This release adds 2 notable features for engineering teams evaluating rollout.
Published 28d
Error & Performance Tracking
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
evaluation
hacktoberfest2025
langchain
llama-index
llm
llm-evaluation
+5 more
llm-observability
llmops
openai
playground
prompt-engineering
Summary
AI summaryRedesign of the Run experiment flow in Prompt Playground.
Full changelog
What's Changed
- [OPIK-6334] [FE] feat: add skeleton loaders to Prompt and Agent Playgrounds by @andriidudar in https://github.com/comet-ml/opik/pull/6618
- [OPIK-6372] [SDK] fix: merge duplicate Create messages in local emulator by @alexkuzmik in https://github.com/comet-ml/opik/pull/6613
- [OPIK-6334] [FE] fix: render page-surface assistant loader and error state full-bleed by @andriidudar in https://github.com/comet-ml/opik/pull/6620
- [OPIK-6348] [BE] fix: rename BI event key 'environment' to 'config_environment' by @petrotiurin in https://github.com/comet-ml/opik/pull/6612
- [OPIK-6346] Silent-skip playground logging when permissions are missing by @LifeXplorer in https://github.com/comet-ml/opik/pull/6574
- [OPIK-6307] [FE] feat: redesign Run experiment flow in Prompt Playground by @awkoy in https://github.com/comet-ml/opik/pull/6571
Full Changelog: https://github.com/comet-ml/opik/compare/2.0.22...2.0.23
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Related context
Related tools
Earlier breaking changes
- v2.0.38 Split stats query and gate legacy feedback_scores UNION in BE.
Beta — feedback welcome: [email protected]