Skip to content

Releases: livekit/agents

livekit-agents@0.8.8

27 Aug 00:03
3821f70
Compare
Choose a tag to compare

v0.7.x to v0.8.x migration guide

Patch Changes

  • fix uninitialized SpeechHandle error on interruption - #665 (@theomonnom)

  • voiceassistant: avoid stacking assistant replies when allow_interruptions=False - #667 (@theomonnom)

  • fix: disconnect event may now have a arguments - #668 (@theomonnom)

  • Add ServerMessage.termination handler - #635 (@nbsp)

livekit-plugins-nltk@0.7.2

22 Aug 22:42
b608bd8
Compare
Choose a tag to compare

Patch Changes

livekit-plugins-browser@0.0.2

22 Aug 22:42
b608bd8
Compare
Choose a tag to compare

Patch Changes

livekit-agents@0.8.7

22 Aug 22:42
b608bd8
Compare
Choose a tag to compare

Patch Changes

  • voiceassistant: fix llm not having the full chat context on bad interruption timing - #659 (@theomonnom)

livekit-plugins-silero@0.6.4

17 Aug 00:53
087c703
Compare
Choose a tag to compare

Patch Changes

livekit-plugins-rag@0.2.2

17 Aug 00:53
087c703
Compare
Choose a tag to compare

Patch Changes

livekit-plugins-openai@0.8.1

17 Aug 00:53
087c703
Compare
Choose a tag to compare

Patch Changes

  • add support for Ollama, Perplexity, Fireworks, Octo, Together, and Groq LLMs through the OpenAI API - #611 (@nbsp)

  • allow sending user IDs - #633 (@nbsp)

  • Support OpenAI Assistants API as a beta feature under livekit.plugins.openai.beta - #601 (@keepingitneil)
    Add _metadata to ChatCtx and ChatMessage which can be used (in the case of OpenAI assistants) for bookeeping to sync local state with remote, OpenAI state

livekit-plugins-nltk@0.7.1

17 Aug 00:53
087c703
Compare
Choose a tag to compare

Patch Changes

livekit-plugins-deepgram@0.6.5

17 Aug 00:53
087c703
Compare
Choose a tag to compare

Patch Changes

  • deepgram: fallback to nova-2-general when the language isn't supported - #623 (@theomonnom)

livekit-plugins-cartesia@0.4.1

17 Aug 00:53
087c703
Compare
Choose a tag to compare

Patch Changes

  • Switch Cartesia to a sentence tokenizer and keep the same context id throughout. - #608 (@keepingitneil)
    Propagate segment_id through the basic sentence tokenizer