133 lines
4.6 KiB
Python
133 lines
4.6 KiB
Python
import asyncio
|
|
import aiohttp
|
|
import os
|
|
import sys
|
|
|
|
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
|
|
|
|
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
|
from pipecat.services.ai_services import AIService
|
|
from pipecat.services.cartesia import CartesiaTTSService
|
|
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
|
from pipecat.services.openai import OpenAILLMService
|
|
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
|
|
|
from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
|
|
from runner import configure
|
|
from loguru import logger
|
|
from dotenv import load_dotenv
|
|
|
|
from simli import SimliConfig
|
|
from pipecat.services.simli import SimliVideoService
|
|
|
|
load_dotenv(override=True)
|
|
|
|
logger.remove(0)
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
|
|
async def main():
|
|
async with aiohttp.ClientSession() as session:
|
|
_, token = await configure(session)
|
|
print("Creating room")
|
|
aiohttp_session = aiohttp.ClientSession()
|
|
daily_helper = DailyRESTHelper(
|
|
daily_api_key=os.getenv("DAILY_API_KEY", ""),
|
|
daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
|
|
aiohttp_session=aiohttp_session,
|
|
)
|
|
room = await daily_helper.create_room(DailyRoomParams())
|
|
expiry_time: float = 60 * 60
|
|
|
|
token = await daily_helper.get_token(room.url, expiry_time)
|
|
print("Room created ", room.url)
|
|
transport = DailyTransport(
|
|
room.url,
|
|
token,
|
|
"Chatbot",
|
|
DailyParams(
|
|
audio_out_enabled=True,
|
|
camera_out_enabled=True,
|
|
camera_out_width=512,
|
|
camera_out_height=512,
|
|
vad_enabled=True,
|
|
vad_analyzer=SileroVADAnalyzer(),
|
|
transcription_enabled=True,
|
|
#
|
|
# Spanish
|
|
#
|
|
# transcription_settings=DailyTranscriptionSettings(
|
|
# language="es",
|
|
# tier="nova",
|
|
# model="2-general"
|
|
# )
|
|
),
|
|
)
|
|
|
|
# tts = ElevenLabsTTSService(
|
|
# api_key=os.getenv("ELEVENLABS_API_KEY"),
|
|
# voice_id="pNInz6obpgDQGcFmaJgB",
|
|
# )
|
|
|
|
tts = CartesiaTTSService(
|
|
api_key=os.getenv("CARTESIA_API_KEY"),
|
|
voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab",
|
|
)
|
|
|
|
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
|
|
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
#
|
|
# English
|
|
#
|
|
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
|
#
|
|
# Spanish
|
|
#
|
|
# "content": "Eres Chatbot, un amigable y útil robot. Tu objetivo es demostrar tus capacidades de una manera breve. Tus respuestas se convertiran a audio así que nunca no debes incluir caracteres especiales. Contesta a lo que el usuario pregunte de una manera creativa, útil y breve. Empieza por presentarte a ti mismo.",
|
|
},
|
|
]
|
|
simli_ai = SimliVideoService(
|
|
SimliConfig(os.getenv("SIMLI_API_KEY"), os.getenv("SIMLI_FACE_ID"))
|
|
)
|
|
context = OpenAILLMContext(messages)
|
|
context_aggregator = llm.create_context_aggregator(context)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
context_aggregator.user(),
|
|
llm,
|
|
tts,
|
|
simli_ai,
|
|
transport.output(),
|
|
context_aggregator.assistant(),
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
PipelineParams(
|
|
allow_interruptions=True,
|
|
enable_metrics=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)])
|
|
|
|
runner = PipelineRunner()
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main())
|