66 lines
2.6 KiB
Python
66 lines
2.6 KiB
Python
import asyncio
|
|
import aiohttp
|
|
import os
|
|
from dailyai.conversation_wrappers import InterruptibleConversationWrapper
|
|
from dailyai.pipeline.aggregators import LLMAssistantContextAggregator, LLMUserContextAggregator
|
|
|
|
from dailyai.pipeline.frames import StartStreamQueueFrame, TextQueueFrame
|
|
from dailyai.pipeline.pipeline import Pipeline
|
|
from dailyai.services.ai_services import FrameLogger
|
|
from dailyai.services.daily_transport_service import DailyTransportService
|
|
from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
|
|
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
|
|
|
|
from examples.foundational.support.runner import configure
|
|
|
|
|
|
async def main(room_url: str, token):
|
|
async with aiohttp.ClientSession() as session:
|
|
transport = DailyTransportService(
|
|
room_url,
|
|
token,
|
|
"Respond bot",
|
|
duration_minutes=5,
|
|
start_transcription=True,
|
|
mic_enabled=True,
|
|
mic_sample_rate=16000,
|
|
camera_enabled=False,
|
|
)
|
|
|
|
llm = AzureLLMService(
|
|
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
|
|
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
|
|
model=os.getenv("AZURE_CHATGPT_MODEL"))
|
|
tts = AzureTTSService(
|
|
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
|
|
region=os.getenv("AZURE_SPEECH_REGION"))
|
|
|
|
pipeline = Pipeline([FrameLogger(), llm, FrameLogger(), tts])
|
|
|
|
@transport.event_handler("on_first_other_participant_joined")
|
|
async def on_first_other_participant_joined(transport):
|
|
await tts.say("Hi, I'm listening!", transport.send_queue)
|
|
|
|
async def run_conversation():
|
|
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. Respond to what the user said in a creative and helpful way."},
|
|
]
|
|
|
|
await transport.run_interruptible_pipeline(
|
|
pipeline,
|
|
post_processor=LLMAssistantContextAggregator(
|
|
messages, transport._my_participant_id
|
|
),
|
|
pre_processor=LLMUserContextAggregator(
|
|
messages, transport._my_participant_id, complete_sentences=False
|
|
),
|
|
)
|
|
|
|
transport.transcription_settings["extra"]["punctuate"] = False
|
|
await asyncio.gather(transport.run(), run_conversation())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
(url, token) = configure()
|
|
asyncio.run(main(url, token))
|