Files
pipecat/examples/foundational/26c-gemini-multimodal-live-video.py
2025-08-06 19:38:06 -07:00

129 lines
4.1 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
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import (
create_transport,
maybe_capture_participant_camera,
maybe_capture_participant_screen,
)
from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=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)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=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)),
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."
# inference_on_context_initialization=False,
)
context = OpenAILLMContext(
[
{
"role": "user",
"content": "Say hello.",
},
],
)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected: {client}")
await maybe_capture_participant_camera(transport, client, framerate=1)
await maybe_capture_participant_screen(transport, client, framerate=1)
await task.queue_frames([context_aggregator.user().get_context_frame()])
await asyncio.sleep(3)
logger.debug("Unpausing audio and video")
llm.set_audio_input_paused(False)
llm.set_video_input_paused(False)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
await runner.run(task)
async def bot(runner_args: RunnerArguments):
"""Main bot entry point compatible with Pipecat Cloud."""
transport = await create_transport(runner_args, transport_params)
await run_bot(transport, runner_args)
if __name__ == "__main__":
from pipecat.runner.run import main
main()