Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini

Name: Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini
Availability: InStock
Author: Divyanshu Gupta

Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini preview

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early 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

Overview

This template is designed for operations, finance, and accounting teams that need to automatically process scanned invoices and extract structured data without manual entry.

It is ideal for businesses handling vendor invoices, reimbursement forms, or bulk document intake.

What this workflow does

This workflow uses Sarvam AI Vision model to perform OCR on scanned invoices and extract raw text. The extracted content is then processed using an LLM to identify key invoice fields such as:

Vendor name
Invoice number
Invoice date
Total amount
GST / Tax amount

The structured data is automatically appended to Google Sheets for tracking, reconciliation, or downstream accounting automation.

Requirements

Sarvam Vision API key (configured using HTTP Header credentials)-(https://dashboard.sarvam.ai/key-management)
Google Gemini API key (configured via Google Gemini credentials in n8n)
Google Sheets OAuth credentials

How to set up

1.) Add your Sarvam API key in Credentials. 2.) Connect your Google Sheets account. 3.) Update the target Sheet ID. 4.)Test with a sample invoice PDF.

Need Help?

ask in the Forum!

Happy Hacking!

Divyanshu Gupta

4 workflows

Complexity

advanced

Published 28 Feb 2026

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/13779/13779.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Classify invoices and route them to Google Drive with easybits and Slack

## What This Workflow Does Upload a document (PDF, PNG, JPEG) via a web form and let **easybits Extractor** classify it into one of your defined categories. Based on the classification result and a confidence score, the document is automatically sorted into the correct **Google Drive** folder. Low-confidence or unrecognized documents are flagged for manual review via **Slack**. ## How It Works 1. User uploads a file through the hosted web form 2. The binary file is converted to base64 and sent to easybits 3. easybits returns a **document_type** and **confidence_score** 4. The classification result is merged with the original file binary 5. If confidence > 0.5 → routed to the matching Google Drive folder 6. If confidence ≤ 0.5 or no category match → uploaded to **Needs Review** folder + Slack alert **Supported categories:** `medical_invoice` · `restaurant_invoice` · `hotel_invoice` · `trades_invoice` · `telecom_invoice` --- ## Setup Guide ### 1. Set Up Your easybits Extractor Pipeline 1. Go to **extractor.easybits.tech** and create a new pipeline 2. Add two fields to the mapping: **document_class** and **confidence_score** 3. In each field's description, paste the corresponding classification or confidence prompt that tells the model how to analyze the document 4. The classification prompt should return exactly one category label – or `null` if uncertain 5. The confidence prompt should return a decimal number between 0.0 and 1.0 6. Save & test the pipeline, then copy your **Pipeline ID** and **API Key** ### 2. Set Up Google Drive 1. Create a folder in Google Drive for each category: **Medical**, **Restaurant**, **Hotel**, **Trades**, **Telecom**, and **Needs Review** 2. In n8n, go to **Settings → Credentials** and create a **Google Drive OAuth2** credential 3. This requires a **Client ID** and **Client Secret** from the Google Cloud Console (APIs & Services → Credentials → OAuth 2.0 Client ID) 4. Make sure the **Google Drive API** is enabled in your Google Cloud project 5. Open each of the 6 Google Drive upload nodes in this workflow and select the correct target folder ### 3. Set Up Slack 1. In n8n, go to **Settings → Credentials** and create a **Slack API** credential 2. You'll need a Slack Bot Token – create a Slack App at **api.slack.com/apps**, add the `chat:write` scope, and install it to your workspace 3. Create a channel for review notifications (e.g. `#n8n-invoice-review`) 4. Invite the bot to that channel 5. Open the **Review Message** node and select the correct channel ### 4. Connect the easybits Node 1. Open the **easybits Extractor (Classification)** node 2. Replace the pipeline URL with your own: `https://extractor.easybits.tech/api/pipelines/YOUR_PIPELINE_ID` 3. Create a **Bearer Auth** credential using your easybits API Key and assign it to the node ### 5. Activate & Test 1. Click **Active** in the top-right corner of n8n 2. Open the form URL and upload a test document 3. Check the execution log to verify the classification result 4. Confirm the file lands in the correct Google Drive folder 5. Test with an unrecognized document to verify the Slack notification fires

View

Benchmark invoice data extraction accuracy with easybits

## What This Workflow Does Upload the same invoice in different qualities (original PDF, scanned copy, phone photo, compressed JPEG, etc.) and instantly see how accurately each field was extracted. The workflow compares every extracted value against a fixed ground truth and returns a per-field pass/fail report with an overall accuracy percentage – directly in the browser. ## How It Works 1. **Upload** – A document is submitted through the n8n web form 2. **Extract** – easybits Extractor processes the file and returns structured data 3. **Compare** – Each extracted field is compared against the known correct values 4. **Report** – A completion screen shows which fields matched and the overall accuracy ## Setup Guide ### 1. Create Your easybits Extractor Pipeline 1. Go to [extractor.easybits.tech](https://extractor.easybits.tech/) and create a new pipeline 2. Upload one of the example invoices as your reference document – you can find them [here](https://github.com/felix-sattler-easybits/n8n-workflows/tree/88d7c9818b150e71dd749bf9f665359fa57efcb9/data-extraction-stresstest). 3. Click **Auto-Mapping** – the Extractor will automatically detect and set up all fields for you 4. Save the pipeline and copy your **Pipeline ID** and **API Key** ### 2. Connect Your easybits Credentials Open the **easybits Extractor** node in the workflow and connect your credentials (Pipeline ID & API Key). The node will use the pipeline you just created – no further configuration needed. ### 3. Adjust the Ground Truth (if needed) The **Ground Truth** node contains the expected values for all 10 fields. If you're testing with a different document, update these values to match your reference invoice. ### 4. Activate & Test the workflow by uploading your first test document --- ## 🔄 Want to Test a Different Extraction Solution? You can swap out the easybits Extractor node for an **HTTP Request node** pointing at any other extraction API. As long as your HTTP node returns the same field names under `json.data` (e.g. `data.invoice_number`, `data.amount_paid`, etc.), the rest of the workflow – ground truth comparison, validation, and results display – works identically. This makes it easy to benchmark multiple solutions side by side using the exact same test documents and accuracy criteria.

View

Generate invoice PDFs from Stripe payments using TemplateFox, Gmail and Drive

This workflow automatically generates and delivers professional invoice PDFs whenever a Stripe checkout session completes. It fetches the line items from Stripe, formats them into a clean invoice with your company details, generates a branded PDF via TemplateFox, emails it to the customer, and saves a copy to Google Drive. ## Problem Solved Without this automation, invoicing after a Stripe payment requires: - Monitoring your Stripe dashboard for completed checkouts - Manually creating an invoice with the correct line items and totals - Exporting as PDF and emailing it to the customer - Saving the invoice to your file storage for bookkeeping - Repeating this for every single payment This workflow handles all of that automatically for every Stripe checkout, including proper invoice numbering, due dates, and tax calculations. ## Who Can Benefit - **SaaS companies** billing customers through Stripe Checkout - **E-commerce stores** sending invoices after purchase - **Service providers** using Stripe for client payments - **Freelancers** who want automatic invoicing after payment - **Accountants** who need invoice PDFs archived in Google Drive ## Prerequisites - [TemplateFox](https://templatefox.com) account with an API key (free tier available) - Stripe account with API access - Gmail account with OAuth2 configured - Google Drive account with OAuth2 configured - Install the **TemplateFox** community node from Settings → Community Nodes ## Setting Up Your Template You need a TemplateFox invoice template for this workflow. You can: 1. **Start from an example** — Browse [invoice templates](https://templatefox.com/templates/invoice), pick one you like, and customize it in the visual editor to match your branding 2. **Create from scratch** — Design your own invoice template in the [TemplateFox editor](https://app.templatefox.com) Once your template is ready, select it from the dropdown in the TemplateFox node — no need to copy template IDs manually. ## Workflow Details **Step 1: Stripe Trigger** Fires on every completed checkout session (`checkout.session.completed`). This captures successful payments with full customer and product details. **Step 2: Get Line Items** An HTTP Request node calls the Stripe API to fetch the line items for the checkout session (product names, quantities, amounts). Stripe doesn't include line items in the webhook payload, so this separate call is required. **Step 3: Format Invoice Data** A Code node combines the Stripe session data and line items into a clean invoice structure: company details, client info (from Stripe customer), line items with prices, subtotal, tax, total, invoice number (auto-generated from date + session ID), and due date (Net 30). **Step 4: TemplateFox — Generate Invoice** Select your invoice template from the dropdown — the node automatically loads your template's fields. Map each field to the matching output from the Code node (e.g. `client_company` → `{{ $json.client_company }}`). TemplateFox generates a professional invoice PDF using your custom template. **Step 5a: Email Invoice** Sends the invoice PDF link to the customer via Gmail with invoice number, amount, and due date. **Step 5b: Save to Google Drive** Downloads the PDF and uploads it to a Google Drive folder for bookkeeping. Runs in parallel with the email step. ## Customization Guidance - **Company details:** Set your company name, address, logo, bank details, and VAT number directly in the template editor — they never change between invoices, so there's no reason to pass them from n8n. - **Invoice numbering:** Modify the `invoiceNumber` format in the Code node (default: `INV-YYYY-MMDD-XXXXXX`). - **Payment terms:** Change the due date calculation (default: Net 30). - **Drive folder:** Set your Google Drive folder ID in the "Save to Google Drive" node. - **Template:** Use any invoice template from your TemplateFox account — select it from the dropdown. - **Email body:** Customize the invoice email text in the "Email Invoice" node. **Note:** This template uses the [TemplateFox community node](https://www.npmjs.com/package/n8n-nodes-templatefox). Install it from Settings → Community Nodes.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini

Workflow preview

Overview

This template is designed for operations, finance, and accounting teams that need to automatically process scanned invoices and extract structured data without manual entry.

What this workflow does

Requirements

How to set up

Need Help?