Does the machine learning api still work:
I have used the following approach:
Added my UiPath taxonomy in the studio
Digitised the document (Using ABBYY OCR)
Used the classifier - to identify its an invoice
Used the extractor - using the machine learning UiPath endpoint as mentioned.
When coming to the validation station, I see that nothing ever gets picked up by the extractor end point.
So is the endpoint still working? As nothing is retrieved? I have re-generated my unique key as well.
Have you checked that in the Data Extraction Scope you checked (activated) the data extraction using the “Configure Extractors” wizard?
Also pls try to grab the supported, released ML Extractor version in the UiPath.DocumentUnderstanding.ML.Activities package isntead of the deprecated UiPath.MachineLearningExtractor package.
Thank you for the update, it seems that I still had the deprecated version, and hence it stopped working with my latest workflow. Everything is working now.
One question I have: When is there a ‘trainer’ activity coming for the data extraction part. So far just the ‘classifier’ trainer activity is released. I have read numerous articles that it would be out Q1 in 2020, but I assume due to corona virus, it is delayed?
It is a work in progress. The first stage that will be released very soon, is the custom model training and retraining for on-prem ML service deployments. Soon to follow is a trainer activity capable of collecting the validated data and making it available for retraining the model at your convenience.
Thank you very much.
Do we have a release date yet, as in, will it be available before June 2020?
For the first stage, that’s the plan… but you know how plans are
so no promises yet
No worries, that is all good. This is a HUGE addition the the intelligent OCR activities! Can’t wait for this feature to come out. Thank you sir!
A couple of things:
(a bit late, but… by the way, welcome to our Forum community! I hope you are enjoying the content and the activity around
and second, have a look here - I just posted a new workflow sample that shows Action Center integration, might be of some help to you:
The IntelligentOCR package allows users to perform document processing in their workflows, with some out-of-the-box functionality available for usage, as well as the framework required for building your own document classification and data extraction components.
To run the workflows, you must add your own ApiKey for Document Understanding from https://platform.uipath.com.
EDIT1: Action Center Integration Sample
Here is a sample workflow that uses an end to end document understan…
Have a great day,
Thank you very much!
Do we have an update on the release date of the ‘classifier’ trainer activity? I know it is a work in progress, but is there any first version release date soon?