96 lines
3.2 KiB
Python
96 lines
3.2 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 LLMMessagesFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.processors.aggregators.llm_response import (
|
|
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
|
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
|
from pipecat.services.anthropic import AnthropicLLMService
|
|
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
|
from pipecat.vad.silero import SileroVADAnalyzer
|
|
|
|
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: str, token):
|
|
async with aiohttp.ClientSession() as session:
|
|
transport = DailyTransport(
|
|
room_url,
|
|
token,
|
|
"Respond bot",
|
|
DailyParams(
|
|
audio_out_enabled=True,
|
|
transcription_enabled=True,
|
|
vad_enabled=True,
|
|
vad_analyzer=SileroVADAnalyzer()
|
|
)
|
|
)
|
|
|
|
tts = ElevenLabsTTSService(
|
|
aiohttp_session=session,
|
|
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
|
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
|
)
|
|
|
|
llm = AnthropicLLMService(
|
|
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
|
model="claude-3-opus-20240229")
|
|
|
|
# todo: think more about how to handle system prompts in a more general way. OpenAI,
|
|
# Google, and Anthropic all have slightly different approaches to providing a system
|
|
# prompt.
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
"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, helpful, and brief way. Say hello.",
|
|
},
|
|
]
|
|
|
|
tma_in = LLMUserResponseAggregator(messages)
|
|
tma_out = LLMAssistantResponseAggregator(messages)
|
|
|
|
pipeline = Pipeline([
|
|
transport.input(), # Transport user input
|
|
tma_in, # User responses
|
|
llm, # LLM
|
|
tts, # TTS
|
|
transport.output(), # Transport bot output
|
|
tma_out # Assistant spoken responses
|
|
])
|
|
|
|
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
|
|
|
@transport.event_handler("on_first_participant_joined")
|
|
async def on_first_participant_joined(transport, participant):
|
|
transport.capture_participant_transcription(participant["id"])
|
|
# Kick off the conversation.
|
|
await task.queue_frames([LLMMessagesFrame(messages)])
|
|
|
|
runner = PipelineRunner()
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
(url, token) = configure()
|
|
asyncio.run(main(url, token))
|