wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

examples: cleanup some 07 interruptible examples

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2024-06-13 16:35:15 -07:00
parent 6cdccaff53
commit c086160239
3 changed files with 134 additions and 141 deletions
Download Patch File Download Diff File Expand all files Collapse all files

92
examples/foundational/07d-interruptible-cartesia.py
View File

@@ -5,7 +5,6 @@
# #
import asyncio import asyncio
import aiohttp
import os import os
import sys import sys
@@ -33,62 +32,61 @@ logger.add(sys.stderr, level="DEBUG")
async def main(room_url: str, token): async def main(room_url: str, token):
async with aiohttp.ClientSession() as session: transport = DailyTransport(
transport = DailyTransport( room_url,
room_url, token,
token, "Respond bot",
"Respond bot", DailyParams(
DailyParams( audio_out_enabled=True,
audio_out_enabled=True, audio_out_sample_rate=44100,
audio_out_sample_rate=44100, transcription_enabled=True,
transcription_enabled=True, vad_enabled=True,
vad_enabled=True, vad_analyzer=SileroVADAnalyzer()
vad_analyzer=SileroVADAnalyzer()
)
) )
)
tts = CartesiaTTSService( tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"), api_key=os.getenv("CARTESIA_API_KEY"),
voice_name="British Lady", voice_name="British Lady",
output_format="pcm_44100" output_format="pcm_44100"
) )
llm = OpenAILLMService( llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"), api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o") model="gpt-4o")
messages = [ messages = [
{ {
"role": "system", "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.", "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.",
}, },
] ]
tma_in = LLMUserResponseAggregator(messages) tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages) tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([ pipeline = Pipeline([
transport.input(), # Transport user input transport.input(), # Transport user input
tma_in, # User responses tma_in, # User responses
llm, # LLM llm, # LLM
tts, # TTS tts, # TTS
transport.output(), # Transport bot output transport.output(), # Transport bot output
tma_out # Assistant spoken responses tma_out # Assistant spoken responses
]) ])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True)) task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined") @transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant): async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"]) transport.capture_participant_transcription(participant["id"])
# Kick off the conversation. # Kick off the conversation.
messages.append( messages.append(
{"role": "system", "content": "Please introduce yourself to the user."}) {"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)]) await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner() runner = PipelineRunner()
await runner.run(task) await runner.run(task)
if __name__ == "__main__": if __name__ == "__main__":

93
examples/foundational/07e-interruptible-playht.py
View File

@@ -5,7 +5,6 @@
# #
import asyncio import asyncio
import aiohttp
import os import os
import sys import sys
@@ -19,7 +18,6 @@ from pipecat.services.playht import PlayHTTTSService
from pipecat.services.openai import OpenAILLMService from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVADAnalyzer from pipecat.vad.silero import SileroVADAnalyzer
from pipecat.processors.logger import FrameLogger
from runner import configure from runner import configure
@@ -33,62 +31,61 @@ logger.add(sys.stderr, level="DEBUG")
async def main(room_url: str, token): async def main(room_url: str, token):
async with aiohttp.ClientSession() as session: transport = DailyTransport(
transport = DailyTransport( room_url,
room_url, token,
token, "Respond bot",
"Respond bot", DailyParams(
DailyParams( audio_out_enabled=True,
audio_out_enabled=True, audio_out_sample_rate=16000,
audio_out_sample_rate=16000, transcription_enabled=True,
transcription_enabled=True, vad_enabled=True,
vad_enabled=True, vad_analyzer=SileroVADAnalyzer()
vad_analyzer=SileroVADAnalyzer()
)
) )
)
tts = PlayHTTTSService( tts = PlayHTTTSService(
user_id=os.getenv("PLAYHT_USER_ID"), user_id=os.getenv("PLAYHT_USER_ID"),
api_key=os.getenv("PLAYHT_API_KEY"), api_key=os.getenv("PLAYHT_API_KEY"),
voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json", voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
) )
llm = OpenAILLMService( llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"), api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o") model="gpt-4o")
messages = [ messages = [
{ {
"role": "system", "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.", "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.",
}, },
] ]
tma_in = LLMUserResponseAggregator(messages) tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages) tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([ pipeline = Pipeline([
transport.input(), # Transport user input transport.input(), # Transport user input
tma_in, # User responses tma_in, # User responses
llm, # LLM llm, # LLM
tts, # TTS tts, # TTS
transport.output(), # Transport bot output transport.output(), # Transport bot output
tma_out # Assistant spoken responses tma_out # Assistant spoken responses
]) ])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True)) task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined") @transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant): async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"]) transport.capture_participant_transcription(participant["id"])
# Kick off the conversation. # Kick off the conversation.
messages.append( messages.append(
{"role": "system", "content": "Please introduce yourself to the user."}) {"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)]) await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner() runner = PipelineRunner()
await runner.run(task) await runner.run(task)
if __name__ == "__main__": if __name__ == "__main__":

90
examples/foundational/07g-interruptible-openai-tts.py
View File

@@ -5,7 +5,6 @@
# #
import asyncio import asyncio
import aiohttp
import os import os
import sys import sys
@@ -32,61 +31,60 @@ logger.add(sys.stderr, level="DEBUG")
async def main(room_url: str, token): async def main(room_url: str, token):
async with aiohttp.ClientSession() as session: transport = DailyTransport(
transport = DailyTransport( room_url,
room_url, token,
token, "Respond bot",
"Respond bot", DailyParams(
DailyParams( audio_out_enabled=True,
audio_out_enabled=True, audio_out_sample_rate=24000,
audio_out_sample_rate=24000, transcription_enabled=True,
transcription_enabled=True, vad_enabled=True,
vad_enabled=True, vad_analyzer=SileroVADAnalyzer()
vad_analyzer=SileroVADAnalyzer()
)
) )
)
tts = OpenAITTSService( tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"), api_key=os.getenv("OPENAI_API_KEY"),
voice="alloy" voice="alloy"
) )
llm = OpenAILLMService( llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"), api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o") model="gpt-4o")
messages = [ messages = [
{ {
"role": "system", "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.", "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.",
}, },
] ]
tma_in = LLMUserResponseAggregator(messages) tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages) tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([ pipeline = Pipeline([
transport.input(), # Transport user input transport.input(), # Transport user input
tma_in, # User responses tma_in, # User responses
llm, # LLM llm, # LLM
tts, # TTS tts, # TTS
transport.output(), # Transport bot output transport.output(), # Transport bot output
tma_out # Assistant spoken responses tma_out # Assistant spoken responses
]) ])
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True)) task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined") @transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant): async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"]) transport.capture_participant_transcription(participant["id"])
# Kick off the conversation. # Kick off the conversation.
messages.append( messages.append(
{"role": "system", "content": "Please introduce yourself to the user."}) {"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)]) await task.queue_frames([LLMMessagesFrame(messages)])
runner = PipelineRunner() runner = PipelineRunner()
await runner.run(task) await runner.run(task)
if __name__ == "__main__": if __name__ == "__main__":