Extract information from an uploaded image (such as a photo) or a file (PDF), and save it to rows in an existing table using AI by adding the Extract rows AI task in an automation. This is a preview release of this feature. See Use the Extract rows AI task in an automation.
Bug fixes
None
Rollout changes
None
Preview announcements
Preview feature releases enable you to try out new app features that are not yet fully supported. See Product launch stages.
No new preview features were released today.
In addition, the AppSheet preview program lets app creators try out new app features that are not yet fully supported. For more details and to opt-in, see AppSheet preview program.
This has been a great news lots of community members should have been waiting for.
After a quick test, I found there is a glitch with this new task.
The use case is extract data out of invoice (typical use case).
Setting #1
I placed a first task (Extract) to get the total amount + tax amount followed by 2nd step of Extract Rows to get the set of details such as amount and product names. This works fine.
Setting #2
Just swap the steps around, the extract rows comes first followed by Extract task.
For the setting #2, the first step of extract rows works, but the second step of Extract does not be triggered (or ignored).
Please kindly have a look into it, as it seems a glitch.
Any plans to make the recent AI features more widely available to the developers who do not have AppSheet Enterprise Plus accounts? I have a use case for PDF table extraction I’m working on today for which I am considering AppScript AI or a custom Python solution (probably the latter) but I would have happily invested time in AppSheet AI-driven row extraction if I were able to access it.
Hi @Matt_Apptif
At this point in time, we are not working towards offering this outside of AppSheet Enterprise Plus accounts. So, it won’t be available to AppSheet Core, at least in the near future.