Data and AI releases

548 this month · 176 companies

arize-phoenix: v13.19.0

UpdateNot yet verified

13.19.0 (2026-03-26) Features add PromptInput compound component for AI interactions (729a56f) agent-chat: collapse tool calls into expandable pool + streaming perf (39acfcf) agent: session switcher with delete controls and async summaries (1443c29) app: update project creation flow with color picker and description (ccfdcf2) Bug Fixes deps: pin...

AI agentsStreaming

Read on github.com

Also shipped Mar 26, 2026Arize AI in March 2026 →

Mutual Exclusivity

What it is: Grouping guides and surveys into a mutual exclusivity set ensures each end-user sees at most one from the group. The primary use case is platform-specific announcements: create a version for iOS and another for Android, add both to the group, and users see only the version that matches their device.

GA
Source ↗

TTS speak speed (Early Access)

You can now control the speaking rate of Deepgram TTS in the Voice Agent API using the agent.speak.provider.speed parameter. This parameter accepts a float value between 0.7 and 1.5 , with 1.0 as the default.

Update
Source ↗

Updated LLM models

New OpenAI models , Two new models are now available in the Standard pricing tier: gpt-5.4-nano gpt-5.4-mini Gemini 2.0 Flash deprecated , The gemini-2.0-flash model is now deprecated. We recommend migrating to gemini-2.5-flash or a newer Gemini model. See the Google models table for alternatives.

Update
Source ↗

More from phoenixEvery phoenix release →

arize-phoenix: v13.18.0

13.18.0 (2026-03-24) Features app: add prompt version diff view (0e9e76b) Replace all markdown rendering with streamdown (d6a64d5)

Update
Source ↗

arize-phoenix-evals: v2.12.0

2.12.0 (2026-03-24) Features evals: accept structured data eval inputs (5f33727) Bug Fixes evals: allow prompt_template and kwargs in built-in classification evaluators (2ec192c) Pin LiteLLM <1.82.7 to mitigate supply chain attack (48970b6) playground: prevent OTel context leak causing duplicate trace_id in dataset runs (2a24625) Documentation evals...

Update
Source ↗

arize-phoenix: v13.17.0

13.17.0 (2026-03-23) Features agent: implement experimental px-gql simulated bash tool (843fa8f) copy spanID to clipboard (a7ded9a) Bug Fixes security: resolve high and moderate dependency vulnerabilities (69ffc21) Starlette 1.0+ TemplateResponse compatibility (43b18b7)

Update
Source ↗

arize-phoenix: v13.20.0

13.20.0 (2026-03-29) Features rest-api: DELETE /prompt_versions/{id}/tags/{tag_name} (0c61d16) rest-api: DELETE /prompts/{prompt_identifier} (ac9ffbe) ui: add CopyField component and clean up settings layout (3c7bd2b)

Update
Source ↗

arize-phoenix: v13.16.0

13.16.0 (2026-03-22) Features Add backend skill (cc8de3b) add configurable package manager preference per language (bf35656) add copy name/ID action menu to nav breadcrumbs (bc3ae84) add copy-to-clipboard to session, span, and trace ID cells (ad32209) add expectedRunCount experiment field and experiments table fraction (d1367fb) add GET /v1/user endpoint...

Update
Source ↗

arize-phoenix: v13.22.0

13.22.0 (2026-04-01) Features ui: updated provider and integration icons, logo icon agent skill (8668c43) Bug Fixes fail loudly on Windows + Python 3.14 install (50d66a3)

Update
Source ↗

arize-phoenix: v13.21.0

13.21.0 (2026-04-01) Features add Python 3.14 support (except Windows) (50c08e3) agent: Improve session summaries (f1750a9) server: REST endpoint for secrets management (39f68cf)

Update
Source ↗