fix: FunctionFilter adds block_system_frame arg

This commit is contained in:
Mark Backman
2025-10-22 10:48:48 -04:00
parent f1040100f4
commit 5b921fc054
4 changed files with 166 additions and 7 deletions

View File

@@ -9,9 +9,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed
- `FunctionFilter` now has a `block_system_frames` arg, which controls whether
or not SystemFrames are filtered.
- Upgraded `aws_sdk_bedrock_runtime` to v0.1.1 to resolve potential CPU issues
when running `AWSNovaSonicLLMService`.
### Fixed
- Fixed an issue in `ServiceSwitcher` where the `STTService`s would result in
all STT services producing `TranscriptionFrame`s.
## [0.0.91] - 2025-10-21
### Added

View File

@@ -0,0 +1,138 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
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, ManuallySwitchServiceFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.service_switcher import ServiceSwitcher, ServiceSwitcherStrategyManual
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.stt import CartesiaSTTService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.stt_service import STTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
load_dotenv(override=True)
# 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=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt_cartesia = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
stt_deepgram = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
stt_switcher = ServiceSwitcher(
services=[stt_cartesia, stt_deepgram], strategy_type=ServiceSwitcherStrategyManual
)
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"))
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 = LLMContext(messages)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt_switcher,
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # 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.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
await asyncio.sleep(15)
print(f"Switching to {stt_deepgram}")
await task.queue_frames([ManuallySwitchServiceFrame(service=stt_deepgram)])
@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()

View File

@@ -138,13 +138,13 @@ class ServiceSwitcher(ParallelPipeline, Generic[StrategyType]):
active_service: The currently active service.
direction: The direction of frame flow to filter.
"""
self._wrapped_service = wrapped_service
self._active_service = active_service
async def filter(_: Frame) -> bool:
return self._wrapped_service == self._active_service
super().__init__(filter, direction)
self._wrapped_service = wrapped_service
self._active_service = active_service
super().__init__(filter, direction, block_system_frames=True)
async def process_frame(self, frame, direction):
"""Process a frame through the filter, handling special internal filter-updating frames."""

View File

@@ -12,7 +12,7 @@ allowing for flexible frame filtering logic in processing pipelines.
from typing import Awaitable, Callable
from pipecat.frames.frames import EndFrame, Frame, SystemFrame
from pipecat.frames.frames import CancelFrame, EndFrame, Frame, StartFrame, SystemFrame
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
@@ -28,6 +28,7 @@ class FunctionFilter(FrameProcessor):
self,
filter: Callable[[Frame], Awaitable[bool]],
direction: FrameDirection = FrameDirection.DOWNSTREAM,
block_system_frames: bool = False,
):
"""Initialize the function filter.
@@ -36,10 +37,12 @@ class FunctionFilter(FrameProcessor):
frame should pass through, False otherwise.
direction: The direction to apply filtering. Only frames moving in
this direction will be filtered. Defaults to DOWNSTREAM.
block_system_frames: Whether to block system frames. Defaults to False.
"""
super().__init__()
self._filter = filter
self._direction = direction
self._block_system_frames = block_system_frames
#
# Frame processor
@@ -49,9 +52,19 @@ class FunctionFilter(FrameProcessor):
# direction of this gate
def _should_passthrough_frame(self, frame, direction):
"""Check if a frame should pass through without filtering."""
# Ignore system frames, end frames and frames that are not following the
# direction of this gate
return isinstance(frame, (SystemFrame, EndFrame)) or direction != self._direction
# Always passthrough frames in the wrong direction
if direction != self._direction:
return True
# Always passthrough lifecycle frames
if isinstance(frame, (StartFrame, EndFrame, CancelFrame)):
return True
# If not blocking system frames, passthrough all other system frames
if not self._block_system_frames and isinstance(frame, SystemFrame):
return True
return False
async def process_frame(self, frame: Frame, direction: FrameDirection):
"""Process a frame through the filter.