Xtract OCR
Xtract OCR extracts the text of images and PDF attachments in a conversation and produces layout-preserving text outputs. It can read handwritten text and supports more than 30 languages.
How to Configure OCR Extractors in UpBrains Plugin?
To configure OCR (Optical Character Recognition) for PDFs and Images in UpBrains Plugin, you need to follow these steps:
- Go to Settings > Document Skills > Extractors
- Click on Add Extractor
- Input Extractor Name
- From the Service dropdown, choose Xtract OCR
- Select your desired Model from the Model dropdown
- (Optional) Page Range: Select pages(range) for processing attachments, if you desire only specific pages to be Xtract.
- (Optional) OCR Character Limit: Limit the number of characters in OCR Output
- Click on Save to finish your changes on Xtract OCR
Last updated on