Unable to extract text from PDF Base64

I need to extract text from PDF which is coming in as an attachment in an email. So, I am posting it as a base64Image. But getting following error:
Not a valid base64 image. The accepted base64 image format is 'data:image/<content_type>;base64,<base64_image_content>

Is there a way we can extract text from pdf(base64)?

Your question has a good timing: Base64 support for PDFs will be available very soon - probably already tomorrow. I will update my answer once we released the feature.

Thanks for your reply. Do we know exactly when will this feature will be available?


Not exactly, but sometime this week :smiley:

Will it be available for Free API key as well?

Yes. Plus we also release autorotate.

Hi, The PDF I would like to extract is basically a form. Can I ask the data extraction from PDF, is it like returning the text as a whole or will it be returned as a key:value sort of thing which can be utilised in a more useful way?