Automate Invoice Data Extraction with OCR.space, GPT, and Google Sheets

This n8n workflow automates the process of extracting key data from invoice PDFs stored in Google Drive, processing it with OCR.space and OpenAI's GPT, and then saving the structured information into a Google Sheet.

It's designed to streamline invoice management, reducing manual data entry and improving accuracy.

What it does

1. Triggers on a Schedule: The workflow runs periodically (e.g., every hour) to check for new invoices.
2. Lists Files in Google Drive: It searches a specified Google Drive folder for new PDF invoice files.
3. Extracts Text with OCR.space: For each PDF invoice found, it sends the file to the OCR.space API to extract all text content.
4. Processes Text with OpenAI (GPT): The extracted text is then sent to OpenAI's GPT model with a specific prompt to identify and extract structured data like invoice number, vendor, total amount, date, and line items.
5. Formats Data: A Code node processes the GPT output to ensure the extracted data is in a consistent, structured format suitable for a spreadsheet.
6. Appends to Google Sheets: The structured invoice data is then added as a new row to a designated Google Sheet.

Prerequisites/Requirements

• n8n Account: A running n8n instance (cloud or self-hosted).
• Google Account: With access to Google Drive (for storing invoices) and Google Sheets (for storing extracted data).
• OCR.space API Key: For optical character recognition of PDF invoices.
• OpenAI API Key: For using GPT to extract structured data from the OCR output.

Setup/Usage

1. Import the Workflow: Download the provided JSON and import it into your n8n instance.
2. Configure Credentials:
   • Google Drive: Set up a Google OAuth2 credential for Google Drive.
   • Google Sheets: Set up a Google OAuth2 credential for Google Sheets.
   • HTTP Request (OCR.space): Configure a new credential for OCR.space using your API key. This will likely be an "API Key" credential type.
   • OpenAI: Configure an OpenAI API credential with your OpenAI API key.
3. Customize Nodes:
   • Schedule Trigger: Adjust the schedule frequency as needed (e.g., daily, hourly).
   • Google Drive:
     • Specify the "Folder ID" where your invoice PDFs are stored.
     • Ensure the "Operation" is set to "Get All" or "List" files, and filter for PDF files if necessary.
   • HTTP Request (OCR.space):
     • Verify the URL for OCR.space API (e.g., https://api.ocr.space/parse/image).
     • Ensure the "API Key" is correctly passed in the headers or body as required by OCR.space.
     • Confirm the file input is correctly mapped from the Google Drive node.
   • OpenAI:
     • Select the appropriate GPT model (e.g., gpt-4, gpt-3.5-turbo).
     • Review and adjust the prompt to accurately guide GPT in extracting the desired invoice fields (e.g., "Extract invoice number, vendor name, date, total amount, and line items from the following text: {{ $json.ocrText }}").
   • Code:
     • Examine the JavaScript code to ensure it correctly parses and formats the output from the OpenAI node into the structure you want for your Google Sheet.
     • Modify the code if you need to extract different fields or require a specific output format.
   • Google Sheets:
     • Specify the "Spreadsheet ID" and "Sheet Name" where the extracted invoice data should be appended.
     • Map the output fields from the Code node to the correct columns in your Google Sheet.
4. Activate the Workflow: Once configured, activate the workflow to start automating your invoice data extraction.