Releases: livekit/agents
livekit-plugins-turn-detector@0.3.4
Patch Changes
- add jinja2 dependency to turn detector - #1277 (@davidzhao)
livekit-plugins-openai@0.10.12
Patch Changes
- fix unknown
metadata
&store
fields on OpenAI-like API - #1276 (@theomonnom)
livekit-agents@0.12.5
Patch Changes
-
make max_endpoint_delay configurable - #1277 (@davidzhao)
-
set USE_DOCSTRING as default for ai_callable - #1266 (@longcw)
-
fix: do not log process warning when process not found - #1281 (@davidzhao)
-
fix context when functions have been called - #1279 (@jmugicagonz)
livekit-agents@0.12.4
livekit-plugins-turn-detector@0.3.3
livekit-plugins-openai@0.10.11
Patch Changes
-
Moved create_ai_function_info to function_context.py for better reusability and reduce repetation - #1260 (@jayeshp19)
-
add on_duplicate option for multimodal agent response create - #1204 (@longcw)
-
Add support for OpenAI's "detail" parameter to ChatImage - #1213 (@bcherry)
Add support for data URLs on ChatImage in the Anthropic plugin.
-
filter out empty message for set chat ctx in realtime model - #1245 (@longcw)
-
fix: correctly parse function argument types - #1221 (@jayeshp19)
-
add session_updated event for RealtimeSession - #1253 (@longcw)
-
added llama 3.3 70b to model definitions - #1233 (@davidzhao)
-
update default realtime model to gpt-4o-realtime-preview-2024-12-17 - #1250 (@davidzhao)
-
Fix center_aspect_fit bug, add scale_aspect_fit and scale_aspect_fill resizing options. - #1222 (@bcherry)
Make scale_aspect_fit the new default resizing option for video frames.
livekit-plugins-deepgram@0.6.15
Patch Changes
-
added streaming audio decoder for compressed audio. - #1236 (@davidzhao)
-
Support Deepgram TTS - #1201 (@jayeshp19)
livekit-plugins-browser@0.0.5
Patch Changes
- fix: fix
imgui
setup - #1226 (@mbukeRepo)
livekit-plugins-azure@0.5.1
Patch Changes
- fix azure stt language autodetection - #1246 (@davidzhao)
livekit-plugins-anthropic@0.2.8
Patch Changes
-
Moved create_ai_function_info to function_context.py for better reusability and reduce repetation - #1260 (@jayeshp19)
-
Add support for OpenAI's "detail" parameter to ChatImage - #1213 (@bcherry)
Add support for data URLs on ChatImage in the Anthropic plugin.
-
fix: correctly parse function argument types - #1221 (@jayeshp19)
-
Fix center_aspect_fit bug, add scale_aspect_fit and scale_aspect_fill resizing options. - #1222 (@bcherry)
Make scale_aspect_fit the new default resizing option for video frames.