Image to text, extract specific data in order to insert into columns

[Rimatcom]

Hello community, I hope everyone is well during these special dates.
I am looking to implement the following functionality and I need some guidance on the best method to use. If you have experience with this, I would appreciate your insights.

I need the user to take a photograph of a bank transfer receipt, and once they upload the photo to the app, extract CERTAIN specific data such as the amount, the name of the person who made the transfer, and the date, among other details.

I am planning to use the A.I. image-to-text function to extract text, but I’m unsure how to extract specific data like the amount, name, and date. Once I have this data, the goal is to insert it into specific columns for that information. The idea behind this functionality is to automate data entry for the user by simply taking a photo.

Any help is welcome, thank you.

[Jeff_Hager]

PDF → Glide AI → Query JSON is MAGIC

Hey Fellow Gliders! Glide AI is crazy powerful. With “Document to Text”, you can extract the text from any document in seconds… If that’s not magical enough, you can use AI to format that text as JSON with any structure you define. Then, parse that JSON using Query JSON column to precisely predict and extract the values from the original PDF with almost 100% reliability. The tutorial below showcases two scenarios: Resume PDF → Document to Text → Format as JSON → Extract values and det…

[ThinhDinh]

The Smartest AI Expense Tracker no-code app ever built!

We had somewhat of the same setup here. I used Google Cloud & GlideAI to transcribe the image’s text into a JSON form I pre-defined, then query the JSON to get the fields I need.

With the availability of OpenAI’s vision model, I think it should be easier to do that now.