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

Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt (#1534)

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

151
examples/foundational/20b-persistent-context-openai-realtime.py
View File

@@ -8,13 +8,10 @@ import asyncio
import glob
import json
import os
import sys
from datetime import datetime
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
@@ -24,19 +21,19 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import (
OpenAILLMContext,
)
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai_realtime_beta import (
InputAudioTranscription,
OpenAIRealtimeBetaLLMService,
SessionProperties,
TurnDetection,
)
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")
BASE_FILENAME = "/tmp/pipecat_conversation_"
@@ -167,33 +164,31 @@ tools = [
]
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_in_enabled=True,
audio_out_enabled=True,
transcription_enabled=False,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
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(params=VADParams(stop_secs=0.8)),
vad_audio_passthrough=True,
),
)
session_properties = SessionProperties(
input_audio_transcription=InputAudioTranscription(),
# Set openai TurnDetection parameters. Not setting this at all will turn it
# on by default
turn_detection=TurnDetection(silence_duration_ms=1000),
# Or set to False to disable openai turn detection and use transport VAD
# turn_detection=False,
# tools=tools,
instructions="""Your knowledge cutoff is 2023-10. You are a helpful and friendly AI.
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
session_properties = SessionProperties(
input_audio_transcription=InputAudioTranscription(),
# Set openai TurnDetection parameters. Not setting this at all will turn it
# on by default
turn_detection=TurnDetection(silence_duration_ms=1000),
# Or set to False to disable openai turn detection and use transport VAD
# turn_detection=False,
# tools=tools,
instructions="""Your knowledge cutoff is 2023-10. You are a helpful and friendly AI.
Act like a human, but remember that you aren't a human and that you can't do human
things in the real world. Your voice and personality should be warm and engaging, with a lively and
@@ -207,54 +202,66 @@ You are participating in a voice conversation. Keep your responses concise, shor
unless specifically asked to elaborate on a topic.
Remember, your responses should be short. Just one or two sentences, usually.""",
)
)
llm = OpenAIRealtimeBetaLLMService(
api_key=os.getenv("OPENAI_API_KEY"),
session_properties=session_properties,
start_audio_paused=False,
)
llm = OpenAIRealtimeBetaLLMService(
api_key=os.getenv("OPENAI_API_KEY"),
session_properties=session_properties,
start_audio_paused=False,
)
# you can either register a single function for all function calls, or specific functions
# llm.register_function(None, fetch_weather_from_api)
llm.register_function("get_current_weather", fetch_weather_from_api)
llm.register_function("save_conversation", save_conversation)
llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
llm.register_function("load_conversation", load_conversation)
# you can either register a single function for all function calls, or specific functions
# llm.register_function(None, fetch_weather_from_api)
llm.register_function("get_current_weather", fetch_weather_from_api)
llm.register_function("save_conversation", save_conversation)
llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
llm.register_function("load_conversation", load_conversation)
context = OpenAILLMContext([], tools)
context_aggregator = llm.create_context_aggregator(context)
context = OpenAILLMContext([], tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
context_aggregator.user(),
llm, # LLM
transport.output(), # Transport bot output
context_aggregator.assistant(),
]
)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
context_aggregator.user(),
llm, # LLM
transport.output(), # Transport bot output
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
# report_only_initial_ttfb=True,
),
)
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.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await runner.run(task)
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())
from run import main
main()