examples(foundational): support multiple transports

This commit is contained in:
Aleix Conchillo Flaqué
2025-05-24 21:00:24 -07:00
parent ecf878e14d
commit 2cdfaa0a82
128 changed files with 3282 additions and 2716 deletions

View File

@@ -21,92 +21,105 @@ 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.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
aiohttp_session = aiohttp.ClientSession()
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=FalSmartTurnAnalyzer(
api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=aiohttp_session
),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=FalSmartTurnAnalyzer(
api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=aiohttp_session
),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
transport = SmallWebRTCTransport(
webrtc_connection=webrtc_connection,
params=TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=FalSmartTurnAnalyzer(
api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=session
),
),
)
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"))
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
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 and helpful way.",
},
]
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 and helpful way.",
},
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt,
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
context = OpenAILLMContext(messages)
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(), # Transport user input
stt,
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
@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": "Please introduce yourself to the user."})
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")
await task.cancel()
@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": "Please introduce yourself to the user."})
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()
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
runner = PipelineRunner(handle_sigint=False)
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
await runner.run(task)
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
await aiohttp_session.close()
if __name__ == "__main__":
from run import main
main()
main(run_example, transport_params=transport_params)