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

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

1. Workflow 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 busines...

Best for

Invoice Processing automation workflows
AI Summarization automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.httprequest, n8n-nodes-base.wait, @n8n/n8n-nodes-langchain.informationextractor, @n8n/n8n-nodes-langchain.lmchatgooglegemini, n8n-nodes-base.stickynote, n8n-nodes-base.formtrigger, n8n-nodes-base.merge, n8n-nodes-base.compression

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Divyanshu Gupta.

Original n8n.io source

1.1 Workflow description

Title: Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini
Workflow name: Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini

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!

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Get OCR Result

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 2 - Wait

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 3 - Information Extractor

Type / Role: @n8n/n8n-nodes-langchain.informationExtractor - informationExtractor
Config choices: Version 1.2

Block 4 - Google Gemini Chat Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices: Version 1

Block 5 - Sticky Note5

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Sticky Note7

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 7 - Sticky Note6

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 8 - Sticky Note8

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 9 - Sticky Note9

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 10 - Sticky Note10

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 11 - Sticky Note11

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 12 - Trigger – Invoice upload (PDF)

Type / Role: n8n-nodes-base.formTrigger - formTrigger
Config choices: Version 2.5

Block 13 - Create Sarvam invoice OCR job

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 14 - Generate Sarvam presigned upload URL

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 15 - Merge job details with upload URL

Type / Role: n8n-nodes-base.merge - merge
Config choices: Version 3.2

Block 16 - Upload invoice PDF to Sarvam

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 17 - Start Sarvam invoice OCR

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 18 - Check Sarvam OCR status

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 19 - Download Sarvam OCR output ZIP

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.4

Block 20 - Decompress OCR result file

Type / Role: n8n-nodes-base.compression - compression
Config choices: Version 1.1

Block 21 - Extract invoice OCR JSON

Type / Role: n8n-nodes-base.extractFromFile - extractFromFile
Config choices: Version 1.1

Block 22 - Prepare invoice text for LLM

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 23 - Append extracted invoice data to Google Sheets

Type / Role: n8n-nodes-base.googleSheets - googleSheets
Config choices: Version 4.7

3. Summary Table

Workflow	Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini
Complexity	advanced
Nodes	23
Categories	Invoice Processing, AI Summarization
Author	Divyanshu Gupta
Published	28 Feb 2026

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/13779/13779.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Invoice Processing workflows AI Summarization workflows

Frequently asked questions

What does Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Invoice Processing, AI Summarization use case.

Divyanshu Gupta

10 workflows

Nodes

n8n-nodes-base.httprequest n8n-nodes-base.wait @n8n/n8n-nodes-langchain.informationextractor @n8n/n8n-nodes-langchain.lmchatgooglegemini n8n-nodes-base.stickynote n8n-nodes-base.formtrigger n8n-nodes-base.merge n8n-nodes-base.compression

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

Send Stripe payment invoices with Gmail, Google Drive, and WhatsApp

## Quick overview This workflow triggers on successful Stripe payment events, generates and finalizes invoices, then formats and sends invoice details via Gmail, stores invoice PDFs in Google Drive, and notifies an admin through WhatsApp using Rapiwa. ## How it works 1. Triggers when Stripe reports a successful payment, invoice payment, or checkout session completion. 2. Checks whether the payment amount matches the amount received and, if it does not, calculates a payment summary for review. 3. Retrieves the Stripe customer and creates then finalizes a Stripe invoice configured to be sent with Net 30 terms. 4. Fetches invoices created since the event time, iterates through the results, and keeps only Stripe objects that are invoices. 5. Pulls Stripe checkout session line items and formats company, customer, totals, and a custom invoice number for messaging and file naming. 6. Emails the customer the invoice details and PDF link via Gmail, sends an admin WhatsApp alert via Rapiwa, downloads the PDF, and uploads it to Google Drive. ## Setup 1. Add Stripe API credentials, enable the Stripe webhook events used by the trigger, and copy the webhook URL into your Stripe dashboard. 2. Add Gmail OAuth2 credentials and confirm the workflow’s Gmail “send to” mapping matches the email field returned by your Stripe checkout session. 3. Add Google Drive OAuth2 credentials and set the target Drive folder in the Google Drive upload step. 4. Add Rapiwa API credentials and replace the placeholder WhatsApp number with your admin number. 5. Update the company identity, banking details, and any invoice terms (for example days until due) in the invoice formatting and Stripe invoice creation steps. ## Requirements - **Stripe API**: Connects to the Stripe account to listen for webhooks (`payment_intent.succeeded`, `checkout.session.completed`, etc.) and perform API operations (retrieve customers, create invoices, finalize invoices). - **Gmail OAuth2**: Used to send the generated invoice PDF and details to the customer. - *Google Drive OAuth2**: Used to upload and save the generated PDF invoices to a cloud storage folder. - **Rapiwa API**: Used to send WhatsApp notifications to the admin regarding order details and workflow status. ## Customization - Adjust invoice settings in the **Create Stripe Invoice** and **Finalize Invoice** nodes (e.g., due date, collection method, - Customize the customer email content in the **Email (Send Invoice)** node. - Update the **Invoice Save to Google Drive** node's `folderId` to store PDFs in a specific Google Drive folder. ## Additional info • Uses Stripe events for payment validation and invoice generation • Update company details in the **Format Invoice Data** node to match your business • Dynamically fetches purchased items from Stripe sessions • Validates payment amounts before processing invoices • Replace the placeholder WhatsApp number in the **Rapiwa** node with your admin number

View

Send escalating invoice reminders with Notion, Claude, Gmail and Telegram

## Quick overview This workflow runs every morning to pull unpaid invoices from a Notion database, calculates how overdue each one is, uses Anthropic Claude to draft an escalation-appropriate reminder, emails the client via Gmail, updates the invoice record in Notion, and alerts you in Telegram for high-risk late payments. ## How it works 1. Runs every day at 8:00 AM on a schedule. 2. Fetches all unpaid invoice pages from a Notion database and normalizes the key invoice fields into a flat structure. 3. Calculates days overdue from the due date, determines which reminder tier (1/2/3) is due based on thresholds and what was already sent, and skips invoices that are not yet due for the next escalation. 4. Uses Anthropic Claude to generate a subject line and message body that matches the escalation tier. 5. Sends the reminder email to the client via Gmail and updates the Notion page to record the latest reminder tier sent. 6. If the invoice reaches the final (tier 3) escalation, sends a Telegram message to the freelancer to flag the invoice as a payment risk. ## Setup 1. Create or choose a Notion invoice database with the properties referenced by the workflow (including Status, Due Date, Client Email, and Reminder Tier Sent) and paste the database ID into the Notion node configuration. 2. Add credentials for Notion, Anthropic (Claude), Gmail, and Telegram, and select them in their respective nodes. 3. Set your Telegram chat ID in the Telegram node and ensure your Notion Status values match the workflow filter (for example, invoices to remind are marked as “unpaid”).

View

Recover overdue invoices with GPT-4o-mini, Gmail, Google Sheets, and Slack

## Quick overview This workflow runs daily to read overdue invoices from Google Sheets, uses OpenAI (GPT-4o-mini) to draft personalized reminder emails and determine escalation level, sends emails via Gmail, posts Slack alerts for no-invoice runs or AI errors, and logs results back to Google Sheets. ## How it works 1. Runs every 24 hours on a schedule. 2. Reads rows from the “invoices” tab in Google Sheets and, if no invoice value is found, posts a “no overdue invoices” message to Slack. 3. For each invoice, sends the invoice details to OpenAI (GPT-4o-mini) to determine an escalation level, draft an HTML email, and recommend whether to escalate. 4. Parses the AI’s JSON response (falling back to a default reminder if parsing fails) and sends the recovery email to the client via Gmail. 5. If the AI recommends escalation, sends an internal escalation email via Gmail to the legal/AR team with invoice details and the AI summary. 6. Updates the original invoice row in Google Sheets with the escalation level and summary, then appends an audit row to the “Recovery sheet” tab including the email subject, summary, and sent message label ID. 7. If the AI step errors, posts an error alert to Slack and continues processing. ## Setup 1. Add Google Sheets OAuth2 credentials and replace YOUR_GOOGLE_SHEET_ID, ensuring the “invoices” and “Recovery sheet” tabs and columns (Invoice, Client, Email, Amount, Due Date, Days Overdue, Reminders Sent, plus row_number) match the workflow. 2. Add an OpenAI credential for the GPT-4o-mini model. 3. Add Gmail OAuth2 credentials and set the reply-to address ([email protected]) and escalation recipient ([email protected]) to your real emails. 4. Add Slack OAuth2 credentials, replace YOUR_SLACK_CHANNEL_ID, and choose the channel that should receive status and error alerts.

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

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

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?

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - Get OCR Result

Block 2 - Wait

Block 3 - Information Extractor

Block 4 - Google Gemini Chat Model

Block 5 - Sticky Note5

Block 6 - Sticky Note7

Block 7 - Sticky Note6

Block 8 - Sticky Note8

Block 9 - Sticky Note9

Block 10 - Sticky Note10

Block 11 - Sticky Note11

Block 12 - Trigger – Invoice upload (PDF)

Block 13 - Create Sarvam invoice OCR job

Block 14 - Generate Sarvam presigned upload URL

Block 15 - Merge job details with upload URL

Block 16 - Upload invoice PDF to Sarvam

Block 17 - Start Sarvam invoice OCR

Block 18 - Check Sarvam OCR status

Block 19 - Download Sarvam OCR output ZIP

Block 20 - Decompress OCR result file

Block 21 - Extract invoice OCR JSON

Block 22 - Prepare invoice text for LLM

Block 23 - Append extracted invoice data to Google Sheets

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions