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
2025-04-11 19:44:16 -04:00
committed by GitHub
parent 8186219879
commit f6accbd510
120 changed files with 7989 additions and 7179 deletions

View File

@@ -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.pipeline import Pipeline
@@ -20,123 +16,133 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.rime.tts import RimeHttpTTSService
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 store_user_emails(function_name, tool_call_id, args, llm, context, result_callback):
print(f"User emails: {args}")
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,
"Respond bot",
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,
),
)
# Cartesia offers a `<spell></spell>` tags that we can use to ask the user
# to confirm the emails.
# (see https://docs.cartesia.ai/build-with-sonic/formatting-text-for-sonic/spelling-out-input-text)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
aiohttp_session=session,
)
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
# Rime offers a function `spell()` that we can use to ask the user
# to confirm the emails.
# (see https://docs.rime.ai/api-reference/spell)
# tts = RimeHttpTTSService(
# api_key=os.getenv("RIME_API_KEY", ""),
# voice_id="eva",
# aiohttp_session=session,
# )
# Cartesia offers a `<spell></spell>` tags that we can use to ask the user
# to confirm the emails.
# (see https://docs.cartesia.ai/build-with-sonic/formatting-text-for-sonic/spelling-out-input-text)
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")
# You can aslo register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function("store_user_emails", store_user_emails)
# Rime offers a function `spell()` that we can use to ask the user
# to confirm the emails.
# (see https://docs.rime.ai/api-reference/spell)
# tts = RimeHttpTTSService(
# api_key=os.getenv("RIME_API_KEY", ""),
# voice_id="eva",
# aiohttp_session=session,
# )
tools = [
ChatCompletionToolParam(
type="function",
function={
"name": "store_user_emails",
"description": "Store user emails when confirmed",
"parameters": {
"type": "object",
"properties": {
"emails": {
"type": "array",
"description": "The list of user emails",
"items": {"type": "string"},
},
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
# You can aslo register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function("store_user_emails", store_user_emails)
tools = [
ChatCompletionToolParam(
type="function",
function={
"name": "store_user_emails",
"description": "Store user emails when confirmed",
"parameters": {
"type": "object",
"properties": {
"emails": {
"type": "array",
"description": "The list of user emails",
"items": {"type": "string"},
},
"required": ["emails"],
},
"required": ["emails"],
},
)
]
messages = [
{
"role": "system",
# Cartesia <spell></spell>
"content": "You need to gather a valid email or emails from the user. Your output will be converted to audio so don't include special characters in your answers. If the user provides one or more email addresses confirm them with the user. Enclose all emails with <spell> tags, for example <spell>a@a.com</spell>.",
# Rime spell()
# "content": "You need to gather a valid email or emails from the user. Your output will be converted to audio so don't include special characters in your answers. If the user provides one or more email addresses confirm them with the user. Enclose all emails with spell(), for example spell(a@a.com).",
},
)
]
messages = [
{
"role": "system",
# Cartesia <spell></spell>
"content": "You need to gather a valid email or emails from the user. Your output will be converted to audio so don't include special characters in your answers. If the user provides one or more email addresses confirm them with the user. Enclose all emails with <spell> tags, for example <spell>a@a.com</spell>.",
# Rime spell()
# "content": "You need to gather a valid email or emails from the user. Your output will be converted to audio so don't include special characters in your answers. If the user provides one or more email addresses confirm them with the user. Enclose all emails with spell(), for example spell(a@a.com).",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
stt,
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(context)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
@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()])
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=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()
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()