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
@@ -4,14 +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 pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import TextFrame
|
||||
@@ -28,142 +24,146 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
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")
|
||||
|
||||
async def run_bot(webrtc_connection: SmallWebRTCConnection):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
async def main():
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, _) = await configure(session)
|
||||
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,
|
||||
),
|
||||
)
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
None,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
vad_audio_passthrough=True,
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
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 be used to detect if the user has finished a
|
||||
# statement. This doesn't really need to be an LLM, we could use NLP
|
||||
# libraries for that, but it was easier as an example because we
|
||||
# leverage the context aggregators.
|
||||
statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
statement_messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "Determine if the user's statement is a complete sentence or question, ending in a natural pause or punctuation. Return 'YES' if it is complete and 'NO' if it seems to leave a thought unfinished.",
|
||||
},
|
||||
]
|
||||
|
||||
statement_context = OpenAILLMContext(statement_messages)
|
||||
statement_context_aggregator = statement_llm.create_context_aggregator(statement_context)
|
||||
|
||||
# This is the regular LLM.
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
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)
|
||||
|
||||
# We have instructed the LLM to return 'YES' if it thinks the user
|
||||
# completed a sentence. So, if it's 'YES' we will return true in this
|
||||
# predicate which will wake up the notifier.
|
||||
async def wake_check_filter(frame):
|
||||
return frame.text == "YES"
|
||||
|
||||
# This is a notifier that we use to synchronize the two LLMs.
|
||||
notifier = EventNotifier()
|
||||
|
||||
# This a filter that will wake up the notifier if the given predicate
|
||||
# (wake_check_filter) returns true.
|
||||
completness_check = WakeNotifierFilter(notifier, types=(TextFrame,), filter=wake_check_filter)
|
||||
|
||||
# This processor keeps the last context and will let it through once the
|
||||
# notifier is woken up. We start with the gate open because we send an
|
||||
# initial context frame to start the conversation.
|
||||
gated_context_aggregator = GatedOpenAILLMContextAggregator(notifier=notifier, start_open=True)
|
||||
|
||||
# Notify if the user hasn't said anything.
|
||||
async def user_idle_notifier(frame):
|
||||
await notifier.notify()
|
||||
|
||||
# Sometimes the LLM will fail detecting if a user has completed a
|
||||
# sentence, this will wake up the notifier if that happens.
|
||||
user_idle = UserIdleProcessor(callback=user_idle_notifier, timeout=3.0)
|
||||
|
||||
# The ParallePipeline input are the user transcripts. We have two
|
||||
# contexts. The first one will be used to determine if the user finished
|
||||
# a statement and if so the notifier will be woken up. The second
|
||||
# context is simply the regular context but it's gated waiting for the
|
||||
# notifier to be woken up.
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
ParallelPipeline(
|
||||
[
|
||||
statement_context_aggregator.user(),
|
||||
statement_llm,
|
||||
completness_check,
|
||||
NullFilter(),
|
||||
],
|
||||
[context_aggregator.user(), gated_context_aggregator, llm],
|
||||
),
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
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 be used to detect if the user has finished a
|
||||
# statement. This doesn't really need to be an LLM, we could use NLP
|
||||
# libraries for that, but it was easier as an example because we
|
||||
# leverage the context aggregators.
|
||||
statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
statement_messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "Determine if the user's statement is a complete sentence or question, ending in a natural pause or punctuation. Return 'YES' if it is complete and 'NO' if it seems to leave a thought unfinished.",
|
||||
},
|
||||
user_idle,
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
statement_context = OpenAILLMContext(statement_messages)
|
||||
statement_context_aggregator = statement_llm.create_context_aggregator(statement_context)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
report_only_initial_ttfb=True,
|
||||
),
|
||||
)
|
||||
|
||||
# This is the regular LLM.
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
@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()])
|
||||
|
||||
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.",
|
||||
},
|
||||
]
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
@transport.event_handler("on_client_closed")
|
||||
async def on_client_closed(transport, client):
|
||||
logger.info(f"Client closed connection")
|
||||
await task.cancel()
|
||||
|
||||
# We have instructed the LLM to return 'YES' if it thinks the user
|
||||
# completed a sentence. So, if it's 'YES' we will return true in this
|
||||
# predicate which will wake up the notifier.
|
||||
async def wake_check_filter(frame):
|
||||
return frame.text == "YES"
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
# This is a notifier that we use to synchronize the two LLMs.
|
||||
notifier = EventNotifier()
|
||||
|
||||
# This a filter that will wake up the notifier if the given predicate
|
||||
# (wake_check_filter) returns true.
|
||||
completness_check = WakeNotifierFilter(
|
||||
notifier, types=(TextFrame,), filter=wake_check_filter
|
||||
)
|
||||
|
||||
# This processor keeps the last context and will let it through once the
|
||||
# notifier is woken up. We start with the gate open because we send an
|
||||
# initial context frame to start the conversation.
|
||||
gated_context_aggregator = GatedOpenAILLMContextAggregator(
|
||||
notifier=notifier, start_open=True
|
||||
)
|
||||
|
||||
# Notify if the user hasn't said anything.
|
||||
async def user_idle_notifier(frame):
|
||||
await notifier.notify()
|
||||
|
||||
# Sometimes the LLM will fail detecting if a user has completed a
|
||||
# sentence, this will wake up the notifier if that happens.
|
||||
user_idle = UserIdleProcessor(callback=user_idle_notifier, timeout=3.0)
|
||||
|
||||
# The ParallePipeline input are the user transcripts. We have two
|
||||
# contexts. The first one will be used to determine if the user finished
|
||||
# a statement and if so the notifier will be woken up. The second
|
||||
# context is simply the regular context but it's gated waiting for the
|
||||
# notifier to be woken up.
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
ParallelPipeline(
|
||||
[
|
||||
statement_context_aggregator.user(),
|
||||
statement_llm,
|
||||
completness_check,
|
||||
NullFilter(),
|
||||
],
|
||||
[context_aggregator.user(), gated_context_aggregator, llm],
|
||||
),
|
||||
user_idle,
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
report_only_initial_ttfb=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.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
from run import main
|
||||
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user