Change8

arize-phoenix-v16.0.0

Breaking Changes
📦 arize-phoenixView on GitHub →
1 breaking3 features🐛 1 fixes🔧 1 symbols

Summary

Version 16.0.0 introduces powerful Sandboxed Code Evaluators for flexible evaluation strategy composition and enables native web search/fetch for agents. This release contains breaking changes requiring migration.

⚠️ Breaking Changes

  • Sandboxing and Code Evaluators were introduced, which likely changes how evaluation strategies are defined and executed. Users should consult MIGRATION.md for specific required changes.

Migration Steps

  1. Review the MIGRATION.md file for detailed instructions regarding the changes related to Sandboxing and Code Evaluators.

✨ New Features

  • Introduction of Sandboxed Code Evaluators, allowing users to compose evaluation strategies by writing Python or TypeScript evaluate() functions directly in the Phoenix UI for server-side execution.
  • Code Evaluators support composite scoring, embedding-based evaluation, and LLM juries.
  • Agents now enable provider native web search/fetch when available.

🐛 Bug Fixes

  • Fixed an issue preventing broken tool groups in agents.

Affected Symbols