# # Copyright (c) 2024, Daily # # SPDX-License-Identifier: BSD 2-Clause License # import asyncio import os import sys import aiohttp from dotenv import load_dotenv from loguru import logger from runner import configure 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.services.ai_services import OpenAILLMContext from pipecat.services.cartesia import CartesiaTTSService from pipecat.services.together import TogetherLLMService from pipecat.transports.services.daily import DailyParams, DailyTransport from pipecat.vad.silero import SileroVADAnalyzer load_dotenv(override=True) logger.remove(0) logger.add(sys.stderr, level="DEBUG") async def main(): async with aiohttp.ClientSession() as session: (room_url, token) = await configure(session) transport = DailyTransport( room_url, token, "Respond bot", DailyParams( audio_out_enabled=True, transcription_enabled=True, vad_enabled=True, vad_analyzer=SileroVADAnalyzer(), ), ) tts = CartesiaTTSService( api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady ) llm = TogetherLLMService( api_key=os.getenv("TOGETHER_API_KEY"), model=os.getenv("TOGETHER_MODEL"), params=TogetherLLMService.InputParams( temperature=1.0, top_p=0.9, top_k=40, extra={ "frequency_penalty": 2.0, "presence_penalty": 0.0, }, ), ) 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 in plain language. Respond to what the user said in a creative and helpful way.", }, ] context = OpenAILLMContext(messages) context_aggregator = llm.create_context_aggregator(context) user_aggregator = context_aggregator.user() assistant_aggregator = context_aggregator.assistant() pipeline = Pipeline( [ transport.input(), # Transport user input user_aggregator, # User responses llm, # LLM tts, # TTS transport.output(), # Transport bot output assistant_aggregator, # Assistant spoken responses ] ) task = PipelineTask( pipeline, PipelineParams( allow_interruptions=True, enable_metrics=True, enable_usage_metrics=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__": asyncio.run(main())