What's Changed
- docs: Add missing params to Generate Goldens From Documents guide by @AbdoAlshoki2 in #3311
- . by @penguine-ip in #3337
- feat(persona): metadata and noise url by @tanayvaswani in #3333
- fix(models): add Claude Opus 5.5 to the Anthropic registry (AmazonBedrockModel unchanged) by @kimnamu in #3349
- fix(voice): phone call lifecycle by @tanayvaswani in #3379
- . by @penguine-ip in #3402
- feat: Add transcription accuracy metric by @A-Vamshi in #3414
- feat: Add user_transcript support to voice connectors by @A-Vamshi in #3403
- fix(litellm): model name region by @tanayvaswani in #3424
- feat: update expectations reasoning and add verdicts as an attribute by @A-Vamshi in #3423
- feat(dataset): send the pulled dataset version with test runs by @ykocaogullar in #3417
- feat(expectations): add support for reading
metadataandtagsby @tanayvaswani in #3443 - docs(seo): benchmark titles, RAGAS description, sitemap entry by @tony-confidentai in #3119
- feat(docs): record where a tab arrived from, carry the trail to every host by @tony-confidentai in #3331
- feat(metrics): transcription accuracy and sound glitch metrics by @ykocaogullar in #3453
- feat: Add voice input support on all evaluation models by @A-Vamshi in #3460
- feat: Audio support on ConversationalGEval metric by @A-Vamshi in #3462
- Stop dropout and held-tone detectors firing on normal speech by @ykocaogullar in #3459
- Move blog posts into folders and content images into a local media li… by @penguine-ip in #3465
- Docs/llm evaluation guide polish by @penguine-ip in #3467
- feat: Add context exceeded error for metric evaluations by @A-Vamshi in #3455
- Add the evaluation setup wizard and
deepeval setupby @penguine-ip in #3472 - Update Confident AI wording by @penguine-ip in #3471
- Add Build with agents dropdown to home hero by @penguine-ip in #3473
New Contributors
- @AbdoAlshoki2 made their first contribution in #3311
Full Changelog: python-v4.2.4...setup-v0.1.0