- I have a lease contract that is around 10 pages long in PDF and have a metadata extract template to show 10 fields (execution date, lease squared footage, etc.).
- So the extracted data is coming from multiple pages (few fields are coming from page 1 and some fields are coming from Page 3, 5 and 10)
- What I am doing?
I am using Box AI to extract the data out. So all works well, but I am unable to see the what exact text has been extracted from what page.
What is missing - I need your help here?
- Ideally I would like the data in the PDF document highlighted either in yellow or boxed around in some way, so it is easy to review. Somewhat of a citation to the value i see that is extracted.
- On a related question -- once I review the extracted data, is there a way to lock the extracted data once I approve everything is OK.
Think of a scenario that there are 10 contracts, and for 6 contracts I have reviewed and all and it looks good or I can update it to fix any metadata extract errors to make it OK. Now, I want to lock this extracted metadata, so no junior person or my AI agent can change it as I have already reviewed this. How can I achieve this?
- To continue to the above example, how can I pull the metadata from all the reviewed contracts in an excel file. So as I have reviewed 6 contracts, I would like to have an excel file with 6 rows of data.
Thanks!
