From abf015026177d4c9f5d60485af89ce30a3d7b61b Mon Sep 17 00:00:00 2001 From: vipyne Date: Wed, 15 Oct 2025 10:45:36 -0500 Subject: [PATCH 1/3] add 47-custom-frame-processor.py to foundational examples --- .../foundational/47-custom-frame-processor.py | 223 ++++++++++++++++++ 1 file changed, 223 insertions(+) create mode 100644 examples/foundational/47-custom-frame-processor.py diff --git a/examples/foundational/47-custom-frame-processor.py b/examples/foundational/47-custom-frame-processor.py new file mode 100644 index 000000000..7de01ab17 --- /dev/null +++ b/examples/foundational/47-custom-frame-processor.py @@ -0,0 +1,223 @@ +# +# Copyright (c) 2024–2025, Daily +# +# SPDX-License-Identifier: BSD 2-Clause License +# + +import io +import os +import re + +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 ( + BotStartedSpeakingFrame, + BotStoppedSpeakingFrame, + CancelFrame, + EndFrame, + Frame, + FunctionCallResultFrame, + InputAudioRawFrame, + InterruptionFrame, + LLMRunFrame, + LLMTextFrame, + StartFrame, + UserStartedSpeakingFrame, + UserStoppedSpeakingFrame, + VADUserStartedSpeakingFrame, +) +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 +from pipecat.processors.frame_processor import FrameDirection, FrameProcessor +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.cartesia.tts import CartesiaTTSService +from pipecat.services.deepgram.stt import DeepgramSTTService +from pipecat.services.openai.llm import OpenAILLMService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.daily.transport import DailyParams + +load_dotenv(override=True) + + +class CustomFrameProcessor(FrameProcessor): + """CustomFrameProcessor does 3 things: + + 1. keeps count of `InputAudioRawFrame` frames and logs count + when a `UserStoppedSpeakingFrame` is emitted. + + 2. Filters `LLMTextFrame` frames and replaces "the" with "the pumpkin". + + 3. Logs the following frames: + BotStartedSpeakingFrame + BotStoppedSpeakingFrame + CancelFrame + EndFrame + InterruptionFrame + StartFrame + UserStartedSpeakingFrame + VADUserStartedSpeakingFrame + + 4. Always pushes all frames + + """ + + def __init__(self): + super().__init__() + self._raw_audio_input_frame_count = 0 + + async def process_frame(self, frame: Frame, direction: FrameDirection): + await super().process_frame(frame, direction) + + #### 1. + # InputAudioRawFrames are noisy- probably don't want to log every instance + # keep a count and only log it when we see `UserStoppedSpeakingFrame` + if isinstance(frame, InputAudioRawFrame): + self._raw_audio_input_frame_count = self._raw_audio_input_frame_count + 1 + await self.push_frame(frame, direction) + + elif isinstance(frame, UserStoppedSpeakingFrame): + logger.info( + f"* * frame: {frame}; number of `InputAudioRawFrame` frames so far: {self._raw_audio_input_frame_count}" + ) + await self.push_frame(frame, direction) + + #### 2. + # everytime the LLM's response includes "the", replace it with "the pumpkin" + elif isinstance(frame, LLMTextFrame): + if "the" in frame.text: + text = re.sub(r" the\b", " the pumpkin", frame.text) + frame.text = text + await self.push_frame(frame, direction) + + #### 3. + # frames types to log + elif isinstance( + frame, + ( + BotStartedSpeakingFrame, + BotStoppedSpeakingFrame, + CancelFrame, + EndFrame, + InterruptionFrame, + StartFrame, + UserStartedSpeakingFrame, + VADUserStartedSpeakingFrame, + ), + ): + logger.info(f"* * frame: {frame}") + await self.push_frame(frame, direction) + + #### 4. + # ALWAYS push all other frames + else: + # SUPER IMPORTANT: always push every frame! + await self.push_frame(frame, direction) + + +# 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()), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + audio_out_enabled=True, + video_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 = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) + + tts = CartesiaTTSService( + api_key=os.getenv("CARTESIA_API_KEY"), + voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady + ) + + llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY")) + + custom_frame_processor = CustomFrameProcessor() + + 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(), + stt, + context_aggregator.user(), + llm, + custom_frame_processor, # filter and log frames + tts, + transport.output(), + context_aggregator.assistant(), + ] + ) + + 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: {client}") + # Kick off the conversation. + messages.append( + { + "role": "system", + "content": "Please introduce yourself to the user and inform them that your responses illustrate use of a Custom Frame Processor.", + } + ) + 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() From 8b24bae9c5f60e1af56859a541c66bb9a4a0bbb9 Mon Sep 17 00:00:00 2001 From: vipyne Date: Tue, 21 Oct 2025 11:42:06 -0500 Subject: [PATCH 2/3] pr notes --- .../foundational/47-custom-frame-processor.py | 100 +++++------------- 1 file changed, 25 insertions(+), 75 deletions(-) diff --git a/examples/foundational/47-custom-frame-processor.py b/examples/foundational/47-custom-frame-processor.py index 7de01ab17..26fe86391 100644 --- a/examples/foundational/47-custom-frame-processor.py +++ b/examples/foundational/47-custom-frame-processor.py @@ -16,20 +16,9 @@ from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnal from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.audio.vad.vad_analyzer import VADParams from pipecat.frames.frames import ( - BotStartedSpeakingFrame, - BotStoppedSpeakingFrame, - CancelFrame, - EndFrame, Frame, - FunctionCallResultFrame, - InputAudioRawFrame, - InterruptionFrame, LLMRunFrame, - LLMTextFrame, - StartFrame, - UserStartedSpeakingFrame, - UserStoppedSpeakingFrame, - VADUserStartedSpeakingFrame, + MetricsFrame, ) from pipecat.pipeline.pipeline import Pipeline from pipecat.pipeline.runner import PipelineRunner @@ -48,76 +37,42 @@ from pipecat.transports.daily.transport import DailyParams load_dotenv(override=True) -class CustomFrameProcessor(FrameProcessor): - """CustomFrameProcessor does 3 things: +def format_metrics(metrics, indent=0): + lines = [] + tab = "\t" * indent - 1. keeps count of `InputAudioRawFrame` frames and logs count - when a `UserStoppedSpeakingFrame` is emitted. + for metric in metrics: + lines.append(tab + type(metric).__name__) + for field, value in vars(metric).items(): + if hasattr(value, "__dict__") and not isinstance( + value, (str, int, float, bool, type(None)) + ): + lines.append(f"{tab}\t{field}={type(value).__name__}") + for k, v in vars(value).items(): + lines.append(f"{tab}\t\t{k}={repr(v)}") + else: + lines.append(f"{tab}\t{field}={repr(value)}") - 2. Filters `LLMTextFrame` frames and replaces "the" with "the pumpkin". + return "\n".join(lines) - 3. Logs the following frames: - BotStartedSpeakingFrame - BotStoppedSpeakingFrame - CancelFrame - EndFrame - InterruptionFrame - StartFrame - UserStartedSpeakingFrame - VADUserStartedSpeakingFrame - 4. Always pushes all frames +class MetricsFrameLogger(FrameProcessor): + """MetricsFrameLogger logs all MetericsFrames. + AND it Always pushes all frames. """ def __init__(self): super().__init__() - self._raw_audio_input_frame_count = 0 async def process_frame(self, frame: Frame, direction: FrameDirection): await super().process_frame(frame, direction) - #### 1. - # InputAudioRawFrames are noisy- probably don't want to log every instance - # keep a count and only log it when we see `UserStoppedSpeakingFrame` - if isinstance(frame, InputAudioRawFrame): - self._raw_audio_input_frame_count = self._raw_audio_input_frame_count + 1 + if isinstance(frame, MetricsFrame): + logger.info(f"{frame.name}\n {format_metrics(frame.data)}") await self.push_frame(frame, direction) - elif isinstance(frame, UserStoppedSpeakingFrame): - logger.info( - f"* * frame: {frame}; number of `InputAudioRawFrame` frames so far: {self._raw_audio_input_frame_count}" - ) - await self.push_frame(frame, direction) - - #### 2. - # everytime the LLM's response includes "the", replace it with "the pumpkin" - elif isinstance(frame, LLMTextFrame): - if "the" in frame.text: - text = re.sub(r" the\b", " the pumpkin", frame.text) - frame.text = text - await self.push_frame(frame, direction) - - #### 3. - # frames types to log - elif isinstance( - frame, - ( - BotStartedSpeakingFrame, - BotStoppedSpeakingFrame, - CancelFrame, - EndFrame, - InterruptionFrame, - StartFrame, - UserStartedSpeakingFrame, - VADUserStartedSpeakingFrame, - ), - ): - logger.info(f"* * frame: {frame}") - await self.push_frame(frame, direction) - - #### 4. - # ALWAYS push all other frames + # ALWAYS push all frames else: # SUPER IMPORTANT: always push every frame! await self.push_frame(frame, direction) @@ -155,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY")) - custom_frame_processor = CustomFrameProcessor() + metrics_frame_processor = MetricsFrameLogger() messages = [ { @@ -173,10 +128,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): stt, context_aggregator.user(), llm, - custom_frame_processor, # filter and log frames tts, transport.output(), context_aggregator.assistant(), + metrics_frame_processor, # pretty print metrics frames ] ) @@ -193,12 +148,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): async def on_client_connected(transport, client): logger.info(f"Client connected: {client}") # Kick off the conversation. - messages.append( - { - "role": "system", - "content": "Please introduce yourself to the user and inform them that your responses illustrate use of a Custom Frame Processor.", - } - ) + messages.append({"role": "system", "content": "Please introduce yourself to the user."}) await task.queue_frames([LLMRunFrame()]) @transport.event_handler("on_client_disconnected") From 23385ca3d2d1645d0c6e4710916c35d11e7d8112 Mon Sep 17 00:00:00 2001 From: vipyne Date: Tue, 21 Oct 2025 11:43:47 -0500 Subject: [PATCH 3/3] replace foundational example 08-bots-arguing.py with 08-custom-frame-processor.py --- examples/foundational/08-bots-arguing.py | 147 ------------------ ...cessor.py => 08-custom-frame-processor.py} | 13 +- 2 files changed, 5 insertions(+), 155 deletions(-) delete mode 100644 examples/foundational/08-bots-arguing.py rename examples/foundational/{47-custom-frame-processor.py => 08-custom-frame-processor.py} (97%) diff --git a/examples/foundational/08-bots-arguing.py b/examples/foundational/08-bots-arguing.py deleted file mode 100644 index b84e945c3..000000000 --- a/examples/foundational/08-bots-arguing.py +++ /dev/null @@ -1,147 +0,0 @@ -import asyncio -import logging -import os -from typing import Tuple - -import aiohttp -from dotenv import load_dotenv - -from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMContextFrame, TextFrame -from pipecat.pipeline.pipeline import Pipeline -from pipecat.processors.aggregators import SentenceAggregator -from pipecat.processors.aggregators.llm_context import LLMContext -from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair -from pipecat.runner.daily import configure -from pipecat.services.azure import AzureLLMService, AzureTTSService -from pipecat.services.elevenlabs import ElevenLabsTTSService -from pipecat.services.fal import FalImageGenService -from pipecat.transports.daily.transport import DailyTransport - -load_dotenv(override=True) - -logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s") -logger = logging.getLogger("pipecat") -logger.setLevel(logging.DEBUG) - - -async def main(): - async with aiohttp.ClientSession() as session: - (room_url, _) = await configure(session) - - transport = DailyTransport( - room_url, - None, - "Respond bot", - duration_minutes=10, - mic_enabled=True, - mic_sample_rate=16000, - camera_enabled=True, - camera_width=1024, - camera_height=1024, - ) - - llm = AzureLLMService( - api_key=os.getenv("AZURE_CHATGPT_API_KEY"), - endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), - model=os.getenv("AZURE_CHATGPT_MODEL"), - ) - tts1 = AzureTTSService( - api_key=os.getenv("AZURE_SPEECH_API_KEY"), - region=os.getenv("AZURE_SPEECH_REGION"), - ) - tts2 = ElevenLabsTTSService( - api_key=os.getenv("ELEVENLABS_API_KEY"), - voice_id="jBpfuIE2acCO8z3wKNLl", - ) - dalle = FalImageGenService( - params=FalImageGenService.InputParams(image_size="1024x1024"), - aiohttp_session=session, - key=os.getenv("FAL_KEY"), - ) - - bot1_messages = [ - { - "role": "system", - "content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long.", - }, - ] - bot2_messages = [ - { - "role": "system", - "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich.", - }, - ] - - async def get_text_and_audio(messages) -> Tuple[str, bytearray]: - """This function streams text from the LLM and uses the TTS service to convert - that text to speech as it's received. - """ - source_queue = asyncio.Queue() - sink_queue = asyncio.Queue() - sentence_aggregator = SentenceAggregator() - pipeline = Pipeline([llm, sentence_aggregator, tts1], source_queue, sink_queue) - - await source_queue.put(LLMContextFrame(LLMContext(messages))) - await source_queue.put(EndFrame()) - await pipeline.run_pipeline() - - message = "" - all_audio = bytearray() - while sink_queue.qsize(): - frame = sink_queue.get_nowait() - if isinstance(frame, TextFrame): - message += frame.text - elif isinstance(frame, AudioFrame): - all_audio.extend(frame.audio) - - return (message, all_audio) - - async def get_bot1_statement(): - message, audio = await get_text_and_audio(bot1_messages) - - bot1_messages.append({"role": "assistant", "content": message}) - bot2_messages.append({"role": "user", "content": message}) - - return audio - - async def get_bot2_statement(): - message, audio = await get_text_and_audio(bot2_messages) - - bot2_messages.append({"role": "assistant", "content": message}) - bot1_messages.append({"role": "user", "content": message}) - - return audio - - async def argue(): - for i in range(100): - print(f"In iteration {i}") - - bot1_description = "A woman conservatively dressed as a librarian in a library surrounded by books, cartoon, serious, highly detailed" - - (audio1, image_data1) = await asyncio.gather( - get_bot1_statement(), dalle.run_image_gen(bot1_description) - ) - await transport.send_queue.put( - [ - ImageFrame(image_data1[1], image_data1[2]), - AudioFrame(audio1), - ] - ) - - bot2_description = "A cat dressed in a hot dog costume, cartoon, bright colors, funny, highly detailed" - - (audio2, image_data2) = await asyncio.gather( - get_bot2_statement(), dalle.run_image_gen(bot2_description) - ) - await transport.send_queue.put( - [ - ImageFrame(image_data2[1], image_data2[2]), - AudioFrame(audio2), - ] - ) - - await asyncio.gather(transport.run(), argue()) - - -if __name__ == "__main__": - asyncio.run(main()) diff --git a/examples/foundational/47-custom-frame-processor.py b/examples/foundational/08-custom-frame-processor.py similarity index 97% rename from examples/foundational/47-custom-frame-processor.py rename to examples/foundational/08-custom-frame-processor.py index 26fe86391..20da4f876 100644 --- a/examples/foundational/47-custom-frame-processor.py +++ b/examples/foundational/08-custom-frame-processor.py @@ -57,13 +57,10 @@ def format_metrics(metrics, indent=0): class MetricsFrameLogger(FrameProcessor): - """MetricsFrameLogger logs all MetericsFrames. + """MetricsFrameLogger formats and logs all MetericsFrames""" - AND it Always pushes all frames. - """ - - def __init__(self): - super().__init__() + def __init__(self, **kwargs): + super().__init__(**kwargs) async def process_frame(self, frame: Frame, direction: FrameDirection): await super().process_frame(frame, direction) @@ -110,8 +107,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY")) - metrics_frame_processor = MetricsFrameLogger() - messages = [ { "role": "system", @@ -122,6 +117,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): context = LLMContext(messages) context_aggregator = LLMContextAggregatorPair(context) + metrics_frame_processor = MetricsFrameLogger() + pipeline = Pipeline( [ transport.input(),