Skip to main content
Z
zalmasi
Participant
August 11, 2023
Answered

Where does the extraction/parsing occur? Local or Cloud?

  • August 11, 2023
  • 1 reply
  • 455 views

Hi. I would like to try the PDF extraction API. My issue is ITAR rated/classified documents.

Question 1: Does the extraction takes place on Adobe Cloud , which (to my knowledge) would violate ITAR,

or is the extraction happening locally through the SDK?

 

I'd love to see if Adobe PDF Extractor performs better than  batch Importing pdfs into MS Word, which happens locally.

For me, performace is better extraction of complex tables and text

 

Question 2: Does the desktop local version of Adobe Acrobat Pro use the same Sensei technology?

 

Many thanks in advance

    This topic has been closed for replies.
    Correct answer Joel Geraci

    Acrobat Pro does not export PDF to JSON. The Extract API doesn't exactly export the PDF to JSON either. It's more like a JSON representation of the PDF content without trying to be an export of it. The AI that drives Extract is part of Sensei.

    Both the Acrobat Pro version and the API version of Export to Office formats use the same converters, not Sensei.

    1 reply

    Joel Geraci
    Community Expert
    Joel GeraciCommunity Expert
    Community Expert
    August 14, 2023

    1) All of the PDF Services APIs run in the cloud.

    2) Yes and no. Sensei has a lot of parts. Some features of Acrobat Pro are enabled by the cloud, some run locally.

      Z
      zalmasiAuthor
      Participant
      August 14, 2023

      Thanks.

      Question: Is the local-only Acrobat version more-or-less as effective as the Sensei API, for exporting PDFs to JSON/Word? 

      Local only (high parameter) machine learning is normal these days. Perhaps, the local Acrobat has (functionally) the same tech.

       

       

      Joel Geraci
      Community Expert
      Joel GeraciCommunity ExpertCorrect answer
      Community Expert
      August 14, 2023

      Acrobat Pro does not export PDF to JSON. The Extract API doesn't exactly export the PDF to JSON either. It's more like a JSON representation of the PDF content without trying to be an export of it. The AI that drives Extract is part of Sensei.

      Both the Acrobat Pro version and the API version of Export to Office formats use the same converters, not Sensei.

      Terms & ConditionsAccessibility statement
      Using the community Terms of use Privacy Cookie preferences Do not sell or share my personal information ad choicesAdChoices