Files
pipecat/examples/foundational/26-gemini-multimodal-live.py
2025-03-13 14:35:47 -07:00

95 lines
2.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import os
import sys
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import LLMMessagesAppendFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
vad_enabled=True,
vad_audio_passthrough=True,
# set stop_secs to something roughly similar to the internal setting
# of the Multimodal Live api, just to align events. This doesn't really
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
)
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
# system_instruction="Talk like a pirate."
)
pipeline = Pipeline(
[
transport.input(),
llm,
transport.output(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await task.queue_frames(
[
LLMMessagesAppendFrame(
messages=[
{
"role": "user",
"content": "Greet the user.",
}
]
)
]
)
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())