Commit Graph

13 Commits

Author SHA1 Message Date
Mark Backman
503e5e9106 Fix Gemini Live local VAD by sending correct activity events to server
When Gemini Live was configured with local VAD (server-side VAD disabled),
the service was listening for the wrong frame types and not sending
ActivityStart/ActivityEnd events to the server. Now it listens for
VADUserStartedSpeakingFrame/VADUserStoppedSpeakingFrame and sends the
appropriate activity signals when local VAD is in use.

Also removes the unnecessary local SileroVADAnalyzer from server-side VAD
examples and adds a new 26a example demonstrating local VAD configuration.
2026-03-25 18:00:13 -04:00
Paul Kompfner
d779a5b4ea Use "developer" role for programmatic conversation-kickoff messages
These messages are developer instructions to the assistant (e.g. "Please
introduce yourself to the user"), not simulated user input. The
"developer" role is semantically correct for this purpose.
2026-03-24 16:02:42 -04:00
Mark Backman
cd28c82de3 Update examples to use the class Settings alias 2026-03-07 09:15:24 -05:00
Mark Backman
2c85d2056c Examples fixes for Gemini Live 2026-03-06 18:42:22 -05:00
Aleix Conchillo Flaqué
593b75bc8b Update foundational examples to use "user" role
Use system_instruction on LLM service constructors instead of adding
system messages to LLMContext. Messages added to context now use
"user" role.
2026-03-06 09:53:33 -08:00
Aleix Conchillo Flaqué
307aeaeda0 examples: update with LLMUserAggregatorParams vad_analyzer and VADProcessor 2026-01-30 10:07:34 -08:00
Aleix Conchillo Flaqué
861588e4a3 examples: update all examples to use the new LLMContextAggregatorPair tuple 2026-01-13 14:01:53 -08:00
Aleix Conchillo Flaqué
2626154a64 update examples and tests copyright and use a proper dash in 2024-2026 2026-01-07 19:32:22 -08:00
Aleix Conchillo Flaqué
a14c911fb2 scripts(evals): improve eval assertion on exit 2025-12-14 12:37:05 -08:00
Paul Kompfner
87131850bc GeminiLiveLLMService supports context-provided system instruction and tools 2025-11-03 10:30:46 -05:00
Paul Kompfner
ac5734d0ed Deprecate expect_stripped_words option from LLMAssistantAggregatorParams, when used with the newer LLMAssistantAggregator, which now handles word spacing automatically.
This commit does not change how it works in the older `LLMAssistantContextAggregator`.
2025-10-30 17:22:47 -04:00
Paul Kompfner
f974c66e12 Update GeminiLLMService to work with LLMContext and LLMContextAggregatorPair 2025-10-28 15:46:28 -04:00
Mark Backman
4b415721e2 Update release evals for OpenAI Realtime, Gemini Live Vertex; shorten 26 foundational names 2025-10-10 12:26:23 -04:00