Extract tabular Data from PDF using AI Builder Form Processing in Power apps

Join this channel to get access to perks:

This video explains the below points on Dynamics 365 Customer Engagement CRM: Extract tabular Data from PDF using AI Builder Form Processing in Power apps

[ganeshshevate]

I have implemented this successfully, Thank you Sanjay Sir,

[tariqhameed]

Really a great video. I am looking the solution for my work and your video help me to resolve my solution. Thanks a lot.

[wachhagottoday]

Great video Sanjay Prakash. Loved how form Processor can be used in Canvas Apps. There was just one thing I wanted to check. How to take Invoice Date value from the Form and put it on the Canvas app where it talks to a field from an OOB table such as Invoice OOB dynamics field. Hope it makes sense.

[johng]

Thanks in a million. Great content. Awesome. Very well explained. I couldn't find this explanation--simply put anywhere else. Great teachers are hard to find. Grade: A++💥

[delmonte]

Thanks Sanjay it works perfectly well!
Is it possible to pick multiple files from sharepoint folder instead of choosing single file?

[rafiurrahman]

Thank you so much. It is a great help for me to finish one of my projects. I had another question if I want to upload multiple PDF files together in a shared folder. How can I trigger that?

[atanutech]

Thank you sanjay for valuable learning.

[SandroMochiaro]

Congratulations on the video. How can I select multiple invoices at once?

[rameshbabuc]

Thanks Sanjay Sir, One quick question - Is it possible to read table rows content continuing from Page 1 to page 2. My use case is below
I need to extract information in tabular format from order confirmation pdfs received. Each pdf has multiple items and each item will have a Name, description, Vendor and delivery date.
So the table will have four columns: Name, description, Vendor, Delivery Date with each row representing an item.

The problem arises when some details for an item are present at the bottom of one page and the remaining details are on the next page. Example : Description in the table continuing in the page 2 from page 1 bottom, So unable to tag these rows which is continuing from page 1 to page 2.



For example: if this is the pdf




code: 1

description: this is first item

Vendor: XYZ1

delivery date: 12.01.2024



code: 102

description: this is second item

Vendor: XYZ2

delivery date: 13.01.2024



code: 103

description: this is third item



1 ends





2 begins

description(Continuing from Page): this is third item Continuing

Vendor: XYZ3

delivery date: 14.01.2024



code: 104

description: this is fourth item

Vendor: XYZ4

delivery date: 15.01.2024



code: 105

description: this is fifth item

Vendor: XYZ5

delivery date: 16.01.2024



text

2







The document cannot be tagged correctly using custom model when page 1 content - Description is continuing on Page 2 . For the above document, the tagged tables look like this

Code Description Vendor Delivery Date
101 this is first item XYZ1 11.01.2024
102 this is second item XYZ2 12.01.2024
103 this is third item XYZ3 13.01.2024


Date
Some text are
continuing
from page 1
104 this is fourth item XYZ4 14.01.2024
105 this is fifth item XYZ5 15.01.2024

[tejaspatel]

Very insightful video, I had a quick question:

I made an AI model that extracts information from a pdf. I am using this model in a Power Automate (cloud) flow to extract information from the pdf and write into an Excel file on OneDrive.

Everytime I make changes to the flow and test it I end up consuming a lot of AI builder credits (due to multiple test runs).

Is there a way for me to use fewer credits while I am in dev phase where I am testing and finalizing the flow?

Has anyone tried using “static results” for the steps in Power automate flow and does this help reduce the AI builder credit useage?

[ConfidencePoint]

Great video. But what if I have 1000 rows in my pdf? Not possible to tag every row. Please suggest a solution

[Smddlvvs]

@softchieflearn How do i give multiple files as input or root directory as input and get a single output file

[lnpg]

Excellent video. How can I extract a table that span in more that 2 pages?

[mufycw]

HI,
Thank you for helping on this. Can you name the video in which you have shown how to extract data from fields, in this video you said that you have already shown in other video..i cant find it

[vivekcaptain]

Hi need extract fields and table from Invoice pdf to Excel.
Fields - Invoice No, Order No, Invoice Date and Customer Po No .
Table which contains point_down
Column 1 - Part No
Column 2- Goods Description
Column 3- Lot No
Column 4- Qty
Column 5- Amount.
Had created a Model and used in power automate where field data extracted but unable to extract the table data ...

[SKEDURINRAJA]

Very useful.. but very expensive after trial period.. I m a 365 user..

[vivekcaptain]

Hi Sanjay excellent video for the beginners myself need extract fields and table from Invoice pdf to Excel.
Fields - Invoice No, Order No, Invoice Date and Customer Po No .
Table which contains point_down
Column 1 - Part No
Column 2- Goods Description
Column 3- Lot No
Column 4- Qty
Column 5- Amount.
Had created a Model and used in power automate where field data extracted but unable to extract the table data ...

[АлександрЛукашев-ей]

Hello, the manual way is working, but I can't to apply the way from inbox in outlook and I can't find ways out.

[Atmesh]

How to do tagging in pivot data in the pdf

[sandilembatha]

How can I do it for different invoices from different suppliers?