Supported Input Formats
Input is divided into two groups: files from which data is read by the model, and files that already contain structured data.
Read by the Model
| Format | Note |
|---|---|
| Digital and scanned, up to 20 pages | |
| JPG, PNG | Photos from a mobile phone, output from a scanner |
| GIF, WebP, BMP | Will be automatically re-encoded |
| Word, Excel, PowerPoint | Text from the document and embedded photos |
E-mail .eml | Envelope: a document will be created from each attachment, up to ten from one message |
| Archive ZIP, RAR, 7z, TAR, TAR.GZ | Envelope: a document will be created from each file inside, up to fifty, all labeled according to the archive name |
Recognition and the model run for these formats. The result is an estimate, although accurate, and therefore a check is performed. TIFF is not supported; convert it to PDF or PNG.
Structured
| Format | Note |
|---|---|
| ISDOC, ISDOCX | Czech electronic invoicing standard, versions 5.x and 6.x |
| UBL 2.1 | Peppol BIS, XRechnung |
| CII D16B | ZUGFeRD, Factur-X, including PDF with embedded XML |
| Pohoda XML | Batch from Pohoda, up to 50 documents in one file |
Here, nothing is disputed, data is loaded directly and the document incurs no credit. In the listing, it has the electronic invoice icon. Checks run similarly, as a structured document can also have a mismatched total or invalid DIČ; the finding then states that the error is with the issuer.
In ISDOCX, the archive opens, the invoice is read, and the attached PDF is saved as the original, so the preview shows the invoice and not the XML. A Pohoda batch with multiple documents creates as many documents as there are in it; they are distinguished in the listing by the order in the name.
What is Not Supported
TIFF, HTML pages, password-protected archives. A ZIP with a single invoice and its PDF is ISDOCX and will be processed as an electronic invoice; a ZIP with multiple invoices is a batch and will be unpacked into separate files.