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.
121 lines
4.0 KiB
Python
121 lines
4.0 KiB
Python
#
|
|
# Copyright (c) 2024-2026, 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 pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
from pipecat.frames.frames import LLMRunFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.worker import PipelineParams, PipelineWorker
|
|
from pipecat.processors.aggregators.llm_response_universal import (
|
|
LLMContext,
|
|
LLMContextAggregatorPair,
|
|
LLMUserAggregatorParams,
|
|
)
|
|
from pipecat.services.cartesia.tts import CartesiaTTSService
|
|
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
from pipecat.services.google.llm import GoogleLLMService
|
|
from pipecat.services.heygen.api_liveavatar import LiveAvatarNewSessionRequest
|
|
from pipecat.transports.heygen.transport import HeyGenParams, HeyGenTransport, ServiceType
|
|
|
|
load_dotenv(override=True)
|
|
|
|
logger.remove(0)
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
|
|
async def main():
|
|
async with aiohttp.ClientSession() as session:
|
|
transport = HeyGenTransport(
|
|
api_key=os.environ["HEYGEN_LIVE_AVATAR_API_KEY"],
|
|
service_type=ServiceType.LIVE_AVATAR,
|
|
session=session,
|
|
params=HeyGenParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
session_request=LiveAvatarNewSessionRequest(
|
|
is_sandbox=True,
|
|
# Sandbox mode only works with this specific avatar
|
|
# https://docs.liveavatar.com/docs/developing-in-sandbox-mode#sandbox-mode-behaviors
|
|
avatar_id="dd73ea75-1218-4ef3-92ce-606d5f7fbc0a",
|
|
),
|
|
)
|
|
|
|
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
|
|
|
tts = CartesiaTTSService(
|
|
api_key=os.environ["CARTESIA_API_KEY"],
|
|
settings=CartesiaTTSService.Settings(
|
|
voice="00967b2f-88a6-4a31-8153-110a92134b9f",
|
|
),
|
|
)
|
|
|
|
llm = GoogleLLMService(
|
|
api_key=os.environ["GOOGLE_API_KEY"],
|
|
settings=GoogleLLMService.Settings(
|
|
system_instruction="You are a helpful assistant. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Be succinct and respond to what the user said in a creative and helpful way.",
|
|
),
|
|
)
|
|
|
|
context = LLMContext()
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
context,
|
|
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
|
)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(), # Transport user input
|
|
stt, # STT
|
|
user_aggregator, # User responses
|
|
llm, # LLM
|
|
tts, # TTS
|
|
transport.output(), # Transport bot output
|
|
assistant_aggregator, # Assistant spoken responses
|
|
]
|
|
)
|
|
|
|
worker = PipelineWorker(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
)
|
|
|
|
@transport.event_handler("on_client_connected")
|
|
async def on_client_connected(transport, client):
|
|
logger.info(f"Client connected")
|
|
# Kick off the conversation.
|
|
context.add_message(
|
|
{
|
|
"role": "developer",
|
|
"content": "Start by saying 'Hello' and then a short greeting.",
|
|
}
|
|
)
|
|
await worker.queue_frames([LLMRunFrame()])
|
|
|
|
@transport.event_handler("on_client_disconnected")
|
|
async def on_client_disconnected(transport, client):
|
|
logger.info(f"Client disconnected")
|
|
await worker.cancel()
|
|
|
|
runner = PipelineRunner()
|
|
|
|
await runner.run(worker)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|