Whats are the steps to setup Intelligent Form Extractor on premise?
Make sure to do below prerequisites before embarking on installation:
- Set-up AI Center and Orchestrator On-Prem
- If air-gapped, make sure you have also followed the steps listed in the Run The AI Center Application Installer .
There are two main steps that is needed to do to use Intelligent Form Extractor (IFE):
- Set-up Handwriting Recognition
- Set-up Intelligent Form Extractor.
Set-up Handwriting Recognition
Setting up handwriting recognition for IFE requires few simple steps.
- Navigate to Document Understanding ML packages and create a handwriting package.
- The package can be created by hitting “Submit” on this page and providing essential information – Package Name – on the next page. The other information is optional and can be provided/left out based on user preference
- Once the handwriting package is created, create a corresponding ML Skill. The ML Skill can be created by hitting “Create new” on ML Skills tab and supplying the needed information in the all the fields. Please note that “Skill description” is optional but we recommend providing this information for later convenience. Make sure the “Enable GPU” toggle is turned off.
- Once the skill gets created, click on the row corresponding to the skill in the ML Skills tab and go to “Modify Current Deployment”. Turn on the toggle and make the ML Skill Public:
- Once the ML Skill is updated and made public, click on the row corresponding to the skill and copy the URL from the top section. This is the URL that will later used for setting up the skill for IFE:
Set-up Intelligent Form Extractor
- Navigate to Document Understanding ML packages and create an Intelligent Form Extractor package. Provide all the needed information. Select “UiPath OCR” in the “OCR Engine” field and provide the URL that you obtained previously from public handwriting ML Skill in the “OCR URL” fields. Note that even though both these fields are suggested as “Optional”, this information is still needed. Not providing this information will result in errors .
- Create a ML Skill corresponding to the IFE package by clicking on “ML Skills” and hitting “Create new” and providing the required information
- Post the ML Skill is ready and the status changes to “Available”, click on that ML Skill and go to “Modify current deployment” and make the ML Skill “Public”
- Once the skill becomes “Available”, click on that Skill and copy the URL. This is the URL that need to be used in the Studio workflow.
- Use the URL obtained above in the “Endpoint” configuration of IFE and leave the Api Key field blank or “” if DU bundle is tagged to Orchestrator (ie Air Gapped Setup) else pass the API key acquired from cloud platform.