PDF to Text: Unable to extract text content in PDF (Chinese language)

Question

I'm using Alteryx Intelligence Suite version 2025.2, for some Chinese Electronic VAT Invoice, use PDF to Text: Unable to extract text content in PDF (Chinese language), all the VAT number, seller's name, buyer's name, and detail is blank.

Seems this is known issue for long time, when will Alteryx fix the problem?

Below is the screen of Alteryx preview.

The original PDF is as below:

AlteryxMatt · Answer

Hi @TTMCarrieCai!

You can find more information about the PDF to text tool, and it's limitations here: https://help.alteryx.com/current/en/designer/tools/alteryx-intelligence-suite/computer-vision/pdf-to-text.html#pdf-to-text

You could also submit this as a future enhancement in the Ideas forum here.

Alternatively, the new GenAI Tools, as part of 25.2, will leverage LLMs to do this with a higher degree of accuracy across more languages.