V 3.6
V 3.6
Release date: 12-05-2025
Key Highlights
- Metrics:
- Widget in the dashboard has been changed
- More elements are measured now like (Output guardrails time, RAG filter time, LLM section time, etc.)
- LLM metrics are move to a separate LLM Statisics tab
- It's now possible to automatically switch language in the platform with LLM’s or without.
- Ie. if you speak to a bot in in Italian, the language get's detected and switches the default language
- You can switch the language via the API / Websocket
- LLM is now an integrated service in the platform, improving the latency
- The test widget in the platform has been improved:
- New UI
- Can test Text To Speech engines
- Switch which channel you want to test (production, test or BCR)
- New settings TTS on language (better voice selection). You can now select you preferred dialect per language.
- Improve UX for inviting users
- You can create bots without NLU engine (LLM only)
- Split of Text and Voice via API / Websocket
- Setence splitting
- Improved handling of Websocket, Directline and Rest API
- Improved password requirements
- Improved conversational logs
- Additional voices added for ElevenLabs
- Async guardrails
Bug Fixes
- Issues on multi-language not correct
- Fix on websocket sometimes not responding
UX Improvements
- Various small visual improvements