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
@@ -6,14 +6,11 @@
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
|
||||
import aiohttp
|
||||
import google.ai.generativelanguage as glm
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from runner import configure
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import (
|
||||
@@ -47,12 +44,12 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.google.llm import GoogleLLMContext, GoogleLLMService
|
||||
from pipecat.sync.base_notifier import BaseNotifier
|
||||
from pipecat.sync.event_notifier import EventNotifier
|
||||
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")
|
||||
|
||||
TRANSCRIBER_MODEL = "gemini-2.0-flash-001"
|
||||
CLASSIFIER_MODEL = "gemini-2.0-flash-001"
|
||||
@@ -626,149 +623,155 @@ class OutputGate(FrameProcessor):
|
||||
break
|
||||
|
||||
|
||||
async def main():
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, _) = await configure(session)
|
||||
async def run_bot(webrtc_connection: SmallWebRTCConnection):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
None,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
vad_audio_passthrough=True,
|
||||
),
|
||||
)
|
||||
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,
|
||||
),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
# This is the LLM that will transcribe user speech.
|
||||
tx_llm = GoogleLLMService(
|
||||
name="Transcriber",
|
||||
model=TRANSCRIBER_MODEL,
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
temperature=0.0,
|
||||
system_instruction=transcriber_system_instruction,
|
||||
)
|
||||
# This is the LLM that will transcribe user speech.
|
||||
tx_llm = GoogleLLMService(
|
||||
name="Transcriber",
|
||||
model=TRANSCRIBER_MODEL,
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
temperature=0.0,
|
||||
system_instruction=transcriber_system_instruction,
|
||||
)
|
||||
|
||||
# This is the LLM that will classify user speech as complete or incomplete.
|
||||
classifier_llm = GoogleLLMService(
|
||||
name="Classifier",
|
||||
model=CLASSIFIER_MODEL,
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
temperature=0.0,
|
||||
system_instruction=classifier_system_instruction,
|
||||
)
|
||||
# This is the LLM that will classify user speech as complete or incomplete.
|
||||
classifier_llm = GoogleLLMService(
|
||||
name="Classifier",
|
||||
model=CLASSIFIER_MODEL,
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
temperature=0.0,
|
||||
system_instruction=classifier_system_instruction,
|
||||
)
|
||||
|
||||
# This is the regular LLM that responds conversationally.
|
||||
conversation_llm = GoogleLLMService(
|
||||
name="Conversation",
|
||||
model=CONVERSATION_MODEL,
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
system_instruction=conversation_system_instruction,
|
||||
)
|
||||
# This is the regular LLM that responds conversationally.
|
||||
conversation_llm = GoogleLLMService(
|
||||
name="Conversation",
|
||||
model=CONVERSATION_MODEL,
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
system_instruction=conversation_system_instruction,
|
||||
)
|
||||
|
||||
context = OpenAILLMContext()
|
||||
context_aggregator = conversation_llm.create_context_aggregator(context)
|
||||
context = OpenAILLMContext()
|
||||
context_aggregator = conversation_llm.create_context_aggregator(context)
|
||||
|
||||
# This is a notifier that we use to synchronize the two LLMs.
|
||||
notifier = EventNotifier()
|
||||
# This is a notifier that we use to synchronize the two LLMs.
|
||||
notifier = EventNotifier()
|
||||
|
||||
# This turns the LLM context into an inference request to classify the user's speech
|
||||
# as complete or incomplete.
|
||||
# statement_judge_context_filter = StatementJudgeAudioContextAccumulator(notifier=notifier)
|
||||
# This turns the LLM context into an inference request to classify the user's speech
|
||||
# as complete or incomplete.
|
||||
# statement_judge_context_filter = StatementJudgeAudioContextAccumulator(notifier=notifier)
|
||||
|
||||
audio_accumulater = AudioAccumulator()
|
||||
# This sends a UserStoppedSpeakingFrame and triggers the notifier event
|
||||
completeness_check = CompletenessCheck(
|
||||
notifier=notifier, audio_accumulator=audio_accumulater
|
||||
)
|
||||
audio_accumulater = AudioAccumulator()
|
||||
# This sends a UserStoppedSpeakingFrame and triggers the notifier event
|
||||
completeness_check = CompletenessCheck(notifier=notifier, audio_accumulator=audio_accumulater)
|
||||
|
||||
async def block_user_stopped_speaking(frame):
|
||||
return not isinstance(frame, UserStoppedSpeakingFrame)
|
||||
async def block_user_stopped_speaking(frame):
|
||||
return not isinstance(frame, UserStoppedSpeakingFrame)
|
||||
|
||||
conversation_audio_context_assembler = ConversationAudioContextAssembler(context=context)
|
||||
conversation_audio_context_assembler = ConversationAudioContextAssembler(context=context)
|
||||
|
||||
llm_aggregator_buffer = LLMAggregatorBuffer()
|
||||
llm_aggregator_buffer = LLMAggregatorBuffer()
|
||||
|
||||
bot_output_gate = OutputGate(
|
||||
notifier=notifier, context=context, llm_transcription_buffer=llm_aggregator_buffer
|
||||
)
|
||||
bot_output_gate = OutputGate(
|
||||
notifier=notifier, context=context, llm_transcription_buffer=llm_aggregator_buffer
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
audio_accumulater,
|
||||
ParallelPipeline(
|
||||
[
|
||||
# Pass everything except UserStoppedSpeaking to the elements after
|
||||
# this ParallelPipeline
|
||||
FunctionFilter(filter=block_user_stopped_speaking),
|
||||
],
|
||||
[
|
||||
ParallelPipeline(
|
||||
[
|
||||
classifier_llm,
|
||||
completeness_check,
|
||||
],
|
||||
[
|
||||
tx_llm,
|
||||
llm_aggregator_buffer,
|
||||
],
|
||||
)
|
||||
],
|
||||
[
|
||||
conversation_audio_context_assembler,
|
||||
conversation_llm,
|
||||
bot_output_gate, # buffer output until notified, then flush frames and update context
|
||||
# TempPrinter(),
|
||||
],
|
||||
),
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
],
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=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):
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_app_message")
|
||||
async def on_app_message(transport, message, sender):
|
||||
logger.debug(f"Received app message: {message} - {sender}")
|
||||
if "message" not in message:
|
||||
return
|
||||
|
||||
await task.queue_frames(
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
audio_accumulater,
|
||||
ParallelPipeline(
|
||||
[
|
||||
UserStartedSpeakingFrame(),
|
||||
TranscriptionFrame(
|
||||
user_id=sender, timestamp=time.time(), text=message["message"]
|
||||
),
|
||||
UserStoppedSpeakingFrame(),
|
||||
]
|
||||
)
|
||||
# Pass everything except UserStoppedSpeaking to the elements after
|
||||
# this ParallelPipeline
|
||||
FunctionFilter(filter=block_user_stopped_speaking),
|
||||
],
|
||||
[
|
||||
ParallelPipeline(
|
||||
[
|
||||
classifier_llm,
|
||||
completeness_check,
|
||||
],
|
||||
[
|
||||
tx_llm,
|
||||
llm_aggregator_buffer,
|
||||
],
|
||||
)
|
||||
],
|
||||
[
|
||||
conversation_audio_context_assembler,
|
||||
conversation_llm,
|
||||
bot_output_gate, # buffer output until notified, then flush frames and update context
|
||||
# TempPrinter(),
|
||||
],
|
||||
),
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
],
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
await runner.run(task)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
@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_app_message")
|
||||
async def on_app_message(transport, message):
|
||||
logger.debug(f"Received app message: {message}")
|
||||
if "message" not in message:
|
||||
return
|
||||
|
||||
await task.queue_frames(
|
||||
[
|
||||
UserStartedSpeakingFrame(),
|
||||
TranscriptionFrame(user_id="", timestamp=time.time(), text=message["message"]),
|
||||
UserStoppedSpeakingFrame(),
|
||||
]
|
||||
)
|
||||
|
||||
@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