Unanswered

"Convert newly added PDF files to Microsoft Excel in SharePoint" is unstable conversion

(0) Share

Report

Posted on by Geezer

I spoke with Adobe Support about this issue several months ago. This conversion flow is still inaccurate. Case in point: left-most item can be 1-5 lines. For multiple lines items, all lines but the first are attributes, preceded by a bullet point character. In some cases, this is converted to a single cell with multiple lines of text. In other cases, this is converted to multiple rows.

This inconsistency was discussed with Adobe, and persists as of this date. The Connector is not to be trusted.

Categories:

Using connectors

I have the same question (0)

All responses (4)

Answers (0)

Sort by

eric-cheng 5,171 on at

Like
a
(0)

Report
Copy link

Link copied!

Hi @Geezer ,

I haven't used the Adobe connector but depending on the structure of your PDF, perhaps you can give AI builder a go. You should be able to deploy a custom form processing model and extract out tabular data or key value pairs and then write that out to Excel.

Please have a look here and here.

--------------------------------------------------------------------------
If I have answered your question, please mark my post as a solution
If you have found my response helpful, please give it a thumbs up

Was this reply helpful? Yes No
Geezer 68 on at

Like
a
(0)

Report
Copy link

Link copied!

I sidestepped this topic by exporting the data from our web site in a CSV file, opening it directly in Excel and writing an Excelscript which will eventually tie back into Power Automate Flows.

The PDF / Adobe connector remains a weak and inconsistent solution to this topic.

Was this reply helpful? Yes No
Geezer 68 on at

Like
a
(0)

Report
Copy link

Link copied!

I took your advice and looked into AI Builder. First impression was, it took upwards of 12 documents to Train the Model for a simple order form. Seems a bit ridiculous. Once I got a solution that looked like it was going to work, I looked into the cost. $500-$1,000/month. Non-Starter.

We are a small company with 3 employees. We desperately need some processes defined--automated would be very helpful. Costs like this mean anything to do with AI Builder is off the table. And it makes me extremely leery going forward of things like Power BI, Dataverse, Bots....

I guess it's back to Power Automate and Excelscript.

Was this reply helpful? Yes No
takolota1 4,980 Moderator on at

Like
a
(0)

Report
Copy link

Link copied!

So I built this template that processes any document just using the less expensive image recognition AI Builder service & GPT.

It seems much less expensive with a much lower barrier to entry only requiring a premium Power Automate license with 5000 AI Builder credits per month & some on-going LLM / GPT costs…

https://powerusers.microsoft.com/t5/Power-Automate-Cookbook/Extract-Data-From-PDFs-and-Images-With-GPT/td-p/2201345/page/4

If I’m looking at this right, this method should cost

Image recognition +.0017

GPT prompt & output +.007

Flow actions +.00375

So about $ .013 per page.

Less expensive than any of the other microsoft document/receipt/invoice processing options. And several of those take about 30 seconds to run.
And the 5000 AI Builder credits that come with the now $15 premium Power Automate license is enough for 1500 Image recognition pages. So you could probably process 500-750 documents per month with just 1 premium Power Automate license.

So it seems this method is faster, less expensive, easier to adjust, & requires less set-up than other standard AI builder set-ups.

Once the GPT actions are in general availability, I don’t know why I’d use any of the other services. 🤷‍

Was this reply helpful? Yes No