Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt (#1534)

Co-authored-by: Filipi Fuchter <filipi@daily.co>
This commit is contained in:
Mark Backman
2025-04-11 19:44:16 -04:00
committed by GitHub
parent 8186219879
commit f6accbd510
120 changed files with 7989 additions and 7179 deletions

View File

@@ -4,14 +4,10 @@
# 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 simli import SimliConfig
from pipecat.audio.vad.silero import SileroVADAnalyzer
@@ -20,83 +16,97 @@ 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.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.simli.video import SimliVideoService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def run_bot(webrtc_connection: SmallWebRTCConnection):
logger.info(f"Starting bot")
async def main():
async with aiohttp.ClientSession() as session:
room, token = await configure(session)
transport = DailyTransport(
room,
token,
"Simli",
DailyParams(
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_width=512,
camera_out_height=512,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
transcription_enabled=True,
),
)
transport = SmallWebRTCTransport(
webrtc_connection=webrtc_connection,
params=TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
camera_out_enabled=True,
camera_out_width=512,
camera_out_height=512,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab",
)
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
simli_ai = SimliVideoService(
SimliConfig(os.getenv("SIMLI_API_KEY"), os.getenv("SIMLI_FACE_ID"))
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab",
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
simli_ai = SimliVideoService(
SimliConfig(os.getenv("SIMLI_API_KEY"), os.getenv("SIMLI_FACE_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.",
},
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
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(),
stt,
context_aggregator.user(),
llm,
tts,
simli_ai,
transport.output(),
context_aggregator.assistant(),
]
)
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
),
)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
simli_ai,
transport.output(),
context_aggregator.assistant(),
]
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Start conversation - empty prompt to let LLM follow system instructions
await task.queue_frames([context_aggregator.user().get_context_frame()])
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
),
)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
runner = PipelineRunner()
await runner.run(task)
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())
from run import main
main()