Files
pipecat/examples/foundational/02-llm-say-one-thing.py
2024-07-17 14:13:52 -07:00

75 lines
2.2 KiB
Python

#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import aiohttp
import os
import sys
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
# from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from runner import configure
from loguru import logger
from dotenv import load_dotenv
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def main(room_url):
async with aiohttp.ClientSession() as session:
transport = DailyTransport(
room_url,
None,
"Say One Thing From an LLM",
DailyParams(audio_out_enabled=True))
# tts = ElevenLabsTTSService(
# aiohttp_session=session,
# 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")
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
)
messages = [
{
"role": "system",
"content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
}]
runner = PipelineRunner()
task = PipelineTask(Pipeline([llm, tts, transport.output()]))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
# await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
await task.queue_frames([LLMMessagesFrame(messages)])
await runner.run(task)
if __name__ == "__main__":
(url, token) = configure()
asyncio.run(main(url))