104 lines
3.2 KiB
Python
104 lines
3.2 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
import asyncio
|
|
import os
|
|
import sys
|
|
|
|
from dotenv import load_dotenv
|
|
from loguru import logger
|
|
|
|
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
|
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
from pipecat.audio.vad.vad_analyzer import VADParams
|
|
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,
|
|
LLMUserAggregatorParams,
|
|
)
|
|
from pipecat.services.cartesia.tts import CartesiaTTSService
|
|
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
from pipecat.services.openai.llm import OpenAILLMService
|
|
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
|
|
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
|
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
|
|
|
load_dotenv(override=True)
|
|
|
|
logger.remove(0)
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
|
|
async def main():
|
|
transport = LocalAudioTransport(
|
|
LocalAudioTransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
)
|
|
)
|
|
|
|
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
|
|
|
tts = CartesiaTTSService(
|
|
api_key=os.getenv("CARTESIA_API_KEY"),
|
|
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
|
)
|
|
|
|
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
|
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
|
},
|
|
]
|
|
|
|
context = LLMContext(messages)
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
context,
|
|
user_params=LLMUserAggregatorParams(
|
|
user_turn_strategies=UserTurnStrategies(
|
|
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
|
),
|
|
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
|
),
|
|
)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(), # Transport user input
|
|
stt,
|
|
user_aggregator, # User responses
|
|
llm, # LLM
|
|
tts, # TTS
|
|
transport.output(), # Transport bot output
|
|
assistant_aggregator, # Assistant spoken responses
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
)
|
|
|
|
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
|
await task.queue_frames([LLMRunFrame()])
|
|
|
|
runner = PipelineRunner()
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|