Merge pull request #3479 from pipecat-ai/aleix/turns-mute-to-user-mute
turns: move mute to user_mute
This commit is contained in:
1
changelog/3479.deprecated.md
Normal file
1
changelog/3479.deprecated.md
Normal file
@@ -0,0 +1 @@
|
|||||||
|
- For consistency with other package names, we just deprecated `pipecat.turns.mute` (introduced in Pipecat 0.0.99) in favor of `pipecat.turns.user_mute`.
|
||||||
@@ -1,182 +0,0 @@
|
|||||||
#
|
|
||||||
# Copyright (c) 2024-2026, Daily
|
|
||||||
#
|
|
||||||
# SPDX-License-Identifier: BSD 2-Clause License
|
|
||||||
#
|
|
||||||
|
|
||||||
|
|
||||||
import asyncio
|
|
||||||
import os
|
|
||||||
|
|
||||||
from dotenv import load_dotenv
|
|
||||||
from loguru import logger
|
|
||||||
|
|
||||||
from pipecat.adapters.schemas.function_schema import FunctionSchema
|
|
||||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
|
||||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
|
||||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
||||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
|
||||||
from pipecat.frames.frames import LLMRunFrame
|
|
||||||
from pipecat.pipeline.pipeline import Pipeline
|
|
||||||
from pipecat.pipeline.runner import PipelineRunner
|
|
||||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
||||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
|
||||||
from pipecat.processors.aggregators.llm_response_universal import (
|
|
||||||
LLMContextAggregatorPair,
|
|
||||||
LLMUserAggregatorParams,
|
|
||||||
)
|
|
||||||
from pipecat.processors.filters.stt_mute_filter import STTMuteConfig, STTMuteFilter, STTMuteStrategy
|
|
||||||
from pipecat.runner.types import RunnerArguments
|
|
||||||
from pipecat.runner.utils import create_transport
|
|
||||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
||||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
|
||||||
from pipecat.services.llm_service import FunctionCallParams
|
|
||||||
from pipecat.services.openai.llm import OpenAILLMService
|
|
||||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
||||||
from pipecat.transports.daily.transport import DailyParams
|
|
||||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
|
||||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
|
||||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
|
||||||
|
|
||||||
load_dotenv(override=True)
|
|
||||||
|
|
||||||
|
|
||||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
|
||||||
# Add a delay to test interruption during function calls
|
|
||||||
logger.info("Weather API call starting...")
|
|
||||||
await asyncio.sleep(5) # 5-second delay
|
|
||||||
logger.info("Weather API call completed")
|
|
||||||
await params.result_callback({"conditions": "nice", "temperature": "75"})
|
|
||||||
|
|
||||||
|
|
||||||
# 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)),
|
|
||||||
),
|
|
||||||
"twilio": lambda: FastAPIWebsocketParams(
|
|
||||||
audio_in_enabled=True,
|
|
||||||
audio_out_enabled=True,
|
|
||||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
|
||||||
),
|
|
||||||
"webrtc": lambda: TransportParams(
|
|
||||||
audio_in_enabled=True,
|
|
||||||
audio_out_enabled=True,
|
|
||||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
|
||||||
),
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
||||||
logger.info(f"Starting bot")
|
|
||||||
|
|
||||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
|
||||||
|
|
||||||
# Configure the mute processor with both strategies
|
|
||||||
stt_mute_processor = STTMuteFilter(
|
|
||||||
config=STTMuteConfig(
|
|
||||||
strategies={
|
|
||||||
STTMuteStrategy.MUTE_UNTIL_FIRST_BOT_COMPLETE,
|
|
||||||
STTMuteStrategy.FUNCTION_CALL,
|
|
||||||
}
|
|
||||||
),
|
|
||||||
)
|
|
||||||
|
|
||||||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
|
|
||||||
|
|
||||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
|
||||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
|
||||||
|
|
||||||
weather_function = FunctionSchema(
|
|
||||||
name="get_current_weather",
|
|
||||||
description="Get the current weather",
|
|
||||||
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. Infer this from the user's location.",
|
|
||||||
},
|
|
||||||
},
|
|
||||||
required=["location", "format"],
|
|
||||||
)
|
|
||||||
tools = ToolsSchema(standard_tools=[weather_function])
|
|
||||||
|
|
||||||
messages = [
|
|
||||||
{
|
|
||||||
"role": "system",
|
|
||||||
"content": "You are a helpful assistant who can check the weather. Always check the weather when a location is mentioned. Respond concisely and naturally. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.",
|
|
||||||
},
|
|
||||||
]
|
|
||||||
|
|
||||||
context = LLMContext(messages, tools)
|
|
||||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
||||||
context,
|
|
||||||
user_params=LLMUserAggregatorParams(
|
|
||||||
user_turn_strategies=UserTurnStrategies(
|
|
||||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
|
||||||
),
|
|
||||||
),
|
|
||||||
)
|
|
||||||
|
|
||||||
pipeline = Pipeline(
|
|
||||||
[
|
|
||||||
transport.input(), # Transport user input
|
|
||||||
stt, # STT
|
|
||||||
stt_mute_processor, # Add the mute processor between STT and context aggregator
|
|
||||||
user_aggregator, # User responses
|
|
||||||
llm, # LLM
|
|
||||||
tts, # TTS
|
|
||||||
transport.output(), # Transport bot output
|
|
||||||
assistant_aggregator, # Assistant spoken responses
|
|
||||||
]
|
|
||||||
)
|
|
||||||
|
|
||||||
task = PipelineTask(
|
|
||||||
pipeline,
|
|
||||||
params=PipelineParams(
|
|
||||||
enable_metrics=True,
|
|
||||||
enable_usage_metrics=True,
|
|
||||||
),
|
|
||||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
|
||||||
)
|
|
||||||
|
|
||||||
@transport.event_handler("on_client_connected")
|
|
||||||
async def on_client_connected(transport, client):
|
|
||||||
logger.info(f"Client connected")
|
|
||||||
# Kick off the conversation with a weather-related prompt
|
|
||||||
messages.append(
|
|
||||||
{
|
|
||||||
"role": "system",
|
|
||||||
"content": "Ask the user what city they'd like to know the weather for.",
|
|
||||||
}
|
|
||||||
)
|
|
||||||
await task.queue_frames([LLMRunFrame()])
|
|
||||||
|
|
||||||
@transport.event_handler("on_client_disconnected")
|
|
||||||
async def on_client_disconnected(transport, client):
|
|
||||||
logger.info(f"Client disconnected")
|
|
||||||
await task.cancel()
|
|
||||||
|
|
||||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
|
||||||
|
|
||||||
await runner.run(task)
|
|
||||||
|
|
||||||
|
|
||||||
async def bot(runner_args: RunnerArguments):
|
|
||||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
|
||||||
transport = await create_transport(runner_args, transport_params)
|
|
||||||
await run_bot(transport, runner_args)
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
from pipecat.runner.run import main
|
|
||||||
|
|
||||||
main()
|
|
||||||
@@ -34,7 +34,7 @@ from pipecat.services.openai.llm import OpenAILLMService
|
|||||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||||
from pipecat.transports.daily.transport import DailyParams
|
from pipecat.transports.daily.transport import DailyParams
|
||||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||||
from pipecat.turns.mute import (
|
from pipecat.turns.user_mute import (
|
||||||
FunctionCallUserMuteStrategy,
|
FunctionCallUserMuteStrategy,
|
||||||
MuteUntilFirstBotCompleteUserMuteStrategy,
|
MuteUntilFirstBotCompleteUserMuteStrategy,
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -62,7 +62,7 @@ from pipecat.processors.aggregators.llm_context import (
|
|||||||
NotGiven,
|
NotGiven,
|
||||||
)
|
)
|
||||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||||
from pipecat.turns.mute import BaseUserMuteStrategy
|
from pipecat.turns.user_mute import BaseUserMuteStrategy
|
||||||
from pipecat.turns.user_start import BaseUserTurnStartStrategy, UserTurnStartedParams
|
from pipecat.turns.user_start import BaseUserTurnStartStrategy, UserTurnStartedParams
|
||||||
from pipecat.turns.user_stop import BaseUserTurnStopStrategy, UserTurnStoppedParams
|
from pipecat.turns.user_stop import BaseUserTurnStopStrategy, UserTurnStoppedParams
|
||||||
from pipecat.turns.user_turn_controller import UserTurnController
|
from pipecat.turns.user_turn_controller import UserTurnController
|
||||||
|
|||||||
@@ -4,10 +4,21 @@
|
|||||||
# SPDX-License-Identifier: BSD 2-Clause License
|
# SPDX-License-Identifier: BSD 2-Clause License
|
||||||
#
|
#
|
||||||
|
|
||||||
from pipecat.turns.mute.always_user_mute_strategy import AlwaysUserMuteStrategy
|
import warnings
|
||||||
from pipecat.turns.mute.base_user_mute_strategy import BaseUserMuteStrategy
|
|
||||||
from pipecat.turns.mute.first_speech_user_mute_strategy import FirstSpeechUserMuteStrategy
|
from pipecat.turns.user_mute.always_user_mute_strategy import AlwaysUserMuteStrategy
|
||||||
from pipecat.turns.mute.function_call_user_mute_strategy import FunctionCallUserMuteStrategy
|
from pipecat.turns.user_mute.base_user_mute_strategy import BaseUserMuteStrategy
|
||||||
from pipecat.turns.mute.mute_until_first_bot_complete_user_mute_strategy import (
|
from pipecat.turns.user_mute.first_speech_user_mute_strategy import FirstSpeechUserMuteStrategy
|
||||||
|
from pipecat.turns.user_mute.function_call_user_mute_strategy import FunctionCallUserMuteStrategy
|
||||||
|
from pipecat.turns.user_mute.mute_until_first_bot_complete_user_mute_strategy import (
|
||||||
MuteUntilFirstBotCompleteUserMuteStrategy,
|
MuteUntilFirstBotCompleteUserMuteStrategy,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
with warnings.catch_warnings():
|
||||||
|
warnings.simplefilter("always")
|
||||||
|
warnings.warn(
|
||||||
|
"Types in pipecat.turns.mute are deprecated. "
|
||||||
|
"Please use the equivalent types from pipecat.turns.user_mute instead.",
|
||||||
|
DeprecationWarning,
|
||||||
|
stacklevel=2,
|
||||||
|
)
|
||||||
|
|||||||
21
src/pipecat/turns/user_mute/__init__.py
Normal file
21
src/pipecat/turns/user_mute/__init__.py
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
#
|
||||||
|
# Copyright (c) 2024-2026, Daily
|
||||||
|
#
|
||||||
|
# SPDX-License-Identifier: BSD 2-Clause License
|
||||||
|
#
|
||||||
|
|
||||||
|
from .always_user_mute_strategy import AlwaysUserMuteStrategy
|
||||||
|
from .base_user_mute_strategy import BaseUserMuteStrategy
|
||||||
|
from .first_speech_user_mute_strategy import FirstSpeechUserMuteStrategy
|
||||||
|
from .function_call_user_mute_strategy import FunctionCallUserMuteStrategy
|
||||||
|
from .mute_until_first_bot_complete_user_mute_strategy import (
|
||||||
|
MuteUntilFirstBotCompleteUserMuteStrategy,
|
||||||
|
)
|
||||||
|
|
||||||
|
__all__ = [
|
||||||
|
"AlwaysUserMuteStrategy",
|
||||||
|
"BaseUserMuteStrategy",
|
||||||
|
"FirstSpeechUserMuteStrategy",
|
||||||
|
"FunctionCallUserMuteStrategy",
|
||||||
|
"MuteUntilFirstBotCompleteUserMuteStrategy",
|
||||||
|
]
|
||||||
@@ -7,7 +7,7 @@
|
|||||||
"""User mute strategy that always mutes the user while the bot is speaking."""
|
"""User mute strategy that always mutes the user while the bot is speaking."""
|
||||||
|
|
||||||
from pipecat.frames.frames import BotStartedSpeakingFrame, BotStoppedSpeakingFrame, Frame
|
from pipecat.frames.frames import BotStartedSpeakingFrame, BotStoppedSpeakingFrame, Frame
|
||||||
from pipecat.turns.mute.base_user_mute_strategy import BaseUserMuteStrategy
|
from pipecat.turns.user_mute.base_user_mute_strategy import BaseUserMuteStrategy
|
||||||
|
|
||||||
|
|
||||||
class AlwaysUserMuteStrategy(BaseUserMuteStrategy):
|
class AlwaysUserMuteStrategy(BaseUserMuteStrategy):
|
||||||
@@ -7,7 +7,7 @@
|
|||||||
"""User mute strategy that mutes the user only during the bot’s first speech."""
|
"""User mute strategy that mutes the user only during the bot’s first speech."""
|
||||||
|
|
||||||
from pipecat.frames.frames import BotStartedSpeakingFrame, BotStoppedSpeakingFrame, Frame
|
from pipecat.frames.frames import BotStartedSpeakingFrame, BotStoppedSpeakingFrame, Frame
|
||||||
from pipecat.turns.mute.base_user_mute_strategy import BaseUserMuteStrategy
|
from pipecat.turns.user_mute.base_user_mute_strategy import BaseUserMuteStrategy
|
||||||
|
|
||||||
|
|
||||||
class FirstSpeechUserMuteStrategy(BaseUserMuteStrategy):
|
class FirstSpeechUserMuteStrategy(BaseUserMuteStrategy):
|
||||||
@@ -14,7 +14,7 @@ from pipecat.frames.frames import (
|
|||||||
FunctionCallResultFrame,
|
FunctionCallResultFrame,
|
||||||
FunctionCallsStartedFrame,
|
FunctionCallsStartedFrame,
|
||||||
)
|
)
|
||||||
from pipecat.turns.mute.base_user_mute_strategy import BaseUserMuteStrategy
|
from pipecat.turns.user_mute.base_user_mute_strategy import BaseUserMuteStrategy
|
||||||
|
|
||||||
|
|
||||||
class FunctionCallUserMuteStrategy(BaseUserMuteStrategy):
|
class FunctionCallUserMuteStrategy(BaseUserMuteStrategy):
|
||||||
@@ -7,7 +7,7 @@
|
|||||||
"""User mute strategy that mutes the user until the bot completes its first speech."""
|
"""User mute strategy that mutes the user until the bot completes its first speech."""
|
||||||
|
|
||||||
from pipecat.frames.frames import BotStoppedSpeakingFrame, Frame
|
from pipecat.frames.frames import BotStoppedSpeakingFrame, Frame
|
||||||
from pipecat.turns.mute.base_user_mute_strategy import BaseUserMuteStrategy
|
from pipecat.turns.user_mute.base_user_mute_strategy import BaseUserMuteStrategy
|
||||||
|
|
||||||
|
|
||||||
class MuteUntilFirstBotCompleteUserMuteStrategy(BaseUserMuteStrategy):
|
class MuteUntilFirstBotCompleteUserMuteStrategy(BaseUserMuteStrategy):
|
||||||
@@ -4,15 +4,17 @@
|
|||||||
# SPDX-License-Identifier: BSD 2-Clause License
|
# SPDX-License-Identifier: BSD 2-Clause License
|
||||||
#
|
#
|
||||||
|
|
||||||
from pipecat.turns.user_start.base_user_turn_start_strategy import (
|
from .base_user_turn_start_strategy import BaseUserTurnStartStrategy, UserTurnStartedParams
|
||||||
BaseUserTurnStartStrategy,
|
from .external_user_turn_start_strategy import ExternalUserTurnStartStrategy
|
||||||
UserTurnStartedParams,
|
from .min_words_user_turn_start_strategy import MinWordsUserTurnStartStrategy
|
||||||
)
|
from .transcription_user_turn_start_strategy import TranscriptionUserTurnStartStrategy
|
||||||
from pipecat.turns.user_start.external_user_turn_start_strategy import ExternalUserTurnStartStrategy
|
from .vad_user_turn_start_strategy import VADUserTurnStartStrategy
|
||||||
from pipecat.turns.user_start.min_words_user_turn_start_strategy import (
|
|
||||||
MinWordsUserTurnStartStrategy,
|
__all__ = [
|
||||||
)
|
"BaseUserTurnStartStrategy",
|
||||||
from pipecat.turns.user_start.transcription_user_turn_start_strategy import (
|
"ExternalUserTurnStartStrategy",
|
||||||
TranscriptionUserTurnStartStrategy,
|
"MinWordsUserTurnStartStrategy",
|
||||||
)
|
"TranscriptionUserTurnStartStrategy",
|
||||||
from pipecat.turns.user_start.vad_user_turn_start_strategy import VADUserTurnStartStrategy
|
"UserTurnStartedParams",
|
||||||
|
"VADUserTurnStartStrategy",
|
||||||
|
]
|
||||||
|
|||||||
@@ -4,14 +4,15 @@
|
|||||||
# SPDX-License-Identifier: BSD 2-Clause License
|
# SPDX-License-Identifier: BSD 2-Clause License
|
||||||
#
|
#
|
||||||
|
|
||||||
from pipecat.turns.user_stop.base_user_turn_stop_strategy import (
|
from .base_user_turn_stop_strategy import BaseUserTurnStopStrategy, UserTurnStoppedParams
|
||||||
BaseUserTurnStopStrategy,
|
from .external_user_turn_stop_strategy import ExternalUserTurnStopStrategy
|
||||||
UserTurnStoppedParams,
|
from .transcription_user_turn_stop_strategy import TranscriptionUserTurnStopStrategy
|
||||||
)
|
from .turn_analyzer_user_turn_stop_strategy import TurnAnalyzerUserTurnStopStrategy
|
||||||
from pipecat.turns.user_stop.external_user_turn_stop_strategy import ExternalUserTurnStopStrategy
|
|
||||||
from pipecat.turns.user_stop.transcription_user_turn_stop_strategy import (
|
__all__ = [
|
||||||
TranscriptionUserTurnStopStrategy,
|
"BaseUserTurnStopStrategy",
|
||||||
)
|
"ExternalUserTurnStopStrategy",
|
||||||
from pipecat.turns.user_stop.turn_analyzer_user_turn_stop_strategy import (
|
"UserTurnStoppedParams",
|
||||||
TurnAnalyzerUserTurnStopStrategy,
|
"TranscriptionUserTurnStopStrategy",
|
||||||
)
|
"TurnAnalyzerUserTurnStopStrategy",
|
||||||
|
]
|
||||||
|
|||||||
@@ -40,7 +40,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
|
|||||||
LLMUserAggregatorParams,
|
LLMUserAggregatorParams,
|
||||||
)
|
)
|
||||||
from pipecat.tests.utils import SleepFrame, run_test
|
from pipecat.tests.utils import SleepFrame, run_test
|
||||||
from pipecat.turns.mute import FirstSpeechUserMuteStrategy, FunctionCallUserMuteStrategy
|
from pipecat.turns.user_mute import FirstSpeechUserMuteStrategy, FunctionCallUserMuteStrategy
|
||||||
from pipecat.turns.user_stop import TranscriptionUserTurnStopStrategy
|
from pipecat.turns.user_stop import TranscriptionUserTurnStopStrategy
|
||||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||||
|
|
||||||
|
|||||||
@@ -15,7 +15,7 @@ from pipecat.frames.frames import (
|
|||||||
FunctionCallsStartedFrame,
|
FunctionCallsStartedFrame,
|
||||||
InterruptionFrame,
|
InterruptionFrame,
|
||||||
)
|
)
|
||||||
from pipecat.turns.mute import (
|
from pipecat.turns.user_mute import (
|
||||||
AlwaysUserMuteStrategy,
|
AlwaysUserMuteStrategy,
|
||||||
FirstSpeechUserMuteStrategy,
|
FirstSpeechUserMuteStrategy,
|
||||||
FunctionCallUserMuteStrategy,
|
FunctionCallUserMuteStrategy,
|
||||||
|
|||||||
Reference in New Issue
Block a user