Unanswered

Getting Data from PDF. That will store in SharePoint

(0) Share

Report

Posted on by Ayush Solanki

The scenario is: The PDF file is store in SharePoint. From their we need to get their data. we are able to get half PDF data and rest of the PDF data we can't able to get . for getting the data I takes this connector

we get data in this format

Categories:

Using flows

I have the same question (0)

All responses (2)

Answers (0)

AndreasN 318 Super User 2024 Season 1 on at

Like (0)

Report

Is it just one PDF? Is the data in a table in the PDF? Is it multiple PDFs?

If it is just one PDF, and the data is in a table, use the "extract table from PDF" in Power Automate Desktop.

If it's multiple PDFs and they share the same layout, create an AI builder and tag the required data and assign the data columns.

Was this reply helpful? Yes No
takolota1 4,974 Moderator on at

Like (0)

Report

If anyone wants to extract data from a PDF or image without training a model for select documents, try this new GPT data extraction method: https://powerusers.microsoft.com/t5/Power-Automate-Cookbook/Extract-Data-From-PDFs-and-Images-With-GPT/td-p/2201345

It doesn’t require specifying certain document areas, wordings, styles, etc. It just OCRs the file, converts it to a replica text (txt), and passes it to a GPT prompt where you can ask GPT to do whatever you want with the document data.

Was this reply helpful? Yes No