How to Extract Data from PDF with Power Automate

This video tutorial shows how to use the AI Builder in Microsoft Power Automate to extract PDF data and save it to Excel. In the example, we use PDF invoices, but it could be any PDF sample type.

FOLLOW ME:

MY GEAR (Amazon affiliate):
🖥️ My monitor

💡 Lights

⌨️ Keyboard

📹 Camera

🎤 Microphone

0:00 Intro

2:44 Create a model with AI Builder
We create a model in AI Builder. Because it's structured data we use Forms Processing. We can extract both fields and tables from the PDF. Our model will also work with JPGs and PNGs. Create a collection of 5 sample PDFs. Tag the PDF documents (= tell Power Automate where our structured data is). Train, test, and publish the AI Model.

11:28 Use the AI Model in Power Automate
We'll create an automated cloud flow, where each time we receive an email with a PDF (invoice) attachment, we'll extract the data out of the PDF. Chose an Apply to Each and loop through the attachments of each email (there can be more). We save the data from the PDF to Excel Online (OneDriv) - remember to format the table in Excel as a table (important). Use the 'Extract information from forms' activity to use our created AI Model. Finalize it by using the 'Add a row into a table' that will add the data into our Excel database.

22:00 JSON Parse a PDF Table with Power Automate
Our table comes with all the entries and their info. That's a JSON structure. JSON is an efficient way of transferring data and it's very easy to make it pretty, so we can use/store the data. We'll write a simple function.

[tracy_dtc]

FANTASTIC VIDEO! Extremely clear, yet fast and wasting no time. I am so happy I found this. Looking forward to your upcoming unstructured data AI video. Thumbs up 👍 and Thank You!!!

[Prasanna]

You have the best Video on this Topic, even Microsoft would envy this !

[totemimaging]

Thank you so much for this tutorial. I've been meaning to start using AI models in Power Automate and this has just given me the kickstart I needed to implement it on a small test project I was discussing with a colleague this week 🙂 Kudos and looking forward to more of your content!!

[jaredt.]

Amazing to watch the excel online file populate in real time! Thank you so much for this tutorial, you just opened a whole new world of possibilities for me!

[notinvolver]

Amazing content Anders, I've found you about a year ago now and your videos are hands down best in class. Keep it up 👍🏻

[hostile_technics]

You are my favorite content creator for this subject matter. Please continue to be great

[mtzmty]

Not sure yet how I missed this video before. This is really great stuff. Thank you Anders for sharing and please keep it coming

[chrisbare]

Great stuff! That's what I'm looking for! Gonna get started next week. My final goal is to extract data from a pdf and input in a SharePoint list. Long road ahead! Thanks for doing what you do! Awesome!

[gregNFL]

Nicely done. This will help flatten the learning curve. Thank you!

[hengmakara]

This is a fantastic video. finally I found it. Thank you Anders for this sharing.

[stevenmicah]

This is the best tutorial! My whole office now essentially runs off of this! Thank you so much!!

[agraharafamily]

Great resource. Thank you Anders for sharing this.

[Pcontracts]

This is MAGNIFICENT! can't wait to try it on our buisness case.

[thedon]

Mange tak for denne video ! Det hjælper rigtig meget!
Thanks for this video, it help me a lot!!

[prasaddumbre]

Great Post, looking forward to more such videos. Thank you :)

[TrassBI]

Thanks for sharing! Very helpful video🙂

[MindsetExcellence]

Great video! Before using Power Automate I tried using Zapier and although I got it to work, it was very SLOW to populate Excel. Even though your video is from 2 years ago, it was still helpful in many ways. Currently, Microsoft has changed a few things in Power Automate but they're all good improvements. For instance, my flow was able to output my table values automatically without having to perform your last step with JSON viewer/custom expressions. My next step is figuring out how to get the all table values on a single row in Excel (in separate columns) vs having separate Excel rows for each row of table data from PDF form.

In case anyone is wondering...my flow is DocuSign PowerForm > Email (i.e. extract data from DcouSign Attachment) > Excel

[AshutoshKumar-tklm]

thank you for video, Its really helpful to learn AI builder in PA 🙂

[ridingnorthernlights]

Anders, this is a most excellent video! Thank you for putting it together. I'm going to give it a try myself. The Payables staff will love me... ;-)

[akashyap]

Great tutorial, thanks a lot :)
Had a small query -
Can we interact with the model through APIs so that we can send a pdf document over a REST API and get the output of the model through the response. Even if we can trigger the model and save the response at a predefined place, would be really useful