Skip to content
Draft
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions source/hub/ui/release_notes/2026-02-24.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
2.4.0 (2026-02-24)
==================

Hub v2.4.0 introduces performance enhancements for large datasets, new interactive actions in the Playground, and a more robust groundedness evaluation pipeline. This version also shifts entirely to our modern v2 API for improved reliability and long-term stability.


Hub UI
------

What's new?
~~~~~~~~~~~

**Server-backed dataset management**
Dataset test cases now load via a server-backed table, significantly improving performance for large datasets. You can now filter, sort, and paginate through thousands of test cases without slowing down your browser. Additionally, a new bulk action preview shows you exactly how many items will be affected before you apply changes, making large-scale edits safer and more predictable.

**Enhanced Playground interactivity**
The Playground now features quick actions to streamline your prompt engineering workflow. You can instantly remove the last conversation turn, re-generate the assistant's previous answer, and toggle between "Pretty" and "Raw" Markdown rendering. Your display preference is saved in your browser, ensuring a consistent experience across sessions.

**Advanced 3-step Groundedness pipeline**
Groundedness evaluation has been upgraded to a multi-step pipeline that extracts evidence and re-checks borderline claims for higher accuracy. You can now view detailed, per-claim groundedness reasons directly in the results and comparison views, presented in a clear Markdown format. This helps you understand exactly why a response was flagged and reduces false positives.

**Improved task stability**
Task management has been updated to provide stricter validation and more predictable behavior. This ensures that tasks are always linked to valid entities, improving the reliability of your organizational workflows.

What's fixed?
~~~~~~~~~~~~~

- **Large Knowledge Base uploads** - Increased the upload limit to prevent Knowledge Base files larger than 10MB from failing. This ensures that comprehensive documentation sets can be imported without interruption.

- **Evaluation log clarity** - Reduced noise in system logs by suppressing internal warnings during evaluation. This makes it easier to identify and troubleshoot actual results in your runs.

Hub SDK
-------

No changes yet.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

A couple of suggestions for this line:

  1. The phrase 'No changes yet' is a bit informal for release notes. To maintain a professional tone and avoid ambiguity, consider using a more standard phrase like 'No changes in this release'.
  2. It's a good practice to end files with a single newline character. This prevents issues with some command-line tools and is a common convention.
Suggested change
No changes yet.
No changes in this release.