LogoLogo
Python SDKSlack
  • Documentation
  • Cookbooks
  • Self-Hosting
  • Release Notes
  • Reference
  • Changelog
  • History
    • 2025
      • 04.2025
      • 03.2025
      • 02.27.2025
      • 02.14.2025
      • 01.21.2025
    • 2024
      • 12.19.2024
      • 12.05.2024
      • 11.07.2024
      • 10.24.2024
      • 10.03.2024
      • 09.19.2024
      • 09.05.2024
      • 08.23.2024
      • 08.08.2024
      • 07.10.2024
      • 06.07.2024
      • 05.10.2024
      • 04.25.2024
      • 04.12.2024
      • 03.28.2024
      • 03.18.2024
      • 02.16.2024
      • 01.18.2024
      • 01.04.2024
    • 2023 and older
      • 2023
        • 12.07.2023
        • 11.14.2023
        • 10.26.2023
        • 10.11.2023
        • 08.29.2023
        • 07.17.2023
        • 06.05.2023
        • 05.08.2023
        • 04.17.2023
        • 03.13.2023
        • 02.13.2023
        • 01.24.2023
      • 2022
        • 12.19.2022
        • 11.28.2022
        • 11.07.2022
        • 10.10.2022
        • 09.26.2022
        • 09.12.2022
        • 08.29.2022
        • 08.15.2022
        • 08.01.2022
        • 07.18.2022
        • 06.28.2022
        • 06.06.2022
        • 05.23.2022
        • 05.09.2022
        • 04.25.2022
        • 04.11.2022
        • 03.28.2022
        • 03.14.2022
        • 02.28.2022
        • 02.14.2022
        • 01.31.2022
        • 01.18.2022
      • 2021
        • 12.15.2021: CVE-44228
        • 12.13.2021
        • 11.18.2021
        • 11.02.2021
        • 10.15.2021
        • 09.27.2021
        • 06.25.2021
        • 05.28.2021
        • 04.30.2021
        • 04.16.2021
        • 04.02.2021
        • 03.12.2021
        • 02.26.2021
Powered by GitBook

Support

  • Chat Us On Slack
  • support@arize.com

Get Started

  • Signup For Free
  • Book A Demo

Copyright © 2025 Arize AI, Inc

On this page
  • What's New
  • Enhancements
  • In the News
  • 🎓 New LLM Course Updates
  • 📚 New Paper Readings
  • Anyscale + Arize

Was this helpful?

  1. History
  2. 2023 and older
  3. 2023

10.11.2023

New Releases, Enhancements, Changes + Arize in the News!

Last updated 1 year ago

Was this helpful?

What's New

Prompt Playground

Uncover poorly performing prompt templates, iterate on them in real time and verify improved LLM outputs before deployment. Choose to edit the prompt variables, LLM parameters, or the prompt template itself. Then re-run the prompt to easily compare responses for analysis prior to implementing a new or revised prompt template. Learn more .

Enhancements

Support for gpt-3.5-instruct-turbo

Users can now select to use gpt-3.5-instruct-turbo as their LLM of choice when using the Prompt Playground, or summarizing embeddings clusters.

Interactive Calibration Chart and New Precision Recall (PR) Curve

Users can interact with the calibration chart in the "More Charts" view of Performance Tracing. The chart now includes traffic bars and users have the ability to zoom into certain regions of their data, allowing for more granular insight. In addition, users can now select to view a PR curve for further analysis.

Y-Axis Controls On Dashboards

Users can now customize their Y-axis domain, customizing the min and max per-widget. Simply go into the edit form of a line or bar chart widget and hit the Display tab to control. Alternatively, users can employ auto and the charting library will compute what it believes to be the most comprehensible domain automatically.

Simultaneous UMAP visualization for multiple embedding features

Visualize your UPMAP for multiple embedding features for a multi-input model simultaneously, without needing to increase the number of predictions sent. To view multiple embedding features, select them in the "Dimensions" dropdown.

"Average" Option Added to Quantiles Plots

For additional views, users can now plot the mean, in addition to the previously offered median in quantile plots.

Python SDK v7.5.1

  • Core SDK is compatible with Python 3.6+ (previously 3.8+)

  • SDK now works with any version of pyarrow

In the News

🎓 New LLM Course Updates

📚 New Paper Readings

Anyscale + Arize

Learn about Python SDK fixes and improvements .

Catch up on the latest in with these new community readings:

We're proud to be a launch partner of Anyscale Endpoints! , Arize and Anyscale Endpoints enable developers to achieve LLM observability across different use cases on any cloud as their AI applications evolve.

here
LLM Tracing and Observability with Arize Phoenix
How Wayfair Achieves Self-Service Onboarding for MLOps Tooling
Traces and Spans
ReAct Architecture: Simple AI Agents
HDBSCAN
LLM Monitoring
AI research papers
Large Content and Behavior Models
Explaining Grokking Through Circuit Efficiency
Through an early integration
here