Add additional data to your Workflow even after model training has begun
Add data to the Dataset associated with your Workflow at any point in the model training process. Then, all you have to do is click the new “Refresh Data” button under your Workflow’s name to populate your new data!
Both Refresh Data and Workflow’s Submit Files to Workflow are disabled for workflows with untrained or deleted models.
ReadAPI is now available via web API
The Indico Data team is dedicated to providing you all the options to optimize your experience with our platform. Users who use ReadAPI as their OCR provider can now opt to use the web API version!
The selection between web API and container will be done at the cluster level.
The containerized version will remain available to suit the needs of all of our users and their specific security concerns and user cases.
Use sorting to find your Explain class metrics more easily
In Explain, after you’ve completed model training, you can now use the sort drop down to sort your class metrics!
Find data more easily by sorting for:
Other Updates and Improvements:
Improvements have been made to decrease the Workflows canvas, and Datasets list load times.
While labeling Classify and Unbundle models if you have not labeled all of your pages, you will now receive a confirmation prompt to ensure you’ve added all the labels you want.
You may also notice the addition of a Pages Labeled progress bar!
The team is working to create new and exciting ways to explore your data through visualization – in order to facilitate these changes, the contents of the Discover module will be distributed to new modules.
This release contains UI dependency updates for improved security.
When a Label filter is selected, information about actual/predicted labels will no longer be visible in Workflows.
This change was made to improve the usability of our app.
In Review, if a document cannot be viewed for any reason, users will be given the option to reject it.
Rejected documents are counted towards rejected analytics.
Patch Releases For This Version:
Updates in 5.2.1:
Updates to allow extraction tasks to finish configuring are contained in this version.
This patch contains a timeout to correct PDFExtraction getting stuck in XML postprocessing in certain, rare, circumstances.
Updates in 5.2.2:
Under specific circumstances, users were seeing different model predictions after upgrading to 5.1. This OCR related issue has been corrected in 5.2.2 and 5.3.0.
Increase intake capacity. Drive top line revenue growth.
Subscribe to receive our latest blog posts, content and industry news on Intelligent Process Automation.
Once a week we’ll send you an email with our best content to help keep you up to date on everything that’s happening in the world of AI, Intelligent Automation and Machine Learning.