b03247f360
Replaces every "task" identifier that referred to the BaseTask abstraction with "worker". Asyncio task plumbing (asyncio.Task, BaseTaskManager, TaskManager, create_task, cancel_task, etc.) stays untouched. Highlights: - Classes: BaseTask → BaseWorker, PipelineTask → PipelineWorker, LLMTask → LLMWorker, LLMContextTask → LLMContextWorker, TaskBus → WorkerBus, TaskRegistry → WorkerRegistry, TaskActivationArgs → WorkerActivationArgs, TaskReadyData → WorkerReadyData, TaskRegistryEntry → WorkerRegistryEntry, TaskObserver → WorkerObserver, all Bus*TaskMessage → Bus*WorkerMessage, BusAddTaskMessage.task field → worker, BusWorkerRegistryMessage.tasks field → workers. - Methods/decorators: activate_task → activate_worker, deactivate_task → deactivate_worker, add_task → add_worker, watch_task → watch_worker, @task_ready → @worker_ready, setup_pipeline_task hook → setup_pipeline_worker. - Params/fields: FrameProcessorSetup.pipeline_task and FunctionCallParams.pipeline_task → pipeline_worker. Parameter names like task_name → worker_name; spawn/run accept worker:. - Files: pipeline/base_task.py → base_worker.py, pipeline/task.py → worker.py (plus a re-export shim at pipeline/task.py), task_observer.py → worker_observer.py, task_ready_decorator.py → worker_ready_decorator.py, pipecat.tasks → pipecat.workers, llm_task.py → llm_worker.py, llm_context_task.py → llm_context_worker.py, examples/multi-task → examples/multi-worker. Back-compat: - PipelineTask kept as a deprecated subclass of PipelineWorker that warns on construction. - pipecat.pipeline.task re-exports PipelineWorker/PipelineTask/etc. so existing user imports keep working. - FrameProcessor.pipeline_task kept as a deprecated property that forwards to pipeline_worker. Local variables in examples that hold a worker (task = PipelineTask(...)) are renamed to worker = PipelineWorker(...). Asyncio-task locals (runner_task, etc.) are preserved.
120 lines
3.6 KiB
Python
120 lines
3.6 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
import time
|
|
|
|
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.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeakingFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.worker import PipelineParams, PipelineWorker
|
|
from pipecat.processors.audio.vad_processor import VADProcessor
|
|
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import create_transport
|
|
from pipecat.services.whisper.stt import MLXModel, WhisperSTTServiceMLX
|
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
from pipecat.transports.daily.transport import DailyParams
|
|
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
|
|
|
load_dotenv(override=True)
|
|
|
|
|
|
STOP_SECS = 2.0
|
|
|
|
|
|
class TranscriptionLogger(FrameProcessor):
|
|
"""Measures transcription latency.
|
|
|
|
Uses the (intentionally) long STOP_SECS parameter to give the transcription time to finish,
|
|
then outputs the timing between when the VAD first classified audio input as not-speech and
|
|
the delivery of the last transcription frame.
|
|
"""
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
self._last_transcription_time = time.time()
|
|
|
|
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
|
await super().process_frame(frame, direction)
|
|
|
|
if isinstance(frame, UserStoppedSpeakingFrame):
|
|
logger.debug(
|
|
f"Transcription latency: {(STOP_SECS - (time.time() - self._last_transcription_time)):.2f}"
|
|
)
|
|
|
|
if isinstance(frame, TranscriptionFrame):
|
|
self._last_transcription_time = time.time()
|
|
|
|
# Push all frames through
|
|
await self.push_frame(frame, direction)
|
|
|
|
|
|
# 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,
|
|
),
|
|
"twilio": lambda: FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
logger.info(f"Starting bot")
|
|
|
|
stt = WhisperSTTServiceMLX(
|
|
settings=WhisperSTTServiceMLX.Settings(
|
|
model=MLXModel.LARGE_V3_TURBO.value,
|
|
),
|
|
)
|
|
|
|
tl = TranscriptionLogger()
|
|
vad_processor = VADProcessor(
|
|
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS))
|
|
)
|
|
|
|
pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
|
|
|
|
worker = PipelineWorker(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
|
)
|
|
|
|
@transport.event_handler("on_client_disconnected")
|
|
async def on_client_disconnected(transport, client):
|
|
logger.info(f"Client disconnected")
|
|
await worker.cancel()
|
|
|
|
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
|
|
|
await runner.run(worker)
|
|
|
|
|
|
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()
|