Supported file types

File types

Sensible supports the following file types:

	PDF	Microsoft Word (DOC and DOCX)	Spreadsheet formats¹ (XLSX, XLS, and CSV)	single-page image formats¹ (JPEG, PNG)	multi-page image formats¹ (TIFF)
Context
Sensible app's Extract tab	✅	✅	✅	❌	❌
Single-file extraction with SDKs or API	✅	✅	✅	✅	✅
Portfolio extraction with SDKs or API	✅	✅	❌	❌	❌
Classification by type with SDKs or API	✅	✅	✅	✅	✅

Extraction method
Methods that require rendering non-text image pixels²	✅	✅	❌	✅	❌
NLP Table method, Fixed Table method³	✅	✅	❌	✅	❌
Extraction of text that requires OCR	✅	✅	❌	✅	✅

All OCR settings are inapplicable for Microsoft Excel and CSV.
Methods that require rendering an image include pixel-based methods, such as Box, Checkbox, Nearest Checkbox, and Signature methods, multimodal LLM-based methods, and image coordinates returned by the Document Range method.
As alternatives to these Table methods, use the Fixed Table method or the List method.

Sensible supports the following file sizes:

Operation	Size limit for `/extract/{doc-type}` API endpoint	Size limit for asynchronous calls
Single-document file extraction	under 4.5MB, or under 30 seconds processing time	6 GB
Portfolio extraction	n/a	6 GB
Classification	4.5 MB	4.5 MB

For DOC and DOCX documents, Sensible converts the document to PDF before processing it.
For spreadsheet documents (XLSX, XLS, and CSV), Sensible extracts text directly from the file without OCR. Sensible represents the text both internally and in the Sensible app's editor as follows:
- Standardizes the formatting of all text in the file. Each cell contains exactly one line.
- Standardizes cell height at 0.25'' tall and cell width at 1''. Overflow text in a cell is still available for extraction but isn't viewable in the Sensible app editor unless you click on a line in the rendered document to view its details.
- Standardizes the maximum page height at 15 inches. Sensible splits longer sheets into consecutive pages.

Updated about 14 hours ago