Extract Data from Document with in Seconds

RE: Extract Data from Document with in Seconds

Teja Kunchala — Wed, 06 Mar 2024 12:12:15 GMT

Hi Vinay,

I think there is no chance for us to provide particular timing to the AI skill to extract the data.
I observed some scenarios like
When you retest the document which is already extracted once, It will take less time to extract the data.
For a new document based on the data in document the time may varies
I think more advancements to be expected in AI skill in up coming releases regarding this.

Thank you

RE: Extract Data from Document with in Seconds

anshikag8127 — Mon, 04 Mar 2024 12:32:54 GMT

Hi Vinay,

AI Skill Extract Data from Documents (IDP) usually takes a lot of time to extract, no matter how many times you train it. I would suggest you to use "AWS Textract" integration to extract text from doc's, It takes less than a min. Only thing that you need to take care of document size limit since AWS textract doesn't take more than 5 MB. So before sending document to AWS textract integration, use "split pdf by number" smart service and send one by one using MNI to AWS Tectract.

RE: Extract Data from Document with in Seconds

JUMMIDI VINAY — Fri, 01 Mar 2024 13:22:05 GMT

Okay Thank you Stefan

RE: Extract Data from Document with in Seconds

Stefan Helzle — Fri, 01 Mar 2024 13:20:50 GMT

I understand.

AFAIK there is nothing you can configure or change to make this go faster. I suggest to contact Appian to discuss this use case.

RE: Extract Data from Document with in Seconds

JUMMIDI VINAY — Fri, 01 Mar 2024 13:18:11 GMT

Actually we had a Requirement When the User Uploaded their Driving License with in few seconds in the next , we need to extract and show them in interface.

ok leave about the timing , but can we reduce the extraction in any chance, is there any way to do so that the extraction time can be reduced ?

RE: Extract Data from Document with in Seconds

Stefan Helzle — Fri, 01 Mar 2024 13:13:09 GMT

Where is this strict timing coming from? I mean, typically, in a mostly automated process, people are not waiting for such things.