Welcome to the new Box Support website. Check out all the details here on what’s changed.

Box Status

Extract text in file to use in Skill APP

Follow
New post
Box Product Support

I'm trying out the new skill app model, it sounds promising, however I was checking if box can help extracting text in a PDF or Doc file? Do I have to download the file in my server/function read it and use a specific tool to extract text inside it or is there any API/SDK in box that give this already?

 

It will be great if text in files is sent in anyway to my skill app url so I can just focus on analyzing text and updating metadata instead of reading/parsing the file first.

 

Thanks 

0

Comments

1 comment

Date Votes
  • jcleblanc

    Hi ,

     

    When you're pulling the file from Box to send on to the ML / AI provider you are essentially downloading the file, so it'll be in whatever format the originating file is using (e.g. PDF / doc). Depending on the format you can either read the content directly, and potentially drop any formatting / config data that the formatted file needs, or you can use an extension / package in your respective language to read that file format. That will allow you to extract the data directly.

     

    Thanks,

    Jon

    0
    Comment actions Permalink

Please sign in to leave a comment.