Skip to main content
P
pavanik708440
August 7, 2025
Solved

AI Skill Extraction

  • August 7, 2025
  • 4 replies
  • 0 views

Hi,

I'm trying to Extract data from PDF and store those data in Database. I gave 8 fields in the extraction. I'm able to see all my fields in the ai skill extraction but in the Database I didn't get EMPID, EMP type. Anyone please tell me the reason why I'm not getting those values in my Database. Thank you in advance.

Best answer by shubhama926776

Add a "Reconcile Doc Extraction" task in your process model to validate and finalize extracted data. Ensure your CDT includes EMPID and EMP type fields and that these are correctly mapped from extraction results. Complete the reconciliation step to finalize values. Verify the data flow and process model to make sure fields aren't lost before writing to the database.

4 replies

shubhama926776
shubhama926776Answer
August 8, 2025

Add a "Reconcile Doc Extraction" task in your process model to validate and finalize extracted data. Ensure your CDT includes EMPID and EMP type fields and that these are correctly mapped from extraction results. Complete the reconciliation step to finalize values. Verify the data flow and process model to make sure fields aren't lost before writing to the database.

    P
    pavanik708440Author
    August 11, 2025

    Thank you for the suggestion. I added the Reconcile Doc Extraction task to my process model to validate and finalize the extracted data. I also ensured that the fields were properly mapped from the extraction results. Now, I’m able to save all fields correctly in my database.

    harshas2775
    harshas2775
    August 8, 2025

    Try to train your model with few more documents (around 15-20). Also the pdfs should have labels consistent so that  AI skill can extract them successfully.
    To debug this instance you can try and test the skill with the document as well to understand its capability. 

      P
      pavanik708440Author
      August 11, 2025

      Thank you for the suggestion. I added a few more documents to train the model, included the Reconcile Doc Extraction task in the process model, and ensured the fields were mapped properly. Now, I’m able to save all fields successfully in the database.

      Terms & ConditionsAccessibility statement