Skip to main content
can parse the file types listed in the table below. Support depends on the method you use: Playground, API, or ade-python library.
File TypePlaygroundAPI/Library
PDF
PDF✓
(up to 100 pages)		✓
(see Rate Limits)
Images
JPEG✓✓
JPG✓✓
PNG✓✓
APNG×✓
BMP×✓
DCX×✓
DDS×✓
DIB×✓
GD×✓
GIF×✓
ICNS×✓
JP2 (JP2000)×✓
PCX×✓
PPM×✓
PSD×✓
TGA×✓
TIFF×✓
WEBP×✓
Text Documents
(see notes here)
DOC (Word)✓✓
DOCX (Word)✓✓
ODT (OpenDocument Text)✓✓
Presentations
(see notes here)
ODP (OpenDocument Presentation)✓✓
PPT (PowerPoint)✓✓
PPTX (PowerPoint)✓✓
Spreadsheets
(see notes here)
CSV (comma-separated values)✓
(up to 10 MB)		✓
XLSX (Microsoft Excel)✓
(up to 10 MB)		✓

​
Password-Protected PDFs

doesn’t support parsing password-protected PDFs. If you attempt to parse a password-protected PDF, the API responds with a 422 error (unprocessable content): 
HTTP-422: Failed to split PDF into pages. Ensure it is a valid PDF file. document closed or encrypted

​
Text Documents and Presentations: File Conversion

converts text documents and presentations to PDFs before parsing them. This conversion may change the document layout and increase or decrease the number of pages. For example, unsupported fonts may be replaced with larger alternatives, causing text to wrap differently or overflow onto additional pages. While the conversion process may impact the layout, still parses content correctly.

​
Spreadsheet Considerations

There is no maximum for the number of sheets, columns, or rows in a spreadsheet file. When you load a spreadsheet in the Playground, a render limit applies and only a truncated version of the spreadsheet is displayed. This does not affect the parsing results.

​
Load Bytes

If using the agentic-doc library, you can also load PDF bytes and image bytes. For more information, go to Sample Script: Parse Files from Bytes.