Thank you for being a valued Indico user! We’re constantly making updates to our app and APIs, working on new features, and garnering feedback to be best in class for intelligent process automation. Have ideas on how to make our product even better – please let us know here!
Innovations and Updates in v4.13:
Examples List Page
- There is now a page to view all of a task’s examples (i.e. documents, images, CSV rows) in one place for labeling, relabeling, or restoring rejected items.
- There is now a page to view all of a task’s examples (i.e. documents, images, CSV rows) in one place for labeling, relabeling, or restoring rejected items.
-
- Ability to filter and sort by file type, name or row number, and label status.
- Accessible from both Explain model details page and from Teach Task Settings.
- Note: If rejected items are restored they are restored for all tasks across the dataset.
- Document Name in Discover
- When classifying in Discover, the file name is now available.
- European Language Support
- Support for 7 European languages has been built in for models and OCR.
- Models and OCR can handle multiple languages in a dataset, but each document should be a single language.
- Languages can be set at Dataset creation via Language dropdown in Advanced Options.
-
- Languages now supported are: Spanish, Polish, Portuguese, Italian, German, Dutch, and French.
Other Improvements and Bug Fixes
- We have updated our base Classification model for all new models; any existing models will remain on the current version of the base model for training purposes, please contact us if you have any questions.
- Ongoing security fixes are included in this release.
- Snapshots for Image classification tasks now include the original URLs, rather than storage URLs, so that new datasets can be created from the Snapshot.
- When relabeling document examples from Explain Explore, the documents will now launch as documents rather than text.
[addtoany]
