LiveKit Community

I currently have my agent session defined as :
session = AgentSession(
        stt=agent_config.get_stt_service(),
        llm=agent_config.get_llm_service(),
        tts=agent_config.get_tts_service(),
        vad=silero.VAD.load(),
        turn_detection="manual",
        use_tts_aligned_transcript=True,
    )

I would like my LLM to produce both an answer as well as some textual "suggested questions", a list of questions to continue the conversation. These questions should then be forwarded to the frontend of the user as suggested questions bubbles, how can I achieve this?

Thanks for reaching out, aile. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.


I don't have the answer you're looking for.

You could also try asking your question:
• in one of the other Slack channels
or
• to <https://deepwiki.com/livekit/livekit_composite|https://deepwiki.com/livekit/livekit_composite> which is trained on all LiveKit source code

If you find the answer, please post it here to help others!
