Supported Formats
| File Type | Playground | API |
|---|---|---|
| Images | ||
| JPEG | ||
| JPG | ||
| PNG | ||
| APNG | ||
| BMP | ||
| DCX | ||
| DDS | ||
| GIF | ||
| ICNS | ||
| JP2 (JPEG 2000) | ||
| J2K (JPEG 2000) | ||
| PBM | ||
| PCX | ||
| PGM | ||
| PPM | ||
| PSD | ||
| TGA | ||
| TIF | ||
| TIFF | ||
| WEBP | ||
| Text Documents (see notes here) | ||
| DOC (Word) | ||
| DOCX (Word) | ||
| ODT (OpenDocument Text) | ||
| RTF (Rich Text Format) | ||
| Presentations (see notes here) | ||
| PPT (PowerPoint) | ||
| PPTX (PowerPoint) | ||
| Spreadsheets | ||
| CSV (comma-separated values) | (up to 50 MB) | |
| XLSX (Excel) | (up to 50 MB) |
The Playground does not yet accept DOC, PPT, CSV, or XLSX files when a DPT-3 model is selected. Use the API for those formats. Playground support follows in an upcoming release.
How Files Are Handled
- PDFs are processed one page at a time, so each page is parsed independently.
- Images are treated as a single page.
- Text documents and presentations are converted to PDF before parsing, then processed one page at a time.
- Spreadsheets are parsed directly. They are not converted to PDF.
Unsupported Formats
The API does not accept these file types:- HTML
- GD
- DIB files without a BMP header. A
.dibfile that is a BMP (starts withBM) is accepted. - ODS (OpenDocument Spreadsheet) and ODP (OpenDocument Presentation)
- XLS (legacy binary Excel)
.csv, .tga, .doc, or .ppt).