opik

v2.0.37 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 19d Error & Performance Tracking

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ 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 summary

Skip row‑numbering CTE in version‑id lookups to improve performance.

Changes in this release

Type	Severity	Summary	CVE
Feature	Low	Add agentic tools online scoring functionality Add agentic tools online scoring functionality Source: granite4.1:30b@2026-05-22-audit Confidence: low	—
Performance	Medium	Skip row-numbering CTE in version-id lookups Skip row-numbering CTE in version-id lookups Source: llm_adapter@2026-05-21 Confidence: high	—

Full changelog

What's Changed

[OPIK-5333][BE]: agentic tools online scoring; by @aadereiko in https://github.com/comet-ml/opik/pull/6649
[OPIK-6550] [BE] perf: skip row-numbering CTE in version-id lookups by @LifeXplorer in https://github.com/comet-ml/opik/pull/6727

Full Changelog: https://github.com/comet-ml/opik/compare/2.0.36...2.0.37

View diff on GitHub

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

Share on X Share on Bluesky

Track opik

Get notified when new releases ship.

About opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

opik

Summary

Changes in this release

What's Changed

Related context

Related tools

Earlier breaking changes