c6-b5f2f296d1d7",
"name": "Haftnotiz4",
"type": "n8n-nodes-base.stickyNote",
"position": [
320,
-48
],
"parameters": {
"color": 3,
"width": 352,
"height": 320,
"content": "## 5. Customize AI Brain (Part 2)\nThis second AI call structures the cleaned text into a strict JSON format.\n* **ACTION REQUIRED**: In the connected Google Gemini Chat Model node, select your Gemini API credentials.\n* To change the final output fields, edit the JSON schema inside the Prompt field of this node."
},
"typeVersion": 1
},
{
"id": "c4e2b238-0152-46f2-8195-d25ad26d5882",
"name": "Haftnotiz5",
"type": "n8n-nodes-base.stickyNote",
"position": [
704,
-48
],
"parameters": {
"color": 4,
"width": 384,
"height": 352,
"content": "## Final Step: Save to Google Sheets\n* **ACTION REQUIRED**: Configure your Google Sheets credentials.\n* **ACTION REQUIRED**: Update the Document ID with the ID of your own Google Sheet.\n* Ensure the column names in this node match the header row in your target Google Sheet."
},
"typeVersion": 1
},
{
"id": "5e10a3b1-73f2-4263-8ebd-2f9e0b7db9bf",
"name": "Haftnotiz6",
"type": "n8n-nodes-base.stickyNote",
"position": [
448,
-416
],
"parameters": {
"color": 5,
"width": 480,
"height": 336,
"content": "## Extraction Values\n* Once the workflow is set up and all nodes are configured, define the fields you want to extract from the *fax* content.\n\n* Add corresponding column fields in *Google Sheets* for each data point that needs to be extracted.\n\n* In the *LLM Chain* node prompt, specify the same fields as keys and provide example values to guide the extraction.\n\n* Update the *Structured Output Parser* with these keys and expected values to ensure the output is consistently structured and aligned with your Google Sheets columns."
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "7c15e905-123e-4655-bc9f-b712a70ddda2",
"connections": {
"a452a474-38ee-426b-b225-fd8f65bbd878": {
"main": [
[
{
"node": "ca632b40-621b-4359-9e80-31706f374831",
"type": "main",
"index": 0
}
]
]
},
"e570291a-6ca2-49f4-be02-a837be4444f6": {
"main": [
[
{
"node": "07953a5f-115a-4697-9961-f5d7046ec6db",
"type": "main",
"index": 0
}
]
]
},
"4e9b17d5-0ded-4edb-baa5-b7eae5d0ecfa": {
"main": [
[
{
"node": "5be36f47-e7ed-464a-bf73-6573abed5fc6",
"type": "main",
"index": 0
}
]
]
},
"07953a5f-115a-4697-9961-f5d7046ec6db": {
"main": [
[
{
"node": "4e9b17d5-0ded-4edb-baa5-b7eae5d0ecfa",
"type": "main",
"index": 0
}
]
]
},
"ca632b40-621b-4359-9e80-31706f374831": {
"main": [
[
{
"node": "37801239-6daf-4445-9004-01523094018a",
"type": "main",
"index": 0
}
]
]
},
"5be36f47-e7ed-464a-bf73-6573abed5fc6": {
"main": [
[
{
"node": "579a0a77-34bd-4f38-a22a-dfc68421b0b9",
"type": "main",
"index": 0
}
]
]
},
"bea9b647-0e25-47ee-9eab-c952f512b03f": {
"main": [
[
{
"node": "e570291a-6ca2-49f4-be02-a837be4444f6",
"type": "main",
"index": 0
}
]
]
},
"0330fa20-6915-42c5-8769-0f2658f5b035": {
"ai_languageModel": [
[
{
"node": "ca632b40-621b-4359-9e80-31706f374831",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"d022685e-fe91-4980-b257-0ec2e7989491": {
"ai_outputParser": [
[
{
"node": "ca632b40-621b-4359-9e80-31706f374831",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"579a0a77-34bd-4f38-a22a-dfc68421b0b9": {
"main": [
[
{
"node": "a452a474-38ee-426b-b225-fd8f65bbd878",
"type": "main",
"index": 0
}
]
]
}
}
}Wie verwende ich diesen Workflow?
Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.
Für welche Szenarien ist dieser Workflow geeignet?
Experte - Content-Erstellung, Multimodales KI
Ist es kostenpflichtig?
Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.
Verwandte Workflows
Intuz
@intuzWorkflow automation can help automate your routine activities and help saves $$$, as well as hours of time. As a boutique tech consulting company, Intuz help businesses with custom AI/ML, AI Workflow Automations, and software development. Automate your business workflow for: Sales Marketing Accounting Finance Operations E-Commerce Customer Support Admin & Backoffice Logistics & Supply Chain
Diesen Workflow teilen