Ai_Parse_Document in Databricks | Pulling Text and Tabular Data from PDFs

So good, can't wait for the next lesson! I hope it's out before my interview 😂😂

This is very useful! I use it to parse different advertising invoices and extract the required data (invoice number, currency, account ID, line items, amounts, etc.), which saves the team hours of manual work every month. They now just run the notebook and make minimal adjustments. Every invoice turned out to be messier than the last, but Databricks Assistant was a big help in figuring out how to handle some of those cases.😀👍

Great video enjoyed it

Thanks for this

Thanks 👍🏻

What about security issues, how can I parse CONFIDENTIAL or PERSONAL docs?

Really appreciate this lesson. Perhaps I missed it in a previous video, but at 1:59 Alex uses the default storage, and it's already checked in his video. But when I try to follow along, I get an error message: "Metastore storage root URL does not exist. Default Storage is enabled in your account. You can use the UI to create a new catalog using Default Storage, or please provide a storage location for the catalog (for example 'CREATE CATALOG myCatalog MANAGED LOCATION '<location-path>')." I dug around on the website to see if I could come up with an answer and tried a whole bunch of things without any success short of setting up storage on an external location. Does anyone know what I'm doing wrong?

Can you do more videos about SAS

ChatGPT and Gemini, etc. can do this in a few min. to be html, excel.. format, too.

Hi Alex! Great video! However, I have a issuse when I run the code at 5:00. The error message I have is: [DBFS_DISABLED] Public DBFS root is disabled. Access is denied on path: /Volume/idp/default/youtube_lesson/_delta_log SQLSTATE: 56038 JVM stacktrace: com.databricks.backend.daemon.data.client.DbfsUnsupportedOperationSparkException Looks like there are something wrong with permissions.