Preprocessors
Use the following preprocessors to clean up your documents before extracting structured data. Preprocessors execute in the order you define them in an array.
Preprocessor | Image | Notes |
---|---|---|
Deskew | Corrects the alignment of documents that are skewed, for example as a result of being photographed at an angle instead of straight on. | |
Ligature | Intelligently replaces Unicode ligatures in a text extraction. | |
Merge Lines | Corrects oversplit lines. | |
NLP | Advanced prompt configuration for each large language model (LLM)-based method in a config. | |
OCR | Selectively OCRs pages in documents containing a mix of digitally generated text and text images (such as scanned text). If the whole PDF is a scan, you don't need to configure this preprocessor. | |
Page Range | Ignores pages outside the start page and end page. | |
Remove Header | Removes repeating elements at the top of the page. Ignores header elements that overlap with the page's main body. | |
Remove Footer | Removes repeating elements at the bottom of the page. Ignores footer elements that overlap with the page's main body. | |
Remove Page | Removes pages that match the specified text. | |
Rotate page | In most cases, Sensible corrects page rotation automatically. If it doesn't, configure this preprocessor. | |
Scale | Corrects the size of text in documents whose size varies, for example as a result of being scanned or photographed at different scales. | |
Split Lines | Corrects undersplit lines. |
Updated 1 day ago