![]() ![]() So if you wanted to enforce specific JSON key values, then you could specify that in the prompt & probably give an example of the JSON structure you want it to output. "description": "KIT COBAS HBV/HCV/HIV-1 CONTROL CE-IVD",Īnd remember you can always adjust the prompt to extract the different data you want on different documents & adjust how you want the data to be represented in the output. "description": "KIT COBAS LYS REAGENT IVD", Agency, Plot 1075 Diplomatic Drive, ABUJA NIGERIA, NIGERIA", "consignee_or_ship_to_entity": "Dr The Mission Director, U.S. That is then fed into this GPT action prompt. Then the Convert to txt loop produces this output shown in the final Compose.Īnd if we copy that output over to a text (txt) notebook, then this is what it looks like. The AI Builder action uses optical character recognition (OCR) on this invoice PDF to return each piece of text & its associated x, y coordinates. The Convert to txt loop goes through each vertical line in the PDF or image & creates a line of text to approximately match both the text & spacing between text for that line.Įach vertical line of text is then combined into a single block of text like a big txt file in the final Compose action, before it is then passed to GPT through the AI Builder Create text action. The AI Builder Recognize text action returns a JSON array of each piece of text found in the PDF or image. It also runs in less than a minute, so it can respond in time for a Power Apps call. And you can always adjust the prompt to extract the different data you want on different documents & adjust how you want the data to be represented in the output. It may be good enough to do more direct data entry on some use-cases with well formatted, clean PDFs, and in many other cases it may be best at doing a 1st pass on a file & providing a default / pre-fill value for fields before a person then checks & completes something with the data.īut it does not require training on different formats, styles, wording, etc. Seems to have a 80% or greater reliability for returning requested data fields from most PDFs. This template uses AI Builder's OCR for PDFs & Images to extract the text present in a file, replicates the file in a text (txt) format, then passes it off to a GPT prompt action for things like data extraction. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |