{ "dataset": "lezzwork-invoice-extraction-v1", "description": "10 synthetic supplier invoices as plain text, with the expected extraction values. Vendors, VAT numbers and addresses are invented.", "license": "CC0 \u2014 use freely", "invoices": [ { "id": "I01", "vendor": "Northwind Studio", "vendor_vat": "BG203344556", "vendor_address": "Sofia, 12 Vitosha Blvd", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1005", "issue_date": "2026-08-25", "due_date": "2026-09-08", "currency": "EUR", "lines": [ { "description": "Design revisions", "qty": 8, "unit": "hour", "unit_price": 70, "amount": 560 }, { "description": "Photography half day", "qty": 1, "unit": "day", "unit_price": 450, "amount": 450 }, { "description": "Website maintenance", "qty": 1, "unit": "month", "unit_price": 120, "amount": 120 } ], "net": 1130, "vat_rate": 0.2, "vat_amount": 226.0, "total": 1356.0, "quirk": "date_dmY" }, { "id": "I02", "vendor": "Bluefin Consulting", "vendor_vat": "DE812345678", "vendor_address": "Hamburg, Alsterweg 4", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1012", "issue_date": "2026-08-12", "due_date": "2026-09-11", "currency": "EUR", "lines": [ { "description": "Training session", "qty": 2, "unit": "session", "unit_price": 300, "amount": 600 }, { "description": "Cloud storage 1 TB", "qty": 1, "unit": "month", "unit_price": 9.9, "amount": 9.9 }, { "description": "Copywriting", "qty": 3, "unit": "page", "unit_price": 60, "amount": 180 } ], "net": 789.9, "vat_rate": 0.2, "vat_amount": 157.98, "total": 947.88, "quirk": "" }, { "id": "I03", "vendor": "CloudHost EU", "vendor_vat": "NL854321098", "vendor_address": "Amsterdam, Keizersgracht 210", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1016", "issue_date": "2026-08-19", "due_date": null, "currency": "EUR", "lines": [ { "description": "Hosting plan", "qty": 2, "unit": "month", "unit_price": 29, "amount": 58 }, { "description": "Website maintenance", "qty": 5, "unit": "month", "unit_price": 120, "amount": 600 }, { "description": "Cloud storage 1 TB", "qty": 2, "unit": "month", "unit_price": 9.9, "amount": 19.8 } ], "net": 677.8, "vat_rate": 0.21, "vat_amount": 142.34, "total": 820.14, "quirk": "no_due_date" }, { "id": "I04", "vendor": "Cedar House Architects", "vendor_vat": "BG176543210", "vendor_address": "Plovdiv, 8 Ivan Vazov St", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1024", "issue_date": "2026-08-12", "due_date": "2026-08-26", "currency": "EUR", "lines": [ { "description": "Hosting plan", "qty": 10, "unit": "month", "unit_price": 29, "amount": 290 }, { "description": "Website maintenance", "qty": 5, "unit": "month", "unit_price": 120, "amount": 600 } ], "net": 890, "vat_rate": 0.2, "vat_amount": 178.0, "total": 1068.0, "quirk": "date_dmY" }, { "id": "I05", "vendor": "Pixel & Thread", "vendor_vat": "IT01234567890", "vendor_address": "Milano, Via Torino 22", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1029", "issue_date": "2026-08-10", "due_date": "2026-08-24", "currency": "EUR", "lines": [ { "description": "Website maintenance", "qty": 2, "unit": "month", "unit_price": 120, "amount": 240 }, { "description": "Hosting plan", "qty": 8, "unit": "month", "unit_price": 29, "amount": 232 } ], "net": 472, "vat_rate": 0.2, "vat_amount": 94.4, "total": 566.4, "quirk": "" }, { "id": "I06", "vendor": "Greenway Landscaping", "vendor_vat": "BG204455667", "vendor_address": "Varna, 3 Primorski Blvd", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1037", "issue_date": "2026-08-13", "due_date": "2026-09-12", "currency": "EUR", "lines": [ { "description": "Photography half day", "qty": 3, "unit": "day", "unit_price": 450, "amount": 1350 } ], "net": 1282.5, "vat_rate": 0.21, "vat_amount": 269.32, "total": 1551.82, "quirk": "discount", "discount": 67.5 }, { "id": "I07", "vendor": "Vellum Books", "vendor_vat": "FR12345678901", "vendor_address": "Lyon, 5 Rue de la R\u00e9", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1047", "issue_date": "2026-08-02", "due_date": "2026-08-16", "currency": "EUR", "lines": [ { "description": "Consulting hours", "qty": 3, "unit": "hour", "unit_price": 85, "amount": 255 }, { "description": "Cloud storage 1 TB", "qty": 1, "unit": "month", "unit_price": 9.9, "amount": 9.9 }, { "description": "Photography half day", "qty": 3, "unit": "day", "unit_price": 450, "amount": 1350 } ], "net": 1614.9, "vat_rate": 0.2, "vat_amount": 322.98, "total": 1937.88, "quirk": "" }, { "id": "I08", "vendor": "Orbit Fitness", "vendor_vat": "ES A12345678", "vendor_address": "Valencia, Calle Col\u00f3n 9", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1050", "issue_date": "2026-08-27", "due_date": "2026-09-26", "currency": "EUR", "lines": [ { "description": "Copywriting", "qty": 1, "unit": "page", "unit_price": 60, "amount": 60 } ], "net": 57.0, "vat_rate": 0.21, "vat_amount": 11.97, "total": 68.97, "quirk": "discount", "discount": 3.0 }, { "id": "I09", "vendor": "Lumen Photography", "vendor_vat": "BG201122334", "vendor_address": "Sofia, 44 Oborishte St", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1062", "issue_date": "2026-08-17", "due_date": null, "currency": "EUR", "lines": [ { "description": "Print run 500 flyers", "qty": 1, "unit": "lot", "unit_price": 240, "amount": 240 } ], "net": 240, "vat_rate": 0.21, "vat_amount": 50.4, "total": 290.4, "quirk": "no_due_date" }, { "id": "I10", "vendor": "Tidewater Yoga", "vendor_vat": "PT501234567", "vendor_address": "Porto, Rua das Flores 18", "customer": "Lezzwork (test buyer), Sofia", "invoice_number": "INV-2026-1067", "issue_date": "2026-08-13", "due_date": "2026-08-27", "currency": "EUR", "lines": [ { "description": "Hosting plan", "qty": 8, "unit": "month", "unit_price": 29, "amount": 232 } ], "net": 220.4, "vat_rate": 0.2, "vat_amount": 44.08, "total": 264.48, "quirk": "discount", "discount": 11.6 } ] }