Unstructured Document Processing with Power Apps and AI Builder

[@johng5295]

DHRUVIN, thanks in a million. This content is second to none! Very well explained, and easy to follow. This is the nth time that I am revisiting your youtube video in full. Great content. Awesome. Very well explained. I couldn't find this explanation--simply put anywhere else. “Great teachers are hard to find”. Grade: A++

[@zaldyconde4248]

Thank you so much Dhruvin. This is a great video and this is what I'm waiting for.

[@iamdhruvinshah]

Thanks

[@arzanpatel]

Subbed mate. This type of content is incredibile. Love from Australia

[@nurizzati5657]

Hi Dhruvin, great video! one question, is there a way to save the document uploaded from the document processing ai builder into the file field in sharepoint list?

[@yuvrajjadhav1506]

Bro you great thank you so much this video very informative, after long search got this hats off

[@rajum5453]

Thanks for the video, please explain how do we deploy our model to other org in the next video of this series

[@iamdhruvinshah]

Sure.. I will try to cover it!!

[@ahiqtidar]

A great video, Dhurvin as always. Imagine a use case, where I have 100 invoices and I want to do all of them rather one by one uploading them in app. Is there a way to achieve it

[@aysanhaghani5271]

Thank you so much for this video! for the Premium connector on the app can we use a service account ( or per app license)?

[@iamdhruvinshah]

You can choose from Per User or Per App Licensing!

[@Reedcarlton]

Thank you great video I was looking for this!

[@moimeme6033]

Excellent, Dhruvin! Instead of selecting one file to be analyzed, is there any way to select multiple files in order AI Builder can analyzed them?

[@mayurimadane5036]

Great video bro

[@fanzfanzilla]

Hello Dhruvin, thank you for the video and showing how to use AI builder model with Power Apps. Is there a way to train model on unstructured text data and extract specific information from the sentence by applying NLP.

[@ritukumari1140]

Hi @Dhruvin shah does the unstructired model gives a confidence score???

[@paulplasencia5572]

Hola, muy buen video, porfa podrías compartir tus archivos no estructurados?

[@starbusttweety]

My model is taking too long to train. I have to submit my work ASAP. Is there any way to cut short the training time on my work system? My internet speed is just fine.

[@LEENAG-q2u]

Hi, Could you please let me know how much time will the unstructured document processing model takes to train once the tagging is completed ?

[@EmanuelBishere]

good stuff - thanks!

[@sugandhabaruah6564]

Hi Dhruvin, Really nice content on dealing with unstructured documents using Power App. However, I wanted to know if there's a possibility that after analyzing the PDF, once the form is filled can that form be saved and downloaded? Thanks, Sugandha

[@MoisesLopez-k9i]

Amazing content. I’m having trouble figuring out how to do my tagging I my unstructured doc. I’m a trying to track work events that are posted on a pdf document. The document has multiple events in one document for the same date. So for example. January 1 has 23 events with different locations and different employees attending with their own start time to end time. How would you do this tagging to prepare it for a flow that adds it to a sharepoint list. The process continues on a daily basis where as much as 5 documents are received with their own events and their own employees. The number of events per document are not always the same. Any given documents can fluctuate between 1 event To as much as 60 events.

[@Soulebi03]

hi Dhruvin, wanted to clear some questions if you have some time. If I use this AI builder form processor, do every user of my app need to have power apps premium license? Right now, I am the only one who has power apps premium and I would like everyone be able to use this.

[@anapaola8373]

Awesome, thanks!

[@RKTECH1021]

Hi Dhruvin Great video. I would like to capture pdf data to sql table and then push it to power bi. Do you have video for that or any link that you can provide ? That would be awesome. Thank you so much

[@rameshbabuc5981]

Thanks Dhruvin, 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 -----some text-------------------------------------------- -----some text--------------------------------------------- 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 -------page 1 ends here--------- -------page 2 begins here-------- 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 ---------some text here-------------------------------- ------------------------------page 2 ends---------------------- ------------------------------pdf ends---------------------------- 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 Code Description Vendor Delivery 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

[@arzanpatel]

Dont know if anyone answered tihs, but you can use the second tagging method Select all the rows in the first column on the first page, and tag it as "Code", then move over the second page, select those rows, and in the tag box, state continue tagging as "Code"

[@VikasKottari]

Super

[@VinayKumar-ky8wh]

Hi Reza, When an approval request comes through flow ,,, I need to give the approval responses in the Power app How do I connect the approval action to power apps?

[@VinayKumar-ky8wh]

Hi , When an approval request comes through flow ,,, I need to give the approval responses in the Power app How do I connect the approval action to power apps?

[@vanshikawaghela3420]

I would like to know where I can find the materials for this video. Please share the link with me.

[@srv158]

Hi Dhruvin, My use case is to run an AI model in Power automate flow. However the user needs to add the PDF sample file (on which AI model needs to work) in power apps. Power Automate V2 trigger where Sample File Will be uploaded from Power Apps. This Sample file will be fed in an AI extractor for extracting data. However I am getting following error. Pls help how to solve this issue. {"operationStatus":"Error","error":{"type":"Error","code":"InvalidPredictionInput","message":"The base 64 binary content is missing for input single","properties":{"BackendErrorCode":"InvalidInferenceInput","DependencyHttpStatusCode":"400"},"innerErrors":[{"scope":"Record","target":"single","code":"InvalidRecord","type":"Error","properties":{"MlIssueCode":"InvalidRecord","MlIssueTarget":"single"}}]}}

[@garimatewari2212]

I dont see the link of your github repositories

[@BedudhuriAnandReddy]

yes i need link to download .. please provide

[@andresfelipeanaconachavarr7013]

seria mejor que lo explicaras paso a paso graciass

[@12vLife]

Say we have 1000 documents with pages of data each in a folder and I want to find the most relevant document based on a users question and then answer the users question based on that one document? Is this possible with AI builder and not having to use something like Azure Cognitive Search?