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
@@ -4,17 +4,13 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import glob
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from runner import configure
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -25,19 +21,21 @@ 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.google.llm import GoogleLLMService
|
||||
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")
|
||||
|
||||
video_participant_id = None
|
||||
|
||||
|
||||
BASE_FILENAME = "/tmp/pipecat_conversation_"
|
||||
tts = None
|
||||
webrtc_peer_id = None
|
||||
|
||||
|
||||
async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
|
||||
@@ -54,8 +52,11 @@ async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context
|
||||
|
||||
async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
|
||||
question = arguments["question"]
|
||||
logger.debug(f"Requesting image with user_id={webrtc_peer_id}, question={question}")
|
||||
|
||||
# Request the image frame
|
||||
await llm.request_image_frame(
|
||||
user_id=video_participant_id,
|
||||
user_id=webrtc_peer_id,
|
||||
function_name=function_name,
|
||||
tool_call_id=tool_call_id,
|
||||
text_content=question,
|
||||
@@ -220,75 +221,87 @@ tools = [
|
||||
]
|
||||
|
||||
|
||||
async def main():
|
||||
global tts
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, token) = await configure(session)
|
||||
async def run_bot(webrtc_connection: SmallWebRTCConnection):
|
||||
global tts, webrtc_peer_id
|
||||
webrtc_peer_id = webrtc_connection.pc_id
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
|
||||
),
|
||||
)
|
||||
logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
transport = SmallWebRTCTransport(
|
||||
webrtc_connection=webrtc_connection,
|
||||
params=TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
camera_in_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
|
||||
vad_audio_passthrough=True,
|
||||
),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# you can either register a single function for all function calls, or specific functions
|
||||
# llm.register_function(None, fetch_weather_from_api)
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
llm.register_function("save_conversation", save_conversation)
|
||||
llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
|
||||
llm.register_function("load_conversation", load_conversation)
|
||||
llm.register_function("get_image", get_image)
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
llm = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
context_aggregator.user(),
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
# you can either register a single function for all function calls, or specific functions
|
||||
# llm.register_function(None, fetch_weather_from_api)
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
llm.register_function("save_conversation", save_conversation)
|
||||
llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
|
||||
llm.register_function("load_conversation", load_conversation)
|
||||
llm.register_function("get_image", get_image)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
# report_only_initial_ttfb=True,
|
||||
),
|
||||
)
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
global video_participant_id
|
||||
video_participant_id = participant["id"]
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
await transport.capture_participant_video(video_participant_id, framerate=0)
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(),
|
||||
llm, # LLM
|
||||
tts,
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
# report_only_initial_ttfb=True,
|
||||
),
|
||||
)
|
||||
|
||||
await runner.run(task)
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@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__":
|
||||
asyncio.run(main())
|
||||
from run import main
|
||||
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user