# Extract invoice data to Excel with Gemini and OCR: n8n workflow

> Started by an incoming Telegram message, and works across Excel and Telegram. It hands the judgement calls to Gemini.

Source: https://millionrounds.com/workflow/extract-invoice-data-to-excel-with-gemini-and-ocr (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Money admin](https://millionrounds.com/workflows?category=Money+admin#library)

# Extract invoice data to Excel with Gemini and OCR

Started by an incoming Telegram message, and works across Excel and Telegram. It hands the judgement calls to Gemini. 23 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fextract-invoice-data-to-excel-with-gemini-and-ocr)

**23 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 1 Logic 12 Service 9

The steps in the order they run, from what starts it.

- 1 **Telegram Trigger** Telegram trigger *Starts it*
- 2 **Detect File Type** Code *Logic*
- 3 **Route by File Type** Switch *Logic*
- 4 **Mapping PDF** Set *Logic*
- 5 **Notifikasi file sedang diproses** Telegram *Service*
- 6 **Mapping Image** Set *Logic*
- 7 **Notifikasi file invalid** Telegram *Service*
- 8 **Get PDF** Telegram *Service*
- 9 **Get Image** Telegram *Service*
- 10 **Extract PDF Text** Extract From File *Service*
- 11 **Extract Text from Image (OCR)** Tesseract Node *Service*
- 12 **Clean PDF Text** Code *Logic*
- 13 **Clean OCR Text** Code *Logic*
- 14 **Prepare PDF Data** Set *Logic*
- 15 **Prepare Image Data** Set *Logic*
- 16 **Extract Structured Data (AI)** Google Gemini *Model*
- 17 **Parse AI Response** Code *Logic*
- 18 **Validate Extracted Data** Code *Logic*
- 19 **Check Data Validity** If *Logic*
- 20 **Format Data for Excel** Code *Logic*
- 21 **Send Invalid Data Notification** Telegram *Service*
- 22 **Save Data to Excel** Microsoft Excel *Service*
- 23 **Send Success Notification** Telegram *Service*

## How it's built

- **Starts on:** An incoming Telegram message
- **Steps:** 23, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Excel, Telegram
- **Model:** Gemini

## Questions

What does it need to run?

An n8n account, plus your own Excel and Telegram accounts, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming Telegram message.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 23 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 23 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fextract-invoice-data-to-excel-with-gemini-and-ocr)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Excel](https://millionrounds.com/workflows?service=Excel#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also money admin, with the same services where possible, closest in size first.

- [**Automated expense tracking from emails & Telegram with Gemini** 23 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/automated-expense-tracking-from-emails-and-telegram-with-gem)
- [**Process invoices & engineering emails with Gmail and Telegram** 23 steps · calls a model · Gmail, Telegram](https://millionrounds.com/workflow/process-invoices-and-engineering-emails-with-gmail-and-teleg)
- [**Process receipts with Google Vision OCR and Telegram** 23 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/process-receipts-with-google-vision-ocr-and-telegram)
- [**Extract and log Outlook invoices to OneDrive Excel with OpenAI** 24 steps · calls a model · Excel, Outlook](https://millionrounds.com/workflow/extract-and-log-outlook-invoices-to-onedrive-excel-with-open)
- [**Log receipt expenses in Notion with Gmail and Telegram** 24 steps · calls a model · Airtable, Gmail](https://millionrounds.com/workflow/log-receipt-expenses-in-notion-with-gmail-and-telegram)
- [**Route rental payment and receipt messages with Telegram** 22 steps · calls a model · Telegram](https://millionrounds.com/workflow/route-rental-payment-and-receipt-messages-with-telegram)