This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
I have trained a custom splitter via the google cloud console. It works great. However I'd like to also extract the text from the PDFs I am sending to the splitter. I am using batchProcessDocuments with Node.js and everything works fine. I eventually receive a Document with pages and entities like your docs: https://cloud.google.com/document-ai/docs/splitters However I do not get Document.blocks or page.paragraphs. I'd like to get the bounding box of every word of line in the document, like your example shows -> https://storage.googleapis.com/cloud-samples-data/documentai/SampleDocuments/CUSTOM_SPLITTING_PROCES...
however I do not get this result when calling batchprocessdocument. Do I need to specify that I want this data in my request?
LinkedIn
Twitter
