150 lines
4.9 KiB
Python
150 lines
4.9 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import os
|
||
|
||
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, TTSTextFrame
|
||
from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
|
||
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.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
|
||
from pipecat.runner.types import RunnerArguments
|
||
from pipecat.runner.utils import create_transport
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.inworld.tts import InworldTTSService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_output import BaseOutputTransport
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.daily.transport import DailyParams
|
||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
transport_params = {
|
||
"daily": lambda: DailyParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||
logger.info("Starting bot")
|
||
|
||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
|
||
tts = InworldTTSService(
|
||
api_key=os.getenv("INWORLD_API_KEY", ""),
|
||
voice_id="Ashley",
|
||
model="inworld-tts-1",
|
||
temperature=1.1,
|
||
)
|
||
|
||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
|
||
messages = [
|
||
{
|
||
"role": "system",
|
||
"content": "You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
|
||
},
|
||
]
|
||
|
||
context = LLMContext(messages)
|
||
context_aggregator = LLMContextAggregatorPair(
|
||
context,
|
||
user_params=LLMUserAggregatorParams(
|
||
user_turn_strategies=UserTurnStrategies(
|
||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||
),
|
||
),
|
||
)
|
||
|
||
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(),
|
||
rtvi,
|
||
stt,
|
||
context_aggregator.user(),
|
||
llm,
|
||
tts,
|
||
transport.output(),
|
||
context_aggregator.assistant(),
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
observers=[
|
||
RTVIObserver(rtvi),
|
||
DebugLogObserver(
|
||
frame_types={
|
||
TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
|
||
}
|
||
),
|
||
],
|
||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info("Client connected")
|
||
# Kick off the conversation.
|
||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||
await task.queue_frames([LLMRunFrame()])
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info("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()
|