Merge remote-tracking branch 'origin/main' into openrouter-integration

This commit is contained in:
sahil suman
2025-01-15 02:52:19 +05:30
353 changed files with 1384 additions and 588 deletions

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -124,7 +124,7 @@ async def main():
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -18,7 +18,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -134,7 +134,7 @@ async def main():
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -7,7 +7,7 @@ from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -75,7 +75,7 @@ async def main(room_url: str, token: str):
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -13,7 +13,7 @@ logger.add(sys.stderr, level="DEBUG")
async def main(room_url: str, token: str):
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -75,7 +75,7 @@ async def main(room_url: str, token: str):
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):

View File

@@ -7,7 +7,7 @@ from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -81,7 +81,7 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):

View File

@@ -8,7 +8,7 @@ from loguru import logger
from twilio.rest import Client
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -83,7 +83,7 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import Frame, LLMMessagesFrame, MetricsFrame
from pipecat.frames.frames import EndFrame, Frame, MetricsFrame
from pipecat.metrics.metrics import (
LLMUsageMetricsData,
ProcessingMetricsData,
@@ -113,7 +113,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,7 @@ from PIL import Image
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import Frame, OutputImageRawFrame, SystemFrame, TextFrame
from pipecat.frames.frames import EndFrame, Frame, OutputImageRawFrame, SystemFrame, TextFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
@@ -126,6 +126,10 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -13,7 +13,7 @@ from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -90,7 +90,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -88,7 +88,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -78,13 +78,25 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -19,7 +19,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -101,7 +101,15 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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):
@@ -114,6 +122,10 @@ async def main():
messages = [({"content": "Please briefly introduce yourself to the user."})]
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -16,7 +16,7 @@ from runner import configure
from pipecat.frames.frames import (
BotInterruptionFrame,
LLMMessagesFrame,
EndFrame,
StopInterruptionFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
@@ -80,7 +80,15 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)
@stt.event_handler("on_speech_started")
async def on_speech_started(stt, *args, **kwargs):
@@ -94,7 +102,11 @@ async def main():
async def on_first_participant_joined(transport, participant):
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -73,13 +73,25 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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):
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -88,7 +88,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2024, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -90,7 +90,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -91,7 +91,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -82,14 +82,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -70,14 +70,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -80,14 +80,26 @@ async def main():
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -74,14 +74,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,22 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
# Register an event handler to exit the application when the user leaves.
@transport.event_handler("on_participant_left")

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -71,14 +71,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -90,7 +90,10 @@ async def main():
task = PipelineTask(
pipeline,
PipelineParams(
allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)
@@ -98,7 +101,11 @@ async def main():
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -80,14 +80,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,26 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,14 +14,11 @@ from loguru import logger
from runner import configure
from pipecat.audio.filters.krisp_filter import KrispFilter
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMAssistantResponseAggregator,
LLMUserResponseAggregator,
)
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -63,28 +60,40 @@ async def main():
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
tma_in, # User responses
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out, # Assistant spoken responses
context_aggregator.assistant(), # Assistant spoken responses
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
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):
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -89,7 +89,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -81,7 +81,11 @@ async def main():
async def on_first_participant_joined(transport, participant):
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -17,6 +17,7 @@ from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
EndFrame,
Frame,
InputAudioRawFrame,
LLMFullResponseEndFrame,
@@ -268,6 +269,10 @@ async def main():
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -88,7 +88,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -0,0 +1,148 @@
#
# Copyright (c) 2025, Daily
#
# 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
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.deepseek import DeepSeekLLMService
from pipecat.services.openai import OpenAILLMContext
from pipecat.transports.services.daily import DailyParams, DailyTransport
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def start_fetch_weather(function_name, llm, context):
# note: we can't push a frame to the LLM here. the bot
# can interrupt itself and/or cause audio overlapping glitches.
# possible question for Aleix and Chad about what the right way
# to trigger speech is, now, with the new queues/async/sync refactors.
# await llm.push_frame(TextFrame("Let me check on that."))
logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
await result_callback({"conditions": "nice", "temperature": "75"})
async def main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
)
llm = DeepSeekLLMService(api_key=os.getenv("DEEPSEEK_API_KEY"), model="deepseek-chat")
# Register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
tools = [
ChatCompletionToolParam(
type="function",
function={
"name": "get_current_weather",
"description": "Get the current weather for a specific location. You MUST use this function whenever asked about weather.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Use fahrenheit for US locations, celsius for others.",
},
},
"required": ["location", "format"],
},
},
)
]
messages = [
{
"role": "system",
"content": """You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
You have one functions available:
1. get_current_weather is used to get current weather information.
Infer whether to use Fahrenheit or Celsius automatically based on the location, unless the user specifies a preference.
Start by asking me for my location. Then, use 'get_weather_current' to give me a forecast.
Respond to what the user said in a creative and helpful way.""",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
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()])
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,6 @@ from openai.types.chat import ChatCompletionToolParam
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -146,7 +145,7 @@ async def main():
"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([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -16,7 +16,6 @@ from openai.types.chat import ChatCompletionToolParam
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -139,7 +138,7 @@ async def main():
"content": f"Please introduce yourself to the user and let them know the languages you speak. Your initial responses should be in {current_language}.",
}
)
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,6 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -98,7 +97,7 @@ async def main():
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
# Handle "latency-ping" messages. The client will send app messages that look like
# this:

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -100,7 +100,7 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,14 +14,11 @@ from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMAssistantResponseAggregator,
LLMUserResponseAggregator,
)
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.deepgram import DeepgramSTTService
from pipecat.services.openai import OpenAILLMService
@@ -73,19 +70,19 @@ async def main():
},
]
tma_in = LLMUserResponseAggregator(messages)
tma_out = LLMAssistantResponseAggregator(messages)
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
tma_in, # User responses
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
tavus, # Tavus output layer
transport.output(), # Transport bot output
tma_out, # Assistant spoken responses
context_aggregator.assistant(), # Assistant spoken responses
]
)
@@ -119,7 +116,11 @@ async def main():
messages.append(
{"role": "system", "content": "Please introduce yourself to the user."}
)
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -14,7 +14,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame, TextFrame
from pipecat.frames.frames import TextFrame
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -155,7 +155,7 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -311,7 +311,7 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_app_message")
async def on_app_message(transport, message, sender):

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -525,7 +525,7 @@ async def main():
"content": "Start by just saying \"Hello I'm ready.\" Don't say anything else.",
}
)
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_app_message")
async def on_app_message(transport, message, sender):

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -16,7 +16,7 @@ from runner import configure_with_args
from pipecat.audio.mixers.soundfile_mixer import SoundfileMixer
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame, MixerEnableFrame, MixerUpdateSettingsFrame
from pipecat.frames.frames import MixerEnableFrame, MixerUpdateSettingsFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -108,7 +108,7 @@ async def main():
await asyncio.sleep(5.0)
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,6 @@ from openai.types.chat import ChatCompletionToolParam
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -132,7 +131,7 @@ async def main():
"content": "Ask the user what city they'd like to know the weather for.",
}
)
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2024, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,13 +15,16 @@ from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import EndFrame
from pipecat.pipeline.pipeline import Pipeline
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 import CartesiaTTSService
from pipecat.services.gemini_multimodal_live.gemini import (
GeminiMultimodalLiveLLMService,
GeminiMultimodalModalities,
InputParams,
)
from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -30,6 +33,16 @@ load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
SYSTEM_INSTRUCTION = f"""
"You are Gemini Chatbot, a friendly, helpful robot.
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. Keep your responses brief. One or two sentences at most.
"""
async def main():
async with aiohttp.ClientSession() as session:
@@ -55,24 +68,42 @@ async def main():
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
# system_instruction="Talk like a pirate."
transcribe_user_audio=True,
transcribe_model_audio=True,
system_instruction=SYSTEM_INSTRUCTION,
tools=[{"google_search": {}}, {"code_execution": {}}],
params=InputParams(modalities=GeminiMultimodalModalities.TEXT),
)
llm.set_model_modalities(
GeminiMultimodalModalities.TEXT
) # This forces model to produce text only responses
# Optionally, you can set the response modalities via a function
# llm.set_model_modalities(
# GeminiMultimodalModalities.TEXT
# )
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
)
messages = [
{
"role": "user",
"content": 'Start by saying "Hello, I\'m Gemini".',
},
]
# Set up conversation context and management
# The context_aggregator will automatically collect conversation context
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
@@ -85,6 +116,16 @@ async def main():
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
print(f"Participant left: {participant}")
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

View File

@@ -0,0 +1,108 @@
#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import os
import sys
from pathlib import Path
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
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.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
sys.path.append(str(Path(__file__).parent.parent))
from runner import configure
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
# Function handlers for the LLM
search_tool = {"google_search": {}}
tools = [search_tool]
system_instruction = """
You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting.
Always use the google search API to retrieve the latest news. You must also use it to check which day is today.
You can:
- Use the Google search API to check the current date.
- Provide the most recent and relevant news from any place by using the google search API.
- Answer any questions the user may have, ensuring your responses are accurate and concise.
Start each interaction by asking the user about which place they would like to know the information.
"""
async def main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Latest news!",
DailyParams(
audio_out_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
vad_audio_passthrough=True,
),
)
# Initialize the Gemini Multimodal Live model
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck
transcribe_user_audio=True,
transcribe_model_audio=True,
system_instruction=system_instruction,
tools=tools,
)
context = OpenAILLMContext(
[
{
"role": "user",
"content": "Start by greeting the user warmly, introducing yourself, and mentioning the current day. Be friendly and engaging to set a positive tone for the interaction.",
}
],
)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
context_aggregator.user(), # User responses
llm, # LLM
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,6 @@ from runner import configure
from simli import SimliConfig
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -93,7 +92,7 @@ async def main():
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
await task.queue_frames([context_aggregator.user().get_context_frame()])
runner = PipelineRunner()
await runner.run(task)

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
from pipecat.frames.frames import EndFrame, TranscriptionMessage, TranscriptionUpdateFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -101,11 +101,6 @@ async def main():
transcript = TranscriptProcessor()
transcript_handler = TranscriptHandler()
# Register event handler for transcript updates
@transcript.event_handler("on_transcript_update")
async def on_transcript_update(processor, frame):
await transcript_handler.on_transcript_update(processor, frame)
pipeline = Pipeline(
[
transport.input(), # Transport user input
@@ -128,6 +123,15 @@ async def main():
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
# Register event handler for transcript updates
@transcript.event_handler("on_transcript_update")
async def on_transcript_update(processor, frame):
await transcript_handler.on_transcript_update(processor, frame)
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

View File

@@ -1,5 +1,5 @@
#
# Copyright (c) 2025, Daily
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
@@ -15,7 +15,7 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
from pipecat.frames.frames import EndFrame, TranscriptionMessage, TranscriptionUpdateFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -128,6 +128,10 @@ async def main():
async def on_transcript_update(processor, frame):
await transcript_handler.on_transcript_update(processor, frame)
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

Some files were not shown because too many files have changed in this diff Show More