148 lines
5.4 KiB
Python
148 lines
5.4 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import os
|
||
|
||
import aiohttp
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.pipeline.pipeline import Pipeline
|
||
from pipecat.pipeline.runner import PipelineRunner
|
||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_transport import TransportParams
|
||
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
|
||
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
|
||
from pipecat.transports.services.daily import DailyTransportMessageFrame
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
async def run_bot(webrtc_connection: SmallWebRTCConnection):
|
||
logger.info(f"Starting bot")
|
||
|
||
transport = SmallWebRTCTransport(
|
||
webrtc_connection=webrtc_connection,
|
||
params=TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
vad_audio_passthrough=True,
|
||
),
|
||
)
|
||
|
||
# Create an HTTP session
|
||
async with aiohttp.ClientSession() as session:
|
||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
|
||
tts = DeepgramTTSService(
|
||
aiohttp_session=session,
|
||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||
voice="aura-asteria-en",
|
||
base_url="http://0.0.0.0:8080/v1/speak",
|
||
)
|
||
|
||
llm = OpenAILLMService(
|
||
# To use OpenAI
|
||
# api_key=os.getenv("OPENAI_API_KEY"),
|
||
# model="gpt-4o"
|
||
# Or, to use a local vLLM (or similar) api server
|
||
model="meta-llama/Meta-Llama-3-8B-Instruct",
|
||
base_url="http://0.0.0.0:8000/v1",
|
||
)
|
||
|
||
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.",
|
||
},
|
||
]
|
||
|
||
context = OpenAILLMContext(messages)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt, # STT
|
||
context_aggregator.user(),
|
||
llm, # LLM
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(),
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
allow_interruptions=True,
|
||
enable_metrics=True,
|
||
),
|
||
)
|
||
|
||
# When the first participant joins, the bot should introduce itself.
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# Kick off the conversation.
|
||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||
|
||
# Handle "latency-ping" messages. The client will send app messages that look like
|
||
# this:
|
||
# { "latency-ping": { ts: <client-side timestamp> }}
|
||
#
|
||
# We want to send an immediate pong back to the client from this handler function.
|
||
# Also, we will push a frame into the top of the pipeline and send it after the
|
||
#
|
||
@transport.event_handler("on_app_message")
|
||
async def on_app_message(transport, message, sender):
|
||
try:
|
||
if "latency-ping" in message:
|
||
logger.debug(f"Received latency ping app message: {message}")
|
||
ts = message["latency-ping"]["ts"]
|
||
# Send immediately
|
||
transport.output().send_message(
|
||
DailyTransportMessageFrame(
|
||
message={"latency-pong-msg-handler": {"ts": ts}}, participant_id=sender
|
||
)
|
||
)
|
||
# And push to the pipeline for the Daily transport.output to send
|
||
await task.queue_frame(
|
||
DailyTransportMessageFrame(
|
||
message={"latency-pong-pipeline-delivery": {"ts": ts}},
|
||
participant_id=sender,
|
||
)
|
||
)
|
||
except Exception as e:
|
||
logger.debug(f"message handling error: {e} - {message}")
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info(f"Client disconnected")
|
||
|
||
@transport.event_handler("on_client_closed")
|
||
async def on_client_closed(transport, client):
|
||
logger.info(f"Client closed connection")
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=False)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from run import main
|
||
|
||
main()
|