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
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from openai.types.chat import ChatCompletionToolParam
|
||||
from runner import configure
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
|
||||
@@ -22,13 +18,14 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.processors.filters.function_filter import FunctionFilter
|
||||
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")
|
||||
|
||||
current_voice = "News Lady"
|
||||
|
||||
@@ -55,105 +52,117 @@ async def barbershop_man_filter(frame) -> bool:
|
||||
return current_voice == "Barbershop Man"
|
||||
|
||||
|
||||
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,
|
||||
token,
|
||||
"Pipecat",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
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,
|
||||
),
|
||||
)
|
||||
|
||||
news_lady = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="bf991597-6c13-47e4-8411-91ec2de5c466", # Newslady
|
||||
)
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
british_lady = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
news_lady = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="bf991597-6c13-47e4-8411-91ec2de5c466", # Newslady
|
||||
)
|
||||
|
||||
barbershop_man = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
|
||||
)
|
||||
british_lady = 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.register_function("switch_voice", switch_voice)
|
||||
barbershop_man = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
|
||||
)
|
||||
|
||||
tools = [
|
||||
ChatCompletionToolParam(
|
||||
type="function",
|
||||
function={
|
||||
"name": "switch_voice",
|
||||
"description": "Switch your voice only when the user asks you to",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"voice": {
|
||||
"type": "string",
|
||||
"description": "The voice the user wants you to use",
|
||||
},
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
llm.register_function("switch_voice", switch_voice)
|
||||
|
||||
tools = [
|
||||
ChatCompletionToolParam(
|
||||
type="function",
|
||||
function={
|
||||
"name": "switch_voice",
|
||||
"description": "Switch your voice only when the user asks you to",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"voice": {
|
||||
"type": "string",
|
||||
"description": "The voice the user wants you to use",
|
||||
},
|
||||
"required": ["voice"],
|
||||
},
|
||||
"required": ["voice"],
|
||||
},
|
||||
)
|
||||
},
|
||||
)
|
||||
]
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
ParallelPipeline( # TTS (one of the following vocies)
|
||||
[FunctionFilter(news_lady_filter), news_lady], # News Lady voice
|
||||
[
|
||||
FunctionFilter(british_lady_filter),
|
||||
british_lady,
|
||||
], # British Reading Lady voice
|
||||
[FunctionFilter(barbershop_man_filter), barbershop_man], # Barbershop Man voice
|
||||
),
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
messages = [
|
||||
)
|
||||
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
|
||||
@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": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
ParallelPipeline( # TTS (one of the following vocies)
|
||||
[FunctionFilter(news_lady_filter), news_lady], # News Lady voice
|
||||
[
|
||||
FunctionFilter(british_lady_filter),
|
||||
british_lady,
|
||||
], # British Reading Lady voice
|
||||
[FunctionFilter(barbershop_man_filter), barbershop_man], # Barbershop Man voice
|
||||
),
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
"content": f"Please introduce yourself to the user and let them know the voices you can do. Your initial responses should be as if you were a {current_voice}.",
|
||||
}
|
||||
)
|
||||
await task.queue_frames([context_aggregator.user().get_context_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.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Please introduce yourself to the user and let them know the voices you can do. Your initial responses should be as if you were a {current_voice}.",
|
||||
}
|
||||
)
|
||||
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()
|
||||
|
||||
runner = PipelineRunner()
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
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