Extract structured invoice data from JotForm PDFs with GPT-4.1-mini & Sheets

Name: Extract structured invoice data from JotForm PDFs with GPT-4.1-mini & Sheets
Availability: InStock
Rating: 4.5 (13 reviews)
Author: Ranjan Dailata

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER 🎉 Early Black Friday Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Who this is for

This workflow is designed for Finance teams, accounting professionals, and automation engineers.

Use Case:

Automates processing of invoice submissions received via JotForm.

Core Function: Extracts structured data such as:
- Invoice number
- Client information
- Totals and tax amounts
- Line items or services
Key Benefit: Eliminates manual data entry, saving time and reducing human error.
Automation Goal: Streamline document handling with AI-powered PDF parsing and structured output generation.

Ideal users include:

Accounting or finance teams handling form-based invoice uploads
Automation specialists using n8n for document processing
Developers integrating invoice data into Google Sheets or CRMs

What problem this workflow solves

Manually extracting structured data from invoice PDFs submitted through JotForm is time-consuming, error-prone, and repetitive.

This workflow solves that by:

Automatically receiving the PDF through JotForm’s webhook
Extracting structured fields (invoice number, company, client, line items, totals, etc.) using GPT-4-mini
Saving the extracted data directly to Google Sheets
Writing structured JSON data to disk for archival or further processing

What this workflow does

Webhook Trigger (JotForm → n8n) JotForm submission sends invoice data and attachment link to n8n.
Parse Submission & Extract Metadata Extracts submission metadata (form ID, user details, invoice number, file link, etc.) using the Information Extractor node.
Download PDF Attachment Fetches the uploaded PDF from JotForm’s secure file URL via the HTTP Request node, authenticated using a JotForm API key.
Store & Process File Saves the invoice to disk and prepares it for AI processing.
Extract Invoice Text Content Uses the Extract from File node to parse text from the PDF document.
AI-Powered Structured Extraction (OpenAI GPT-4.1-mini) Sends the extracted text to a LangChain LLM Chain with a Structured Output Parser, ensuring consistent JSON output aligned with a defined schema.
Save Extracted Data
- Writes structured JSON to disk
- Appends parsed results to Google Sheets for easy reporting

Setup Instructions

Prerequisites

A JotForm account with a form containing an invoice PDF upload field

You may build the invoice Jotform by leveraging the Jotform Templates

Invoice Upload Form

A Google Sheets account with a connected spreadsheet
OpenAI
n8n running locally or on a server with public webhook access (e.g. via loca.lt, ngrok, or n8n.cloud)
Make sure to get the Jotform API Key via the Jotform Account API Key

Steps

Import the provided JSON into n8n
- Go to n8n → Workflows → Import from File/Clipboard
- Paste the provided JSON definition
Configure Webhook
- Copy the webhook URL from the Webhook node
- Paste it into your JotForm’s Settings → Integrations → Webhook URL
Set API Keys & Credentials
- Ensure the Jotform API key has been setup to download the Jotform PDF document
- Ensure your Google Sheets and OpenAI credentials are connected
Test Submission
- Submit your JotForm with an invoice PDF
- n8n workflow will trigger automatically
Check Outputs
- Open your Google Sheet to see structured invoice entries
- Check the disk folder (e.g., C:\Invoices) for JSON exports

How to customize this workflow

Change AI Model Use the OpenAI Chat Model for Structured Data node. → Replace gpt-4.1-mini with gemini-1.5-pro or any other LLM node of your choice.
Adjust Output Schema Modify the Structured Output Parser node. → Edit the JSON schema to match your desired output fields and format.
Save to a Different Location In the Write the Structured Invoice to Disk node, → Update the file path pattern (e.g. /data/invoices/{{invoiceId}}.json).
Log to a Database Instead of Google Sheets Replace the Append or Update Row in Sheet node → with a MySQL or PostgreSQL node for database logging.
Add Notifications Extend the workflow by adding Slack or Email nodes → to send alerts when a new invoice extraction is completed.

Summary

The Structured Invoice Data Extraction from JotForm PDFs via Google Gemini, Converts JotForm-uploaded invoice PDFs into structured financial data automatically.

Key Features:

No manual parsing fully automated
Works with any invoice layout via AI
Saves structured results to Google Sheets + JSON file
Extensible for CRMs, QuickBooks, or ERP sync

Ranjan Dailata

0 workflows

Nodes

set gmail telegram agent google-gemini

Complexity

advanced

Published 21 Oct 2025

Likes 0

View on n8n.io Download Workflow

✨

Share Your Workflow

Have a great workflow to share? Join the n8n Creator Hub and help the community!

Submit Your Template How to Submit

Related Workflows

Send Stripe invoice reminders with GPT-4.1-mini, Google Sheets and Slack

## Who this workflow is for Accounting and bookkeeping firms needing automated invoice creation and payment reminders. ## What this workflow does AI generates personalized emails for overdue invoices, logs invoice info in Google Sheets, notifies accountants via Slack, creates PDF invoices, and schedules follow-ups. ## How the workflow works 1. Invoice creation triggers workflow 2. AI drafts personalized email 3. Routes based on payment status 4. Logs invoice info in Google Sheets 5. Sends Slack notifications to accountant 6. Sends email to client 7. Generates PDF invoice 8. Schedules follow-up events 9. Optional CRM/accounting tool integration **Author:** Hyrum Hurst, AI Automation Engineer **Company:** QuarterSmart **Contact:** [email protected]

View

Send automated payment reminders for Xero invoices via Outlook email

## Who's this for Small business owners, finance teams, accountants, and bookkeepers who use Xero for invoicing and want to improve cash flow by automating payment reminders. If you're spending time manually following up on unpaid invoices or struggling with late payments, this workflow eliminates the manual effort and ensures consistent, timely communication with customers while maintaining a complete audit trail. ## What it does This workflow automatically monitors all invoices in your Xero account and sends friendly payment reminders to customers when invoices are approaching their due date. It runs daily at noon, checks every invoice, calculates how many days until payment is due, sends personalized email reminders for invoices due within 7 days, and logs each reminder activity back into Xero's invoice history. The automation ensures no invoice slips through the cracks, reduces the administrative burden of accounts receivable management, and maintains professional customer relationships through polite, timely reminders—all while keeping your Xero records up to date with reminder tracking. ## How it works The workflow executes automatically every day at 12 PM and follows this process: - Triggers the daily check using the Schedule Trigger node - Fetches all invoices from your Xero account using the Xero API integration - Filters out invoices that are already marked as "PAID" to avoid sending unnecessary reminders - Calculates the number of days remaining until each unpaid invoice is due using a JavaScript code node - Identifies invoices that are due within the next 7 days (customizable threshold) - Sends personalized email reminders to customers via Microsoft Outlook, including invoice number, due date, and amount - Logs the reminder activity back into Xero's invoice history with the date sent and days until due - Creates a complete audit trail in Xero showing when reminders were sent for each invoice The workflow only sends reminders for invoices meeting the criteria, so customers aren't bombarded with unnecessary emails. The Xero history logging ensures your team can see at a glance which customers have been reminded and when, preventing duplicate reminders and providing accountability. ## Requirements - Xero account with API access enabled (available to all Xero users at no additional cost) - Microsoft Outlook or Office 365 account for sending email reminders - Valid email addresses configured for all customers in your Xero contact records - n8n instance (self-hosted or cloud) with credentials configured for: - Xero OAuth2 connection (used twice: once for fetching invoices, once for logging history) - Microsoft Outlook OAuth2 connection ## Setup instructions **1. Enable Xero API access** Ensure your Xero account has API access enabled. This is available by default for all Xero accounts. You'll need administrator access to create the API connection. **2. Configure n8n credentials** In your n8n instance, set up OAuth2 credentials for: - **Xero:** Follow n8n's Xero credential documentation to authorize access to your Xero organization. Make sure the credentials have permission to both read invoices and write to invoice history. - **Microsoft Outlook:** Set up OAuth2 connection to allow n8n to send emails on your behalf **3. Assign credentials to nodes** Open the workflow and assign your configured credentials to these nodes: - "Fetch All Xero Invoices" → Select your Xero credential - "Send Email Reminder to Customer" → Select your Microsoft Outlook credential - "Log Reminder in Xero History" → Select your Xero credential (same as above) **4. Customize the email template** Edit the "Send Email Reminder to Customer" node to personalize the message: - Update the sender name and signature - Add your company branding or logo - Include payment instructions or online payment links - Adjust the tone to match your customer communication style - Add any legal disclaimers or terms if required - Customize the subject line if needed **5. Adjust the reminder threshold (optional)** By default, reminders are sent for invoices due within 7 days. To change this: - Open the "Calculate Days Until Due" code node - Find the line: `isDueSoon: diffDays <= 7 && diffDays >= 0` - Change `7` to your preferred number of days (e.g., `14` for two weeks notice) **6. Test the workflow** Before enabling the daily schedule: - Use the manual trigger to test with your actual Xero data - Verify that invoices are fetched correctly - Check that the date calculations are accurate - Send a test email to yourself to review the message format - Confirm the reminder is logged in Xero's invoice history - Verify only qualifying invoices trigger reminders **7. Activate the workflow** Once testing is complete, activate the workflow. It will run automatically every day at noon (or your customized schedule time).

View

Post bank statement transactions to QuickBooks Online using OpenRouter AI

## ✅ What problem does this workflow solve? Manually entering bank statements into QuickBooks is one of the most time-consuming and error-prone accounting tasks. Accountants often spend hours converting PDF bank statements into individual income and expense entries—risking missed transactions, incorrect categorization, and inconsistencies. This workflow **fully automates the end-to-end process**: from uploading a (even password-protected) bank statement PDF to creating **accurate Sales Receipts and Expenses directly inside QuickBooks**, using AI and n8n. --- ## ⚙️ What does this workflow do? - Accepts bank statement PDFs via a secure web form - Decrypts and extracts text from password-protected PDFs - Uses AI to extract **structured transactions** from raw statement text - Validates AI output against a strict JSON schema - Processes each transaction individually for reliability - Automatically routes transactions based on type: - **Credits → Income (Sales Receipts)** - **Debits → Expenses** - Intelligently creates missing QuickBooks entities: - Customers - Vendors - Items - Expense categories - Posts transactions directly into QuickBooks - Eliminates manual accounting entry completely --- ## 🧠 How It Works – End-to-End Flow ### 1️⃣ Secure Bank Statement Upload A user uploads a bank statement PDF (normal or password-protected) using an **n8n Form Trigger**. ### 2️⃣ PDF Decryption & Text Extraction The workflow: - Unlocks the PDF (if password-protected) - Extracts the full statement text using the **Extract PDF Text** node ### 3️⃣ AI-Powered Transaction Extraction An **AI Agent** reads the raw bank statement text and extracts every transaction with high precision: - Transaction type (credit / debit) - Date (YYYY-MM-DD)` - Amount - Description - Reference number - Payee / counterparty ### 4️⃣ Strict JSON Validation AI output is validated using a **Structured Output Parser** to ensure: - No malformed data - Schema-safe transactions - Reliable downstream processing ### 5️⃣ Transaction Processing Loop Each transaction is processed individually using batching and loop control to guarantee accuracy. ### 6️⃣ Smart Routing: Credit vs Debit A switch node routes transactions automatically: - **Credits** → Income flow - **Debits** → Expense flow --- ## 💰 Credit Path – Income Automation For every **credit transaction**: - Checks if a matching QuickBooks item exists - Creates missing service items automatically - Finds or creates the customer - Builds a **Sales Receipt payload** - Posts the transaction into QuickBooks as income --- ## 💸 Debit Path – Expense Automation For every **debit transaction**: - Searches for the vendor by payee name - Creates the vendor if missing - Loads expense categories from the Chart of Accounts - Auto-maps transactions to the correct category using keyword logic - Builds a **Purchase (Expense) payload** - Posts the expense into QuickBooks --- ## 🧠 Built-In QuickBooks Intelligence This workflow intelligently handles: - Duplicate prevention - Missing customer/vendor creation - Automatic item mapping - Category resolution using transaction descriptions - Consistent accounting structure across all entries --- ## 📊 Results & Benefits ✅ Zero manual bank statement entry ✅ Works with password-protected PDFs ✅ Handles both income and expenses automatically ✅ Creates clean, structured QuickBooks records ✅ Saves **dozens of accounting hours every month** ✅ Reduces human error and reconciliation issues --- ## 🔧 Setup Requirements 1. Connect your **QuickBooks Online** account (Sandbox or Production) 2. Add **OpenRouter / AI model credentials** for transaction extraction 3. Update the PDF password (if required) in the extraction node 4. Replace `company_id` in QuickBooks API endpoints 5. Verify QuickBooks account IDs (bank, income, expense) 6. Test with a sample bank statement PDF --- ## 👤 Who is this for? This workflow is ideal for: - 📒 Accountants & bookkeeping firms - 🏢 Businesses managing frequent bank statements - 💼 Finance teams using QuickBooks Online - 🤖 Automation-first accounting systems

View

👨‍💻

Need Custom Automation?

N8N Automation Expert

Specialized in N8N automation, I design custom workflows that connect your tools and automate your processes.