bff741a647
Pass realtime_service_mode=RealtimeServiceModeConfig() through every realtime LLM service example (base, async-tool, video, text-output, persistent-context, update-settings, MCP) so context aggregation uses the new realtime-mode semantics instead of relying on local VAD as a workaround. Where examples previously wired SileroVADAnalyzer into LLMUserAggregatorParams to coax turn frames out of services that don't emit them server-side (AWS Nova Sonic, Ultravox, Gemini Live), the local VAD is now removed. realtime_service_mode keeps context writes correct without it, and the Phase 1.5 server-side InterruptionFrame fixes for Nova Sonic and Ultravox keep the bot from talking past the user when they barge in. Transcript-logging event handlers move from on_user_turn_stopped / on_assistant_turn_stopped to on_user_message_added / on_assistant_message_added, which carry the finalized text in realtime mode (the turn-stopped events fire before the message is finalized, so their `content` is None in that mode). For services that don't emit user-turn frames (Gemini Live, AWS Nova Sonic, Ultravox) the example now carries a Tier 1 comment block that spells out which downstream processors won't activate, how to add local VAD if needed, and the caveat that locally-generated turn boundaries are a heuristic that may diverge from server-side ground truth. Adds examples/realtime/realtime-openai-local-vad.py, a new variant of the OpenAI Realtime example that disables OpenAI's server-side turn detection and drives turn boundaries locally — useful when you want a turn analyzer like LocalSmartTurnV3 to decide when the user is done speaking. Server-emitted turn frames are still preferred when available. The Gemini Live local-VAD variant already existed; it's been updated in place rather than rewritten.
127 lines
3.6 KiB
Python
127 lines
3.6 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
|
|
import asyncio
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
from loguru import logger
|
|
|
|
from pipecat.frames.frames import LLMRunFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.processors.aggregators.llm_context import LLMContext
|
|
from pipecat.processors.aggregators.llm_response_universal import (
|
|
LLMContextAggregatorPair,
|
|
RealtimeServiceModeConfig,
|
|
)
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import (
|
|
create_transport,
|
|
maybe_capture_participant_camera,
|
|
maybe_capture_participant_screen,
|
|
)
|
|
from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
|
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
from pipecat.transports.daily.transport import DailyParams
|
|
|
|
load_dotenv(override=True)
|
|
|
|
# We use lambdas to defer transport parameter creation until the transport
|
|
# type is selected at runtime.
|
|
transport_params = {
|
|
"daily": lambda: DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
video_in_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
video_in_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
llm = GeminiLiveLLMService(
|
|
api_key=os.environ["GOOGLE_API_KEY"],
|
|
settings=GeminiLiveLLMService.Settings(
|
|
voice="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
|
|
# system_instruction="Talk like a pirate."
|
|
),
|
|
# inference_on_context_initialization=False,
|
|
)
|
|
|
|
context = LLMContext(
|
|
[
|
|
{
|
|
"role": "developer",
|
|
"content": "Say hello.",
|
|
},
|
|
],
|
|
)
|
|
# Server-side VAD is enabled by default; no local VAD is added.
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
context,
|
|
realtime_service_mode=RealtimeServiceModeConfig(),
|
|
)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
user_aggregator,
|
|
llm,
|
|
transport.output(),
|
|
assistant_aggregator,
|
|
]
|
|
)
|
|
|
|
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([LLMRunFrame()])
|
|
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()
|