Test files › RAG test corpus › price-list.xlsx
Sample XLSX file (price list)
A price list with a two-row header: "Price (EUR)" merged over "Net" and "Gross incl. 19% VAT".
↓ Download price-list.xlsx| Filename | price-list.xlsx |
| Format | XLSX |
| Size | 1.8 KB (1,854 bytes) |
| MIME type | application/vnd.openxmlformats-officedocument.spreadsheetml.sheet |
| SHA-256 | a731809af39849d2cf008dfc9fc55ce7b4b6871323ebc855b1785c6aad507919 |
What this file catchesLoaders that take row 1 as the header (pandas read_excel default) name the gross column "Unnamed: 2" and read the sub-header row as data, so a question about the gross price often returns the net one.
Download & verify
curl -fsSL -o "price-list.xlsx" "https://files.hexaqa.com/rag/corpus/price-list.xlsx"
curl -fsSL "https://files.hexaqa.com/rag/corpus/price-list.xlsx" | sha256sum
# expect: a731809af39849d2cf008dfc9fc55ce7b4b6871323ebc855b1785c6aad507919