Extract invoice data from scanned PDFs to Google Sheets with Sarvam and Gemini
Ready for 3.0What this workflow does
This AI workflow has 16 nodes and runs when someone submits an n8n form. Along the way it connects Google Gemini Chat Model and Google Sheets.
How it runs
Trigger: When someone submits an n8n form.
- Create Sarvam invoice OCR job (HTTP Request): calls an HTTP API
- Merge: merges the data from its input branches
- Generate Sarvam presigned upload URL (HTTP Request): calls an HTTP API
- Upload invoice PDF to Sarvam (HTTP Request): calls an HTTP API
- Start Sarvam invoice OCR (HTTP Request): calls an HTTP API
- Check Sarvam OCR status (HTTP Request): calls an HTTP API
- Wait: pauses before continuing
- Get OCR Result (HTTP Request): calls an HTTP API
- Download Sarvam OCR output ZIP (HTTP Request): calls an HTTP API
- Decompress OCR result file (Compression): uses Compression
…plus 4 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - n8n Form Trigger
n8n-nodes-base.formTrigger - Merge
n8n-nodes-base.merge - Compression
n8n-nodes-base.compression - Extract from File
n8n-nodes-base.extractFromFile - Code
n8n-nodes-base.code - Google Sheets
n8n-nodes-base.googleSheets
From the author
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…