Extract Structured Invoice Data from JotForm PDFs with GPT-4.1-mini & Sheets

Description

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




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