edengby

I got: ValueError: A single term is larger than the allowed chunk size. Term size: 5613 Chunk size: 3900Effective chunk size: 3900

Still having that issue: Task was destroyed but it is pending! ``` {"message": "Task was destroyed but it is pending!\ntask: ", "level": "ERROR", "name": "asyncio", "room": "voice_assistant_room_7053", "user_id": "visitor_id", "pid":...

We are still having issues and such hallucinations. Any update? Does Google knows that issues?

No. Only gemini live api. It keeps answering his own questions also.

AgentSession( llm=google.beta.realtime.RealtimeModel(model="gemini-2.0-flash-exp", voice="Charon",temperature=0.0, top_k=1), turn_detection=EnglishModel(), min_endpointing_delay=0.7, max_endpointing_delay=2.0, vad=silero.VAD.load(activation_threshold=0.7), ) This is how we defined the agent.

@davidzhao I'm sorry it's private repo. I cannot. I can provide you any configuration or logs that are needed. It should be fixed at 1.0.20?

``` session = AgentSession( llm=google.beta.realtime.RealtimeModel(model="gemini-2.0-flash-exp", voice="Charon",temperature=0.0, top_k=1), turn_detection=EnglishModel(), min_endpointing_delay=0.7, max_endpointing_delay=2.0, vad=silero.VAD.load(activation_threshold=0.7), ) room_input = RoomInputOptions() room_output = RoomOutputOptions(transcription_enabled=True) await session.start( agent=VirtualRealtimeAgent(), room=ctx.room, room_input_options=room_input, room_output_options=room_output, ) ``` That's our configuration. Now,...

Worked for me! Thanks. Still having the other issues: - From time to time he is saying dot instead of the "." or reading the function that needs to be...

I was able to reproduce all these issues easily (illustrations, answering his (own) questions): https://github.com/edengby/livekit-google-agent-bugs/ I used Livekit UI and Python agent boilerplates: https://github.com/livekit-examples/voice-pipeline-agent-python https://github.com/livekit-examples/voice-assistant-frontend On models gemini-1.5-flash and gemini-2.5-flash.