Invoice and lorry receipt extractor

The brief

Transporters retype invoices and lorry receipts (LRs) into their systems. Build an extractor that reads them into validated shipment records (consignor, consignee, route, weight, charges, GSTIN), checks the numbers, and flags anything unsure. Good looks like: a schema, validation of GSTIN, weights and totals, and accuracy per field on 30 labelled documents.

What you will build

1. Create sample invoices and LRs in several layouts
2. Define the shipment record schema
3. Extract with a vision-capable LLM and structured outputs
4. Validate GSTIN, weights and totals
5. Measure accuracy and flag unsure documents

Free, open data to build it with

• CORD: receipt understanding dataset ↗ Clova AI (GitHub)

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.