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
@@ -4,15 +4,11 @@
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
from typing import List, Optional
|
||||
|
||||
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 TranscriptionMessage, TranscriptionUpdateFrame
|
||||
@@ -24,13 +20,12 @@ from pipecat.processors.transcript_processor import TranscriptProcessor
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
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")
|
||||
|
||||
|
||||
class TranscriptHandler:
|
||||
"""Handles real-time transcript processing and output.
|
||||
@@ -93,85 +88,88 @@ class TranscriptHandler:
|
||||
await self.save_message(msg)
|
||||
|
||||
|
||||
async def main():
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, token) = 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,
|
||||
),
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
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
|
||||
)
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o",
|
||||
)
|
||||
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, helpful, and brief way. Say hello.",
|
||||
},
|
||||
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, helpful, and brief way. Say hello.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
# Create transcript processor and handler
|
||||
transcript = TranscriptProcessor()
|
||||
transcript_handler = TranscriptHandler() # Output to log only
|
||||
# transcript_handler = TranscriptHandler(output_file="transcript.txt") # Output to file and log
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
transcript.user(), # User transcripts
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
transcript.assistant(), # Assistant transcripts
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
|
||||
# Create transcript processor and handler
|
||||
transcript = TranscriptProcessor()
|
||||
transcript_handler = TranscriptHandler() # Output to log only
|
||||
# transcript_handler = TranscriptHandler(output_file="transcript.txt") # Output to file and log
|
||||
@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()])
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
transcript.user(), # User transcripts
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
transcript.assistant(), # Assistant transcripts
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
# Register event handler for transcript updates
|
||||
@transcript.event_handler("on_transcript_update")
|
||||
async def on_transcript_update(processor, frame):
|
||||
await transcript_handler.on_transcript_update(processor, frame)
|
||||
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=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"])
|
||||
# Kick off the conversation.
|
||||
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()
|
||||
|
||||
# Register event handler for transcript updates
|
||||
@transcript.event_handler("on_transcript_update")
|
||||
async def on_transcript_update(processor, frame):
|
||||
await transcript_handler.on_transcript_update(processor, frame)
|
||||
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
# Stop the pipeline immediately when the participant leaves
|
||||
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()
|
||||
|
||||
Reference in New Issue
Block a user