Files
pipecat/examples/websocket-server/bot.py
2024-06-12 10:29:22 -07:00

94 lines
3.0 KiB
Python

#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
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 PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMAssistantResponseAggregator,
LLMUserResponseAggregator
)
from pipecat.services.deepgram import DeepgramSTTService
from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.network.websocket_server import WebsocketServerParams, WebsocketServerTransport
from pipecat.vad.silero import SileroVADAnalyzer
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():
async with aiohttp.ClientSession() as session:
transport = WebsocketServerTransport(
params=WebsocketServerParams(
audio_out_enabled=True,
add_wav_header=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True
)
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = ElevenLabsTTSService(
aiohttp_session=session,
api_key=os.getenv("ELEVENLABS_API_KEY"),
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
)
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 and helpful way.",
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([
transport.input(), # Websocket input from client
stt, # Speech-To-Text
tma_in, # User responses
llm, # LLM
tts, # Text-To-Speech
transport.output(), # Websocket output to client
tma_out # LLM responses
])
task = PipelineTask(pipeline)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
# Kick off the conversation.
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())