102 lines
3.2 KiB
Python
102 lines
3.2 KiB
Python
import asyncio
|
|
import os
|
|
import sys
|
|
import argparse
|
|
|
|
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.frames.frames import LLMMessagesFrame, EndFrame
|
|
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
|
from pipecat.services.openai import OpenAILLMService
|
|
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
|
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
|
|
|
from loguru import logger
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv(override=True)
|
|
|
|
logger.remove(0)
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
daily_api_key = os.getenv("DAILY_API_KEY", "")
|
|
daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
|
|
|
|
|
|
async def main(room_url: str, token: str):
|
|
transport = DailyTransport(
|
|
room_url,
|
|
token,
|
|
"Chatbot",
|
|
DailyParams(
|
|
api_url=daily_api_url,
|
|
api_key=daily_api_key,
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
camera_out_enabled=False,
|
|
vad_enabled=True,
|
|
vad_analyzer=SileroVADAnalyzer(),
|
|
transcription_enabled=True,
|
|
),
|
|
)
|
|
|
|
tts = ElevenLabsTTSService(
|
|
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
|
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
|
|
)
|
|
|
|
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
|
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
"content": "You are Chatbot, a friendly, helpful robot. Your output will be converted to audio so don't include special characters other than '!' or '?' in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by saying hello.",
|
|
},
|
|
]
|
|
|
|
context = OpenAILLMContext(messages)
|
|
context_aggregator = llm.create_context_aggregator(context)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
context_aggregator.user(),
|
|
llm,
|
|
tts,
|
|
transport.output(),
|
|
context_aggregator.assistant(),
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
|
|
|
@transport.event_handler("on_first_participant_joined")
|
|
async def on_first_participant_joined(transport, participant):
|
|
await transport.capture_participant_transcription(participant["id"])
|
|
await task.queue_frames([LLMMessagesFrame(messages)])
|
|
|
|
@transport.event_handler("on_participant_left")
|
|
async def on_participant_left(transport, participant, reason):
|
|
await task.queue_frame(EndFrame())
|
|
|
|
@transport.event_handler("on_call_state_updated")
|
|
async def on_call_state_updated(transport, state):
|
|
if state == "left":
|
|
await task.queue_frame(EndFrame())
|
|
|
|
runner = PipelineRunner()
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser(description="Pipecat Bot")
|
|
parser.add_argument("-u", type=str, help="Room URL")
|
|
parser.add_argument("-t", type=str, help="Token")
|
|
config = parser.parse_args()
|
|
|
|
asyncio.run(main(config.u, config.t))
|