from dotenv import load_dotenv

from livekit import agents
from livekit.agents import AgentSession, Agent, RoomInputOptions
from livekit.plugins import (
    google,
    #openai,
    cartesia,
    deepgram,
    noise_cancellation,
    silero,
)
from livekit.plugins.turn_detector.multilingual import MultilingualModel

load_dotenv()


class Assistant(Agent):
    def __init__(self) -> None:
        super().__init__(instructions="You are a helpful voice AI assistant.")


async def entrypoint(ctx: agents.JobContext):
    session = AgentSession(
        stt=deepgram.STT(model="nova-3", language="multi"),

        #llm=openai.LLM(model="gpt-4o-mini"),
        #llm=openai.LLM.with_ollama(model="qwen3:4b", base_url="http://localhost:11434/v1"),

        llm=google.LLM(model="gemini-2.0-flash"),

        tts=cartesia.TTS(),
        vad=silero.VAD.load(),
        turn_detection=MultilingualModel(),
    )

    await session.start(
        room=ctx.room,
        agent=Assistant(),
        room_input_options=RoomInputOptions(
            # LiveKit Cloud enhanced noise cancellation
            # - If self-hosting, omit this parameter
            # - For telephony applications, use `BVCTelephony` for best results
            noise_cancellation=noise_cancellation.BVC(), 
        ),
    )

    await ctx.connect()

    await session.generate_reply(
        instructions="Greet the user and offer your assistance./no_think"
    )


if __name__ == "__main__":
    agents.cli.run_app(agents.WorkerOptions(entrypoint_fnc=entrypoint))