Extract Data from Invoices with OCR, Gemini AI, and Airtable
UnknownWhat this workflow does
This AI workflow has 11 nodes and runs on Local File events (add). Along the way it connects Google Gemini Chat Model, Telegram, Airtable and Tesseractjs (community) and 1 more.
How it runs
Trigger: On Local File events (add).
- Read File (Read/Write Files from Disk): reads a file from disk
- Check File Type (If): checks a condition and branches into true / false
- Pdf Page Extract: uses Pdf Page Extract
- Tesseract (Tesseract Node): uses Tesseract Node
- Switch: routes items into 3 branches
- Aggregate: combines items into one
- Extract Invoice Data (Gemini) (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; 1 tool (Save to Airtable)
- Telegram: uses Telegram
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 2 community packages, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-tesseractjs is verified or supports 3.0 (used in Tesseract).
- Check that n8n-nodes-pdf-page-extract is verified or supports 3.0 (used in PDF Page Extract).
Nodes used (11)
- Local File Trigger
n8n-nodes-base.localFileTrigger - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Tesseract Node
n8n-nodes-tesseractjs.tesseractNode - Switch
n8n-nodes-base.switch - Aggregate
n8n-nodes-base.aggregate - Pdf Page Extract
n8n-nodes-pdf-page-extract.pdfPageExtract - Telegram
n8n-nodes-base.telegram - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - AI Agent
@n8n/n8n-nodes-langchain.agent - If
n8n-nodes-base.if - Airtable Tool
n8n-nodes-base.airtableTool
From the author
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. 📖 Extract Data from Invoices with OCR, Gemini AI, and Airtable This template automates the process of extracting key details from invoices (PDF, JPG, PNG)…