wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into aiortc_example

Browse Source
This commit is contained in:
Filipi Fuchter
2025-03-24 08:37:08 -03:00
parent 526f9c2e06 48e8d3968a
commit 5184d178ef
157 changed files with 5555 additions and 2264 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
src/pipecat/audio/utils.py
View File

@@ -18,23 +18,6 @@ def create_default_resampler(**kwargs) -> BaseAudioResampler:
return SOXRAudioResampler(**kwargs)
def resample_audio(audio: bytes, original_rate: int, target_rate: int) -> bytes:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'resample_audio()' is deprecated, use 'create_default_resampler()' instead.",
DeprecationWarning,
)
if original_rate == target_rate:
return audio
audio_data = np.frombuffer(audio, dtype=np.int16)
resampled_audio = soxr.resample(audio_data, original_rate, target_rate)
return resampled_audio.astype(np.int16).tobytes()
def mix_audio(audio1: bytes, audio2: bytes) -> bytes:
data1 = np.frombuffer(audio1, dtype=np.int16)
data2 = np.frombuffer(audio2, dtype=np.int16)

22
src/pipecat/frames/frames.py
View File

@@ -634,6 +634,15 @@ class FunctionCallInProgressFrame(SystemFrame):
function_name: str
tool_call_id: str
arguments: str
cancel_on_interruption: bool
@dataclass
class FunctionCallCancelFrame(SystemFrame):
"""A frame to signal a function call has been cancelled."""
function_name: str
tool_call_id: str
@dataclass
@@ -653,13 +662,19 @@ class TransportMessageUrgentFrame(SystemFrame):
@dataclass
class UserImageRequestFrame(SystemFrame):
"""A frame user to request an image from the given user."""
"""A frame to request an image from the given user. The frame might be
generated by a function call in which case the corresponding fields will be
properly set.
"""
user_id: str
context: Optional[Any] = None
function_name: Optional[str] = None
tool_call_id: Optional[str] = None
def __str__(self):
return f"{self.name}, user: {self.user_id}"
return f"{self.name}(user: {self.user_id}, function: {self.function_name}, request: {self.tool_call_id})"
@dataclass
@@ -689,10 +704,11 @@ class UserImageRawFrame(InputImageRawFrame):
"""An image associated to a user."""
user_id: str
request: Optional[UserImageRequestFrame] = None
def __str__(self):
pts = format_pts(self.pts)
return f"{self.name}(pts: {pts}, user: {self.user_id}, size: {self.size}, format: {self.format})"
return f"{self.name}(pts: {pts}, user: {self.user_id}, size: {self.size}, format: {self.format}, request: {self.request})"
@dataclass

6
src/pipecat/pipeline/runner.py
View File

@@ -40,12 +40,18 @@ class PipelineRunner(BaseObject):
task.set_event_loop(self._loop)
await task.run()
del self._tasks[task.name]
# Cleanup base object.
await self.cleanup()
# If we are cancelling through a signal, make sure we wait for it so
# everything gets cleaned up nicely.
if self._sig_task:
await self._sig_task
if self._force_gc:
self._gc_collect()
logger.debug(f"Runner {self} finished running {task}")
async def stop_when_done(self):

165
src/pipecat/pipeline/task.py
View File

@@ -5,7 +5,8 @@
#
import asyncio
from typing import Any, AsyncIterable, Dict, Iterable, List, Optional
import time
from typing import Any, AsyncIterable, Dict, Iterable, List, Optional, Tuple, Type
from loguru import logger
from pydantic import BaseModel, ConfigDict
@@ -13,6 +14,7 @@ from pydantic import BaseModel, ConfigDict
from pipecat.clocks.base_clock import BaseClock
from pipecat.clocks.system_clock import SystemClock
from pipecat.frames.frames import (
BotSpeakingFrame,
CancelFrame,
CancelTaskFrame,
EndFrame,
@@ -20,6 +22,7 @@ from pipecat.frames.frames import (
ErrorFrame,
Frame,
HeartbeatFrame,
LLMFullResponseEndFrame,
MetricsFrame,
StartFrame,
StopFrame,
@@ -119,12 +122,42 @@ class PipelineTaskSink(FrameProcessor):
class PipelineTask(BaseTask):
"""Manages the execution of a pipeline, handling frame processing and task lifecycle.
It has a couple of event handlers `on_frame_reached_upstream` and
`on_frame_reached_downstream` that are called when upstream frames or
downstream frames reach both ends of pipeline. By default, the events
handlers will not be called unless some filters are set using
`set_reached_upstream_filter` and `set_reached_downstream_filter`.
@task.event_handler("on_frame_reached_upstream")
async def on_frame_reached_upstream(task, frame):
...
@task.event_handler("on_frame_reached_downstream")
async def on_frame_reached_downstream(task, frame):
...
It also has an event handler that detects when the pipeline is idle. By
default, a pipeline is idle if no `BotSpeakingFrame` or
`LLMFullResponseEndFrame` are received within `idle_timeout_secs`.
@task.event_handler("on_idle_timeout")
async def on_idle_timeout(task):
...
Args:
pipeline: The pipeline to execute.
params: Configuration parameters for the pipeline.
observers: List of observers for monitoring pipeline execution.
clock: Clock implementation for timing operations.
check_dangling_tasks: Whether to check for processors' tasks finishing properly.
idle_timeout_secs: Timeout (in seconds) to consider pipeline idle or
None. If a pipeline is idle the pipeline task will be cancelled
automatically.
idle_timeout_frames: A tuple with the frames that should trigger an idle
timeout if not received withing `idle_timeout_seconds`.
cancel_on_idle_timeout: Whether the pipeline task should be cancelled if
the idle timeout is reached.
"""
def __init__(
@@ -136,12 +169,21 @@ class PipelineTask(BaseTask):
clock: BaseClock = SystemClock(),
task_manager: Optional[BaseTaskManager] = None,
check_dangling_tasks: bool = True,
idle_timeout_secs: Optional[float] = 300,
idle_timeout_frames: Tuple[Type[Frame], ...] = (
BotSpeakingFrame,
LLMFullResponseEndFrame,
),
cancel_on_idle_timeout: bool = True,
):
super().__init__()
self._pipeline = pipeline
self._clock = clock
self._params = params
self._check_dangling_tasks = check_dangling_tasks
self._idle_timeout_secs = idle_timeout_secs
self._idle_timeout_frames = idle_timeout_frames
self._cancel_on_idle_timeout = cancel_on_idle_timeout
if self._params.observers:
import warnings
@@ -163,20 +205,47 @@ class PipelineTask(BaseTask):
# This is the heartbeat queue. When a heartbeat frame is received in the
# down queue we add it to the heartbeat queue for processing.
self._heartbeat_queue = asyncio.Queue()
# This is the idle queue. When frames are received downstream they are
# put in the queue. If no frame is received the pipeline is considered
# idle.
self._idle_queue = asyncio.Queue()
# This event is used to indicate a finalize frame (e.g. EndFrame,
# StopFrame) has been received in the down queue.
self._pipeline_end_event = asyncio.Event()
# This is a source processor that we connect to the provided
# pipeline. This source processor allows up to receive and react to
# upstream frames.
self._source = PipelineTaskSource(self._up_queue)
self._source.link(pipeline)
# This is a sink processor that we connect to the provided
# pipeline. This sink processor allows up to receive and react to
# downstream frames.
self._sink = PipelineTaskSink(self._down_queue)
pipeline.link(self._sink)
# This task maneger will handle all the asyncio tasks created by this
# PipelineTask and its frame processors.
self._task_manager = task_manager or TaskManager()
# The task observer acts as a proxy to the provided observers. This way,
# we only need to pass a single observer (using the StartFrame) which
# then just acts as a proxy.
self._observer = TaskObserver(observers=observers, task_manager=self._task_manager)
# These events can be used to check which frames make it to the source
# or sink processors. Instead of calling the event handlers for every
# frame the user needs to specify which events they are interested
# in. This is mainly for efficiency reason because each event handler
# creates a task and most likely you only care about one or two frame
# types.
self._reached_upstream_types: Tuple[Type[Frame], ...] = ()
self._reached_downstream_types: Tuple[Type[Frame], ...] = ()
self._register_event_handler("on_frame_reached_upstream")
self._register_event_handler("on_frame_reached_downstream")
self._register_event_handler("on_idle_timeout")
@property
def params(self) -> PipelineParams:
"""Returns the pipeline parameters of this task."""
@@ -185,6 +254,20 @@ class PipelineTask(BaseTask):
def set_event_loop(self, loop: asyncio.AbstractEventLoop):
self._task_manager.set_event_loop(loop)
def set_reached_upstream_filter(self, types: Tuple[Type[Frame], ...]):
"""Sets which frames will be checked before calling the
on_frame_reached_upstream event handler.
"""
self._reached_upstream_types = types
def set_reached_downstream_filter(self, types: Tuple[Type[Frame], ...]):
"""Sets which frames will be checked before calling the
on_frame_reached_downstream event handler.
"""
self._reached_downstream_types = types
def has_finished(self) -> bool:
"""Indicates whether the tasks has finished. That is, all processors
have stopped.
@@ -277,19 +360,30 @@ class PipelineTask(BaseTask):
self._heartbeat_monitor_handler(), f"{self}::_heartbeat_monitor_handler"
)
def _maybe_start_idle_task(self):
if self._idle_timeout_secs:
self._idle_monitor_task = self._task_manager.create_task(
self._idle_monitor_handler(), f"{self}::_idle_monitor_handler"
)
async def _cancel_tasks(self):
await self._maybe_cancel_heartbeat_tasks()
await self._observer.stop()
await self._task_manager.cancel_task(self._process_up_task)
await self._task_manager.cancel_task(self._process_down_task)
await self._observer.stop()
await self._maybe_cancel_heartbeat_tasks()
await self._maybe_cancel_idle_task()
async def _maybe_cancel_heartbeat_tasks(self):
if self._params.enable_heartbeats:
await self._task_manager.cancel_task(self._heartbeat_push_task)
await self._task_manager.cancel_task(self._heartbeat_monitor_task)
async def _maybe_cancel_idle_task(self):
if self._idle_timeout_secs:
await self._task_manager.cancel_task(self._idle_monitor_task)
def _initial_metrics_frame(self) -> MetricsFrame:
processors = self._pipeline.processors_with_metrics()
data = []
@@ -303,6 +397,10 @@ class PipelineTask(BaseTask):
self._pipeline_end_event.clear()
async def _cleanup(self, cleanup_pipeline: bool):
# Cleanup base object.
await self.cleanup()
# Cleanup pipeline processors.
await self._source.cleanup()
if cleanup_pipeline:
await self._pipeline.cleanup()
@@ -311,12 +409,13 @@ class PipelineTask(BaseTask):
async def _process_push_queue(self):
"""This is the task that runs the pipeline for the first time by sending
a StartFrame and by pushing any other frames queued by the user. It runs
until the tasks is canceled or stopped (e.g. with an EndFrame).
until the tasks is cancelled or stopped (e.g. with an EndFrame).
"""
self._clock.start()
self._maybe_start_heartbeat_tasks()
self._maybe_start_idle_task()
start_frame = StartFrame(
clock=self._clock,
@@ -356,6 +455,10 @@ class PipelineTask(BaseTask):
"""
while True:
frame = await self._up_queue.get()
if isinstance(frame, self._reached_upstream_types):
await self._call_event_handler("on_frame_reached_upstream", frame)
if isinstance(frame, EndTaskFrame):
# Tell the task we should end nicely.
await self.queue_frame(EndFrame())
@@ -366,12 +469,14 @@ class PipelineTask(BaseTask):
# Tell the task we should stop nicely.
await self.queue_frame(StopFrame())
elif isinstance(frame, ErrorFrame):
logger.error(f"Error running app: {frame}")
if frame.fatal:
logger.error(f"A fatal error occurred: {frame}")
# Cancel all tasks downstream.
await self.queue_frame(CancelFrame())
# Tell the task we should stop.
await self.queue_frame(StopTaskFrame())
else:
logger.warning(f"Something went wrong: {frame}")
self._up_queue.task_done()
async def _process_down_queue(self):
@@ -383,6 +488,14 @@ class PipelineTask(BaseTask):
"""
while True:
frame = await self._down_queue.get()
# Queue received frame to the idle queue so we can monitor idle
# pipelines.
await self._idle_queue.put(frame)
if isinstance(frame, self._reached_downstream_types):
await self._call_event_handler("on_frame_reached_downstream", frame)
if isinstance(frame, (EndFrame, StopFrame)):
self._pipeline_end_event.set()
elif isinstance(frame, HeartbeatFrame):
@@ -417,6 +530,48 @@ class PipelineTask(BaseTask):
f"{self}: heartbeat frame not received for more than {wait_time} seconds"
)
async def _idle_monitor_handler(self):
"""This tasks monitors activity in the pipeline. If no frames are
received (heartbeats don't count) the pipeline is considered idle.
"""
running = True
last_frame_time = 0
while running:
try:
frame = await asyncio.wait_for(
self._idle_queue.get(), timeout=self._idle_timeout_secs
)
if isinstance(frame, StartFrame) or isinstance(frame, self._idle_timeout_frames):
# If we find a StartFrame or one of the frames that prevents a
# time out we update the time.
last_frame_time = time.time()
else:
# If we find any other frame we check if the pipeline is
# idle by checking the last time we received one of the
# valid frames.
diff_time = time.time() - last_frame_time
if diff_time >= self._idle_timeout_secs:
running = await self._idle_timeout_detected()
self._idle_queue.task_done()
except asyncio.TimeoutError:
running = await self._idle_timeout_detected()
async def _idle_timeout_detected(self) -> bool:
"""Logic for when the pipeline is idle.
Returns:
bool: Whther the pipeline task is being cancelled or not.
"""
await self._call_event_handler("on_idle_timeout")
if self._cancel_on_idle_timeout:
logger.warning(f"Idle pipeline detected, cancelling pipeline task...")
await self.cancel()
return False
return True
def _print_dangling_tasks(self):
tasks = [t.get_name() for t in self._task_manager.current_tasks()]
if tasks:

282
src/pipecat/processors/aggregators/llm_response.py
View File

@@ -5,16 +5,21 @@
#
import asyncio
import time
from abc import abstractmethod
from typing import List
from typing import Dict, List
from loguru import logger
from pipecat.frames.frames import (
BotStoppedSpeakingFrame,
CancelFrame,
EmulateUserStartedSpeakingFrame,
EmulateUserStoppedSpeakingFrame,
EndFrame,
Frame,
FunctionCallCancelFrame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
InterimTranscriptionFrame,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
@@ -23,10 +28,12 @@ from pipecat.frames.frames import (
LLMMessagesUpdateFrame,
LLMSetToolsFrame,
LLMTextFrame,
OpenAILLMContextAssistantTimestampFrame,
StartFrame,
StartInterruptionFrame,
TextFrame,
TranscriptionFrame,
UserImageRawFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
@@ -35,6 +42,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
OpenAILLMContextFrame,
)
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.utils.time import time_now_iso8601
class LLMFullResponseAggregator(FrameProcessor):
@@ -139,68 +147,20 @@ class BaseLLMResponseAggregator(FrameProcessor):
pass
@abstractmethod
async def push_aggregation(self):
async def handle_aggregation(self, aggregation: str):
"""Adds the given aggregation to the aggregator. The aggregator can use
a simple list of message or a context. It doesn't not push any frames.
"""
pass
class LLMResponseAggregator(BaseLLMResponseAggregator):
"""This is a base LLM aggregator that uses a simple list of messages to
store the conversation. It pushes `LLMMessagesFrame` as an aggregation
frame.
"""
def __init__(
self,
*,
messages: List[dict],
role: str = "user",
**kwargs,
):
super().__init__(**kwargs)
self._messages = messages
self._role = role
self._aggregation = ""
self.reset()
@property
def messages(self) -> List[dict]:
return self._messages
@property
def role(self) -> str:
return self._role
def add_messages(self, messages):
self._messages.extend(messages)
def set_messages(self, messages):
self.reset()
self._messages.clear()
self._messages.extend(messages)
def set_tools(self, tools):
pass
def reset(self):
self._aggregation = ""
@abstractmethod
async def push_aggregation(self):
if len(self._aggregation) > 0:
self._messages.append({"role": self._role, "content": self._aggregation})
"""Pushes the current aggregation. For example, iN the case of context
aggregation this might push a new context frame.
# Reset the aggregation. Reset it before pushing it down, otherwise
# if the tasks gets cancelled we won't be able to clear things up.
self._aggregation = ""
frame = LLMMessagesFrame(self._messages)
await self.push_frame(frame)
# Reset our accumulator state.
self.reset()
"""
pass
class LLMContextResponseAggregator(BaseLLMResponseAggregator):
@@ -247,20 +207,6 @@ class LLMContextResponseAggregator(BaseLLMResponseAggregator):
def reset(self):
self._aggregation = ""
async def push_aggregation(self):
if len(self._aggregation) > 0:
self._context.add_message({"role": self.role, "content": self._aggregation})
# Reset the aggregation. Reset it before pushing it down, otherwise
# if the tasks gets cancelled we won't be able to clear things up.
self._aggregation = ""
frame = OpenAILLMContextFrame(self._context)
await self.push_frame(frame)
# Reset our accumulator state.
self.reset()
class LLMUserContextAggregator(LLMContextResponseAggregator):
"""This is a user LLM aggregator that uses an LLM context to store the
@@ -275,26 +221,26 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
self,
context: OpenAILLMContext,
aggregation_timeout: float = 1.0,
bot_interruption_timeout: float = 2.0,
**kwargs,
):
super().__init__(context=context, role="user", **kwargs)
self._aggregation_timeout = aggregation_timeout
self._bot_interruption_timeout = bot_interruption_timeout
self._seen_interim_results = False
self._user_speaking = False
self._last_user_speaking_time = 0
self._emulating_vad = False
self._waiting_for_aggregation = False
self._aggregation_event = asyncio.Event()
self._aggregation_task = None
self.reset()
def reset(self):
super().reset()
self._seen_interim_results = False
self._waiting_for_aggregation = False
async def handle_aggregation(self, aggregation: str):
self._context.add_message({"role": self.role, "content": self._aggregation})
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
@@ -331,6 +277,17 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
else:
await self.push_frame(frame, direction)
async def push_aggregation(self):
if len(self._aggregation) > 0:
await self.handle_aggregation(self._aggregation)
# Reset the aggregation. Reset it before pushing it down, otherwise
# if the tasks gets cancelled we won't be able to clear things up.
self.reset()
frame = OpenAILLMContextFrame(self._context)
await self.push_frame(frame)
async def _start(self, frame: StartFrame):
self._create_aggregation_task()
@@ -341,12 +298,14 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
await self._cancel_aggregation_task()
async def _handle_user_started_speaking(self, _: UserStartedSpeakingFrame):
self._last_user_speaking_time = time.time()
self._user_speaking = True
self._waiting_for_aggregation = True
async def _handle_user_stopped_speaking(self, _: UserStoppedSpeakingFrame):
self._last_user_speaking_time = time.time()
self._user_speaking = False
# We just stopped speaking. Let's see if there's some aggregation to
# push. If the last thing we saw is an interim transcription, let's wait
# pushing the aggregation as we will probably get a final transcription.
if not self._seen_interim_results:
await self.push_aggregation()
@@ -399,18 +358,13 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
frame we might want to interrupt the bot.
"""
if not self._user_speaking:
diff_time = time.time() - self._last_user_speaking_time
if diff_time > self._bot_interruption_timeout:
# If we reach this case we received a transcription but VAD was
# not able to detect voice (e.g. when you whisper a short
# utterance). So, we need to emulate VAD (i.e. user
# start/stopped speaking).
await self.push_frame(EmulateUserStartedSpeakingFrame(), FrameDirection.UPSTREAM)
self._emulating_vad = True
# Reset time so we don't interrupt again right away.
self._last_user_speaking_time = time.time()
if not self._user_speaking and not self._waiting_for_aggregation:
# If we reach this case we received a transcription but VAD was not
# able to detect voice (e.g. when you whisper a short
# utterance). So, we need to emulate VAD (i.e. user start/stopped
# speaking).
await self.push_frame(EmulateUserStartedSpeakingFrame(), FrameDirection.UPSTREAM)
self._emulating_vad = True
class LLMAssistantContextAggregator(LLMContextResponseAggregator):
@@ -424,17 +378,29 @@ class LLMAssistantContextAggregator(LLMContextResponseAggregator):
super().__init__(context=context, role="assistant", **kwargs)
self._expect_stripped_words = expect_stripped_words
self._started = False
self._started = 0
self._function_calls_in_progress: Dict[str, FunctionCallInProgressFrame] = {}
self.reset()
async def handle_aggregation(self, aggregation: str):
self._context.add_message({"role": "assistant", "content": aggregation})
async def handle_function_call_in_progress(self, frame: FunctionCallInProgressFrame):
pass
async def handle_function_call_result(self, frame: FunctionCallResultFrame):
pass
async def handle_function_call_cancel(self, frame: FunctionCallCancelFrame):
pass
async def handle_user_image_frame(self, frame: UserImageRawFrame):
pass
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if isinstance(frame, StartInterruptionFrame):
await self.push_aggregation()
# Reset anyways
self.reset()
await self._handle_interruptions(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, LLMFullResponseStartFrame):
await self._handle_llm_start(frame)
@@ -448,14 +414,116 @@ class LLMAssistantContextAggregator(LLMContextResponseAggregator):
self.set_messages(frame.messages)
elif isinstance(frame, LLMSetToolsFrame):
self.set_tools(frame.tools)
elif isinstance(frame, FunctionCallInProgressFrame):
await self._handle_function_call_in_progress(frame)
elif isinstance(frame, FunctionCallResultFrame):
await self._handle_function_call_result(frame)
elif isinstance(frame, FunctionCallCancelFrame):
await self._handle_function_call_cancel(frame)
elif isinstance(frame, UserImageRawFrame) and frame.request and frame.request.tool_call_id:
await self._handle_user_image_frame(frame)
elif isinstance(frame, BotStoppedSpeakingFrame):
await self.push_aggregation()
else:
await self.push_frame(frame, direction)
async def push_aggregation(self):
if not self._aggregation:
return
aggregation = self._aggregation.strip()
self.reset()
if aggregation:
await self.handle_aggregation(aggregation)
# Push context frame
await self.push_context_frame()
# Push timestamp frame with current time
timestamp_frame = OpenAILLMContextAssistantTimestampFrame(timestamp=time_now_iso8601())
await self.push_frame(timestamp_frame)
async def _handle_interruptions(self, frame: StartInterruptionFrame):
await self.push_aggregation()
self._started = 0
self.reset()
async def _handle_function_call_in_progress(self, frame: FunctionCallInProgressFrame):
logger.debug(
f"{self} FunctionCallInProgressFrame: [{frame.function_name}:{frame.tool_call_id}]"
)
await self.handle_function_call_in_progress(frame)
self._function_calls_in_progress[frame.tool_call_id] = frame
async def _handle_function_call_result(self, frame: FunctionCallResultFrame):
logger.debug(
f"{self} FunctionCallResultFrame: [{frame.function_name}:{frame.tool_call_id}]"
)
if frame.tool_call_id not in self._function_calls_in_progress:
logger.warning(
f"FunctionCallResultFrame tool_call_id [{frame.tool_call_id}] is not running"
)
return
del self._function_calls_in_progress[frame.tool_call_id]
properties = frame.properties
await self.handle_function_call_result(frame)
# Run inference if the function call result requires it.
if frame.result:
run_llm = False
if properties and properties.run_llm is not None:
# If the tool call result has a run_llm property, use it
run_llm = properties.run_llm
else:
# Default behavior is to run the LLM if there are no function calls in progress
run_llm = not bool(self._function_calls_in_progress)
if run_llm:
await self.push_context_frame(FrameDirection.UPSTREAM)
# Emit the on_context_updated callback once the function call
# result is added to the context
if properties and properties.on_context_updated:
await properties.on_context_updated()
async def _handle_function_call_cancel(self, frame: FunctionCallCancelFrame):
logger.debug(
f"{self} FunctionCallCancelFrame: [{frame.function_name}:{frame.tool_call_id}]"
)
if frame.tool_call_id not in self._function_calls_in_progress:
return
if self._function_calls_in_progress[frame.tool_call_id].cancel_on_interruption:
await self.handle_function_call_cancel(frame)
del self._function_calls_in_progress[frame.tool_call_id]
async def _handle_user_image_frame(self, frame: UserImageRawFrame):
logger.debug(
f"{self} UserImageRawFrame: [{frame.request.function_name}:{frame.request.tool_call_id}]"
)
if frame.request.tool_call_id not in self._function_calls_in_progress:
logger.warning(
f"UserImageRawFrame tool_call_id [{frame.request.tool_call_id}] is not running"
)
return
del self._function_calls_in_progress[frame.request.tool_call_id]
await self.handle_user_image_frame(frame)
await self.push_aggregation()
await self.push_context_frame(FrameDirection.UPSTREAM)
async def _handle_llm_start(self, _: LLMFullResponseStartFrame):
self._started = True
self._started += 1
async def _handle_llm_end(self, _: LLMFullResponseEndFrame):
self._started = False
self._started -= 1
await self.push_aggregation()
async def _handle_text(self, frame: TextFrame):
@@ -474,18 +542,15 @@ class LLMUserResponseAggregator(LLMUserContextAggregator):
async def push_aggregation(self):
if len(self._aggregation) > 0:
self._context.add_message({"role": self.role, "content": self._aggregation})
await self.handle_aggregation(self._aggregation)
# Reset the aggregation. Reset it before pushing it down, otherwise
# if the tasks gets cancelled we won't be able to clear things up.
self._aggregation = ""
self.reset()
frame = LLMMessagesFrame(self._context.messages)
await self.push_frame(frame)
# Reset our accumulator state.
self.reset()
class LLMAssistantResponseAggregator(LLMAssistantContextAggregator):
def __init__(self, messages: List[dict] = [], **kwargs):
@@ -493,14 +558,11 @@ class LLMAssistantResponseAggregator(LLMAssistantContextAggregator):
async def push_aggregation(self):
if len(self._aggregation) > 0:
self._context.add_message({"role": self.role, "content": self._aggregation})
await self.handle_aggregation(self._aggregation)
# Reset the aggregation. Reset it before pushing it down, otherwise
# if the tasks gets cancelled we won't be able to clear things up.
self._aggregation = ""
self.reset()
frame = LLMMessagesFrame(self._context.messages)
await self.push_frame(frame)
# Reset our accumulator state.
self.reset()

68
src/pipecat/processors/aggregators/openai_llm_context.py
View File

@@ -9,9 +9,8 @@ import copy
import io
import json
from dataclasses import dataclass
from typing import Any, Awaitable, Callable, List, Optional
from typing import Any, List, Optional
from loguru import logger
from openai._types import NOT_GIVEN, NotGiven
from openai.types.chat import (
ChatCompletionMessageParam,
@@ -22,12 +21,7 @@ from PIL import Image
from pipecat.adapters.base_llm_adapter import BaseLLMAdapter
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.frames.frames import (
AudioRawFrame,
Frame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
)
from pipecat.frames.frames import AudioRawFrame, Frame
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
# JSON custom encoder to handle bytes arrays so that we can log contexts
@@ -52,7 +46,6 @@ class OpenAILLMContext:
self._messages: List[ChatCompletionMessageParam] = messages if messages else []
self._tool_choice: ChatCompletionToolChoiceOptionParam | NotGiven = tool_choice
self._tools: List[ChatCompletionToolParam] | NotGiven | ToolsSchema = tools
self._user_image_request_context = {}
self._llm_adapter: Optional[BaseLLMAdapter] = None
def get_llm_adapter(self) -> Optional[BaseLLMAdapter]:
@@ -164,7 +157,7 @@ class OpenAILLMContext:
self._tool_choice = tool_choice
def set_tools(self, tools: List[ChatCompletionToolParam] | NotGiven | ToolsSchema = NOT_GIVEN):
if tools != NOT_GIVEN and len(tools) == 0:
if tools != NOT_GIVEN and isinstance(tools, list) and len(tools) == 0:
tools = NOT_GIVEN
self._tools = tools
@@ -187,61 +180,6 @@ class OpenAILLMContext:
# todo: implement for OpenAI models and others
pass
async def call_function(
self,
f: Callable[
[str, str, Any, FrameProcessor, "OpenAILLMContext", Callable[[Any], Awaitable[None]]],
Awaitable[None],
],
*,
function_name: str,
tool_call_id: str,
arguments: str,
llm: FrameProcessor,
run_llm: bool = True,
) -> None:
logger.info(f"Calling function {function_name} with arguments {arguments}")
# Push a SystemFrame downstream. This frame will let our assistant context aggregator
# know that we are in the middle of a function call. Some contexts/aggregators may
# not need this. But some definitely do (Anthropic, for example).
# Also push a SystemFrame upstream for use by other processors, like STTMuteFilter.
progress_frame_downstream = FunctionCallInProgressFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
)
progress_frame_upstream = FunctionCallInProgressFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
)
# Push frame both downstream and upstream
await llm.push_frame(progress_frame_downstream, FrameDirection.DOWNSTREAM)
await llm.push_frame(progress_frame_upstream, FrameDirection.UPSTREAM)
# Define a callback function that pushes a FunctionCallResultFrame upstream & downstream.
async def function_call_result_callback(result, *, properties=None):
result_frame_downstream = FunctionCallResultFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
result=result,
properties=properties,
)
result_frame_upstream = FunctionCallResultFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
result=result,
properties=properties,
)
await llm.push_frame(result_frame_downstream, FrameDirection.DOWNSTREAM)
await llm.push_frame(result_frame_upstream, FrameDirection.UPSTREAM)
await f(function_name, tool_call_id, arguments, llm, self, function_call_result_callback)
def create_wav_header(self, sample_rate, num_channels, bits_per_sample, data_size):
# RIFF chunk descriptor
header = bytearray()

13
src/pipecat/processors/filters/stt_mute_filter.py
View File

@@ -92,20 +92,9 @@ class STTMuteFilter(FrameProcessor):
**kwargs: Additional arguments passed to parent class
"""
def __init__(
self, *, config: STTMuteConfig, stt_service: Optional[FrameProcessor] = None, **kwargs
):
def __init__(self, *, config: STTMuteConfig, **kwargs):
super().__init__(**kwargs)
self._config = config
if stt_service is not None:
import warnings
warnings.warn(
"The stt_service parameter is deprecated and will be removed in a future version. "
"STTMuteFilter now manages mute state internally.",
DeprecationWarning,
stacklevel=2,
)
self._first_speech_handled = False
self._bot_is_speaking = False
self._function_call_in_progress = False

1
src/pipecat/processors/frame_processor.py
View File

@@ -164,6 +164,7 @@ class FrameProcessor(BaseObject):
await self._task_manager.wait_for_task(task, timeout)
async def cleanup(self):
await super().cleanup()
await self.__cancel_input_task()
await self.__cancel_push_task()

276
src/pipecat/processors/frameworks/rtvi.py
View File

@@ -29,6 +29,7 @@ from pipecat.frames.frames import (
CancelFrame,
DataFrame,
EndFrame,
EndTaskFrame,
ErrorFrame,
Frame,
FunctionCallResultFrame,
@@ -391,267 +392,6 @@ class RTVIServerMessageFrame(SystemFrame):
return f"{self.name}(data: {self.data})"
class RTVIFrameProcessor(FrameProcessor):
def __init__(self, direction: FrameDirection = FrameDirection.DOWNSTREAM, **kwargs):
super().__init__(**kwargs)
self._direction = direction
async def _push_transport_message_urgent(self, model: BaseModel, exclude_none: bool = True):
frame = TransportMessageUrgentFrame(message=model.model_dump(exclude_none=exclude_none))
await self.push_frame(frame, self._direction)
class RTVISpeakingProcessor(RTVIFrameProcessor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVISpeakingProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, (UserStartedSpeakingFrame, UserStoppedSpeakingFrame)):
await self._handle_interruptions(frame)
elif isinstance(frame, (BotStartedSpeakingFrame, BotStoppedSpeakingFrame)):
await self._handle_bot_speaking(frame)
async def _handle_interruptions(self, frame: Frame):
message = None
if isinstance(frame, UserStartedSpeakingFrame):
message = RTVIUserStartedSpeakingMessage()
elif isinstance(frame, UserStoppedSpeakingFrame):
message = RTVIUserStoppedSpeakingMessage()
if message:
await self._push_transport_message_urgent(message)
async def _handle_bot_speaking(self, frame: Frame):
message = None
if isinstance(frame, BotStartedSpeakingFrame):
message = RTVIBotStartedSpeakingMessage()
elif isinstance(frame, BotStoppedSpeakingFrame):
message = RTVIBotStoppedSpeakingMessage()
if message:
await self._push_transport_message_urgent(message)
class RTVIUserTranscriptionProcessor(RTVIFrameProcessor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVIUserTranscriptionProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, (TranscriptionFrame, InterimTranscriptionFrame)):
await self._handle_user_transcriptions(frame)
async def _handle_user_transcriptions(self, frame: Frame):
message = None
if isinstance(frame, TranscriptionFrame):
message = RTVIUserTranscriptionMessage(
data=RTVIUserTranscriptionMessageData(
text=frame.text, user_id=frame.user_id, timestamp=frame.timestamp, final=True
)
)
elif isinstance(frame, InterimTranscriptionFrame):
message = RTVIUserTranscriptionMessage(
data=RTVIUserTranscriptionMessageData(
text=frame.text, user_id=frame.user_id, timestamp=frame.timestamp, final=False
)
)
if message:
await self._push_transport_message_urgent(message)
class RTVIUserLLMTextProcessor(RTVIFrameProcessor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVIUserLLMTextProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, OpenAILLMContextFrame):
await self._handle_context(frame)
async def _handle_context(self, frame: OpenAILLMContextFrame):
messages = frame.context.messages
if len(messages) > 0:
message = messages[-1]
if message["role"] == "user":
content = message["content"]
if isinstance(content, list):
text = " ".join(item["text"] for item in content if "text" in item)
else:
text = content
rtvi_message = RTVIUserLLMTextMessage(data=RTVITextMessageData(text=text))
await self._push_transport_message_urgent(rtvi_message)
class RTVIBotTranscriptionProcessor(RTVIFrameProcessor):
def __init__(self):
super().__init__()
self._aggregation = ""
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVIBotTranscriptionProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, UserStartedSpeakingFrame):
await self._push_aggregation()
elif isinstance(frame, LLMTextFrame):
self._aggregation += frame.text
if match_endofsentence(self._aggregation):
await self._push_aggregation()
async def _push_aggregation(self):
if len(self._aggregation) > 0:
message = RTVIBotTranscriptionMessage(data=RTVITextMessageData(text=self._aggregation))
await self._push_transport_message_urgent(message)
self._aggregation = ""
class RTVIBotLLMProcessor(RTVIFrameProcessor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVIBotLLMProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, LLMFullResponseStartFrame):
await self._push_transport_message_urgent(RTVIBotLLMStartedMessage())
elif isinstance(frame, LLMFullResponseEndFrame):
await self._push_transport_message_urgent(RTVIBotLLMStoppedMessage())
elif isinstance(frame, LLMTextFrame):
message = RTVIBotLLMTextMessage(data=RTVITextMessageData(text=frame.text))
await self._push_transport_message_urgent(message)
class RTVIBotTTSProcessor(RTVIFrameProcessor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVIBotTTSProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, TTSStartedFrame):
await self._push_transport_message_urgent(RTVIBotTTSStartedMessage())
elif isinstance(frame, TTSStoppedFrame):
await self._push_transport_message_urgent(RTVIBotTTSStoppedMessage())
elif isinstance(frame, TTSTextFrame):
message = RTVIBotTTSTextMessage(data=RTVITextMessageData(text=frame.text))
await self._push_transport_message_urgent(message)
class RTVIMetricsProcessor(RTVIFrameProcessor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVIMetricsProcessor' is deprecated, use an 'RTVIObserver' instead.",
DeprecationWarning,
)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
await self.push_frame(frame, direction)
if isinstance(frame, MetricsFrame):
await self._handle_metrics(frame)
async def _handle_metrics(self, frame: MetricsFrame):
metrics = {}
for d in frame.data:
if isinstance(d, TTFBMetricsData):
if "ttfb" not in metrics:
metrics["ttfb"] = []
metrics["ttfb"].append(d.model_dump(exclude_none=True))
elif isinstance(d, ProcessingMetricsData):
if "processing" not in metrics:
metrics["processing"] = []
metrics["processing"].append(d.model_dump(exclude_none=True))
elif isinstance(d, LLMUsageMetricsData):
if "tokens" not in metrics:
metrics["tokens"] = []
metrics["tokens"].append(d.value.model_dump(exclude_none=True))
elif isinstance(d, TTSUsageMetricsData):
if "characters" not in metrics:
metrics["characters"] = []
metrics["characters"].append(d.model_dump(exclude_none=True))
message = RTVIMetricsMessage(data=metrics)
await self._push_transport_message_urgent(message)
class RTVIObserver(BaseObserver):
"""Pipeline frame observer for RTVI server message handling.
@@ -876,18 +616,6 @@ class RTVIProcessor(FrameProcessor):
self._input_transport = input_transport
self._input_transport.enable_audio_in_stream_on_start(False)
def observer(self) -> RTVIObserver:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'RTVI.observer()' is deprecated, instantiate an 'RTVIObserver' directly instead.",
DeprecationWarning,
)
return RTVIObserver(self)
def register_action(self, action: RTVIAction):
id = self._action_id(action.service, action.action)
self._registered_actions[id] = action
@@ -1039,7 +767,7 @@ class RTVIProcessor(FrameProcessor):
update_config = RTVIUpdateConfig.model_validate(message.data)
await self._handle_update_config(message.id, update_config)
case "disconnect-bot":
await self.push_frame(EndFrame())
await self.push_frame(EndTaskFrame(), FrameDirection.UPSTREAM)
case "action":
action = RTVIActionRun.model_validate(message.data)
action_frame = RTVIActionFrame(message_id=message.id, rtvi_action_run=action)

59
src/pipecat/processors/transcript_processor.py
View File

@@ -90,11 +90,62 @@ class AssistantTranscriptProcessor(BaseTranscriptProcessor):
self._aggregation_start_time: Optional[str] = None
async def _emit_aggregated_text(self):
"""Emit aggregated text as a transcript message."""
"""Aggregates and emits text fragments as a transcript message.
This method uses a heuristic to automatically detect whether text fragments
use pre-spacing (spaces at the beginning of fragments) or not, and applies
the appropriate joining strategy. It handles fragments from different TTS
services with different formatting patterns.
Examples:
Pre-spaced fragments (concatenated):
```
TTSTextFrame: ["Hello"]
TTSTextFrame: [" there"]
TTSTextFrame: ["!"]
TTSTextFrame: [" How"]
TTSTextFrame: ["'s"]
TTSTextFrame: [" it"]
TTSTextFrame: [" going"]
TTSTextFrame: ["?"]
```
Result: "Hello there! How's it going?"
Word-by-word fragments (joined with spaces):
```
TTSTextFrame: ["Hello"]
TTSTextFrame: ["there!"]
TTSTextFrame: ["How"]
TTSTextFrame: ["is"]
TTSTextFrame: ["it"]
TTSTextFrame: ["going?"]
```
Result: "Hello there! How is it going?"
"""
if self._current_text_parts and self._aggregation_start_time:
content = " ".join(self._current_text_parts).strip()
# Heuristic to detect pre-spaced fragments
uses_prespacing = False
if len(self._current_text_parts) > 1:
# Check if any fragment after the first one starts with whitespace
has_spaced_parts = any(
part and part[0].isspace() for part in self._current_text_parts[1:]
)
if has_spaced_parts:
uses_prespacing = True
# Apply appropriate joining method
if uses_prespacing:
# Pre-spaced fragments - just concatenate
content = "".join(self._current_text_parts)
else:
# Word-by-word fragments - join with spaces
content = " ".join(self._current_text_parts)
# Clean up any excessive whitespace
content = content.strip()
if content:
logger.debug(f"Emitting aggregated assistant message: {content}")
logger.trace(f"Emitting aggregated assistant message: {content}")
message = TranscriptionMessage(
role="assistant",
content=content,
@@ -102,7 +153,7 @@ class AssistantTranscriptProcessor(BaseTranscriptProcessor):
)
await self._emit_update([message])
else:
logger.debug("No content to emit after stripping whitespace")
logger.trace("No content to emit after stripping whitespace")
# Reset aggregation state
self._current_text_parts = []

427
src/pipecat/services/ai_services.py
View File

@@ -8,13 +8,13 @@ import asyncio
import io
import wave
from abc import abstractmethod
from typing import Any, AsyncGenerator, Dict, List, Mapping, Optional, Tuple, Type
from dataclasses import dataclass
from typing import Any, AsyncGenerator, Dict, List, Mapping, Optional, Sequence, Set, Tuple, Type
from loguru import logger
from pipecat.adapters.base_llm_adapter import BaseLLMAdapter
from pipecat.adapters.services.open_ai_adapter import OpenAILLMAdapter
from pipecat.audio.utils import calculate_audio_volume, exp_smoothing
from pipecat.frames.frames import (
AudioRawFrame,
BotStartedSpeakingFrame,
@@ -23,6 +23,9 @@ from pipecat.frames.frames import (
EndFrame,
ErrorFrame,
Frame,
FunctionCallCancelFrame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
InterimTranscriptionFrame,
LLMFullResponseEndFrame,
StartFrame,
@@ -38,6 +41,8 @@ from pipecat.frames.frames import (
TTSTextFrame,
TTSUpdateSettingsFrame,
UserImageRequestFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
VisionImageRawFrame,
)
from pipecat.metrics.metrics import MetricsData
@@ -45,8 +50,9 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.websocket_service import WebsocketService
from pipecat.transcriptions.language import Language
from pipecat.utils.string import match_endofsentence
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
from pipecat.utils.text.base_text_filter import BaseTextFilter
from pipecat.utils.text.simple_text_aggregator import SimpleTextAggregator
from pipecat.utils.time import seconds_to_nanoseconds
@@ -136,6 +142,13 @@ class AIService(FrameProcessor):
await self.push_frame(f)
@dataclass
class FunctionEntry:
function_name: Optional[str]
callback: Any # TODO(aleix): add proper typing.
cancel_on_interruption: bool
class LLMService(AIService):
"""This class is a no-op but serves as a base class for LLM services."""
@@ -145,38 +158,74 @@ class LLMService(AIService):
def __init__(self, **kwargs):
super().__init__(**kwargs)
self._callbacks = {}
self._functions = {}
self._start_callbacks = {}
self._adapter = self.adapter_class()
self._function_call_tasks: Set[Tuple[asyncio.Task, str, str]] = set()
self._register_event_handler("on_completion_timeout")
def get_llm_adapter(self) -> BaseLLMAdapter:
return self._adapter
def create_context_aggregator(
self, context: OpenAILLMContext, *, assistant_expect_stripped_words: bool = True
self,
context: OpenAILLMContext,
*,
user_kwargs: Mapping[str, Any] = {},
assistant_kwargs: Mapping[str, Any] = {},
) -> Any:
pass
self._register_event_handler("on_completion_timeout")
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
# TODO-CB: callback function type
def register_function(self, function_name: Optional[str], callback, start_callback=None):
if isinstance(frame, StartInterruptionFrame):
await self._handle_interruptions(frame)
async def _handle_interruptions(self, frame: StartInterruptionFrame):
for function_name, entry in self._functions.items():
if entry.cancel_on_interruption:
await self._cancel_function_call(function_name)
def register_function(
self,
function_name: Optional[str],
callback: Any,
start_callback=None,
*,
cancel_on_interruption: bool = False,
):
# Registering a function with the function_name set to None will run that callback
# for all functions
self._callbacks[function_name] = callback
# QUESTION FOR CB: maybe this isn't needed anymore?
self._functions[function_name] = FunctionEntry(
function_name=function_name,
callback=callback,
cancel_on_interruption=cancel_on_interruption,
)
# Start callbacks are now deprecated.
if start_callback:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'start_callback' is deprecated, just put your code on top of the actual function call instead.",
DeprecationWarning,
)
self._start_callbacks[function_name] = start_callback
def unregister_function(self, function_name: Optional[str]):
del self._callbacks[function_name]
del self._functions[function_name]
if self._start_callbacks[function_name]:
del self._start_callbacks[function_name]
def has_function(self, function_name: str):
if None in self._callbacks.keys():
if None in self._functions.keys():
return True
return function_name in self._callbacks.keys()
return function_name in self._functions.keys()
async def call_function(
self,
@@ -186,36 +235,144 @@ class LLMService(AIService):
function_name: str,
arguments: str,
run_llm: bool = True,
) -> None:
f = None
if function_name in self._callbacks.keys():
f = self._callbacks[function_name]
elif None in self._callbacks.keys():
f = self._callbacks[None]
else:
return None
await self.call_start_function(context, function_name)
await context.call_function(
f,
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
llm=self,
run_llm=run_llm,
):
if not function_name in self._functions.keys() and not None in self._functions.keys():
return
task = self.create_task(
self._run_function_call(context, tool_call_id, function_name, arguments, run_llm)
)
# QUESTION FOR CB: maybe this isn't needed anymore?
self._function_call_tasks.add((task, tool_call_id, function_name))
task.add_done_callback(self._function_call_task_finished)
async def call_start_function(self, context: OpenAILLMContext, function_name: str):
if function_name in self._start_callbacks.keys():
await self._start_callbacks[function_name](function_name, self, context)
elif None in self._start_callbacks.keys():
return await self._start_callbacks[None](function_name, self, context)
async def request_image_frame(self, user_id: str, *, text_content: Optional[str] = None):
async def request_image_frame(
self,
user_id: str,
*,
function_name: Optional[str] = None,
tool_call_id: Optional[str] = None,
text_content: Optional[str] = None,
):
await self.push_frame(
UserImageRequestFrame(user_id=user_id, context=text_content), FrameDirection.UPSTREAM
UserImageRequestFrame(
user_id=user_id,
function_name=function_name,
tool_call_id=tool_call_id,
context=text_content,
),
FrameDirection.UPSTREAM,
)
async def _run_function_call(
self,
context: OpenAILLMContext,
tool_call_id: str,
function_name: str,
arguments: str,
run_llm: bool = True,
):
if function_name in self._functions.keys():
entry = self._functions[function_name]
elif None in self._functions.keys():
entry = self._functions[None]
else:
return
logger.debug(
f"{self} Calling function [{function_name}:{tool_call_id}] with arguments {arguments}"
)
# NOTE(aleix): This needs to be removed after we remove the deprecation.
await self.call_start_function(context, function_name)
# Push a SystemFrame downstream. This frame will let our assistant context aggregator
# know that we are in the middle of a function call. Some contexts/aggregators may
# not need this. But some definitely do (Anthropic, for example).
# Also push a SystemFrame upstream for use by other processors, like STTMuteFilter.
progress_frame_downstream = FunctionCallInProgressFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
cancel_on_interruption=entry.cancel_on_interruption,
)
progress_frame_upstream = FunctionCallInProgressFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
cancel_on_interruption=entry.cancel_on_interruption,
)
# Push frame both downstream and upstream
await self.push_frame(progress_frame_downstream, FrameDirection.DOWNSTREAM)
await self.push_frame(progress_frame_upstream, FrameDirection.UPSTREAM)
# Define a callback function that pushes a FunctionCallResultFrame upstream & downstream.
async def function_call_result_callback(result, *, properties=None):
result_frame_downstream = FunctionCallResultFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
result=result,
properties=properties,
)
result_frame_upstream = FunctionCallResultFrame(
function_name=function_name,
tool_call_id=tool_call_id,
arguments=arguments,
result=result,
properties=properties,
)
await self.push_frame(result_frame_downstream, FrameDirection.DOWNSTREAM)
await self.push_frame(result_frame_upstream, FrameDirection.UPSTREAM)
await entry.callback(
function_name, tool_call_id, arguments, self, context, function_call_result_callback
)
async def _cancel_function_call(self, function_name: str):
cancelled_tasks = set()
for task, tool_call_id, name in self._function_call_tasks:
if name == function_name:
# We remove the callback because we are going to cancel the task
# now, otherwise we will be removing it from the set while we
# are iterating.
task.remove_done_callback(self._function_call_task_finished)
logger.debug(f"{self} Cancelling function call [{name}:{tool_call_id}]...")
await self.cancel_task(task)
frame = FunctionCallCancelFrame(
function_name=function_name, tool_call_id=tool_call_id
)
await self.push_frame(frame)
logger.debug(f"{self} Function call [{name}:{tool_call_id}] has been cancelled")
cancelled_tasks.add(task)
# Remove all cancelled tasks from our set.
for task in cancelled_tasks:
self._function_call_task_finished(task)
def _function_call_task_finished(self, task: asyncio.Task):
tuple_to_remove = next((t for t in self._function_call_tasks if t[0] == task), None)
if tuple_to_remove:
self._function_call_tasks.discard(tuple_to_remove)
# The task is finished so this should exit immediately. We need to
# do this because otherwise the task manager would have a dangling
# task if we don't remove it.
asyncio.run_coroutine_threadsafe(self.wait_for_task(task), self.get_event_loop())
class TTSService(AIService):
def __init__(
@@ -237,6 +394,10 @@ class TTSService(AIService):
pause_frame_processing: bool = False,
# TTS output sample rate
sample_rate: Optional[int] = None,
# Text aggregator to aggregate incoming tokens and decide when to push to the TTS.
text_aggregator: Optional[BaseTextAggregator] = None,
# Text filter executed after text has been aggregated.
text_filters: Sequence[BaseTextFilter] = [],
text_filter: Optional[BaseTextFilter] = None,
**kwargs,
):
@@ -252,12 +413,22 @@ class TTSService(AIService):
self._sample_rate = 0
self._voice_id: str = ""
self._settings: Dict[str, Any] = {}
self._text_filter: Optional[BaseTextFilter] = text_filter
self._text_aggregator: BaseTextAggregator = text_aggregator or SimpleTextAggregator()
self._text_filters: Sequence[BaseTextFilter] = text_filters
if text_filter:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'text_filter' is deprecated, use 'text_filters' instead.",
DeprecationWarning,
)
self._text_filters = [text_filter]
self._stop_frame_task: Optional[asyncio.Task] = None
self._stop_frame_queue: asyncio.Queue = asyncio.Queue()
self._current_sentence: str = ""
self._processing_text: bool = False
@property
@@ -270,10 +441,6 @@ class TTSService(AIService):
def set_voice(self, voice: str):
self._voice_id = voice
@abstractmethod
async def flush_audio(self):
pass
# Converts the text to audio.
@abstractmethod
async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
@@ -285,6 +452,9 @@ class TTSService(AIService):
async def update_setting(self, key: str, value: Any):
pass
async def flush_audio(self):
pass
async def start(self, frame: StartFrame):
await super().start(frame)
self._sample_rate = self._init_sample_rate or frame.audio_out_sample_rate
@@ -314,8 +484,9 @@ class TTSService(AIService):
self.set_model_name(value)
elif key == "voice":
self.set_voice(value)
elif key == "text_filter" and self._text_filter:
self._text_filter.update_settings(value)
elif key == "text_filter":
for filter in self._text_filters:
filter.update_settings(value)
else:
logger.warning(f"Unknown setting for TTS service: {key}")
@@ -340,8 +511,8 @@ class TTSService(AIService):
# pause to avoid audio overlapping.
await self._maybe_pause_frame_processing()
sentence = self._current_sentence
self._current_sentence = ""
sentence = self._text_aggregator.text
self._text_aggregator.reset()
self._processing_text = False
await self._push_tts_frames(sentence)
if isinstance(frame, LLMFullResponseEndFrame):
@@ -350,12 +521,14 @@ class TTSService(AIService):
else:
await self.push_frame(frame, direction)
elif isinstance(frame, TTSSpeakFrame):
# Store if we were processing text or not so we can set it back.
processing_text = self._processing_text
await self._push_tts_frames(frame.text)
# We pause processing incoming frames because we are sending data to
# the TTS. We pause to avoid audio overlapping.
await self._maybe_pause_frame_processing()
await self.flush_audio()
self._processing_text = False
self._processing_text = processing_text
elif isinstance(frame, TTSUpdateSettingsFrame):
await self._update_settings(frame.settings)
elif isinstance(frame, BotStoppedSpeakingFrame):
@@ -386,10 +559,10 @@ class TTSService(AIService):
await self._stop_frame_queue.put(frame)
async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
self._current_sentence = ""
self._processing_text = False
if self._text_filter:
self._text_filter.handle_interruption()
self._text_aggregator.handle_interruption()
for filter in self._text_filters:
filter.handle_interruption()
async def _maybe_pause_frame_processing(self):
if self._processing_text and self._pause_frame_processing:
@@ -404,11 +577,7 @@ class TTSService(AIService):
if not self._aggregate_sentences:
text = frame.text
else:
self._current_sentence += frame.text
eos_end_marker = match_endofsentence(self._current_sentence)
if eos_end_marker:
text = self._current_sentence[:eos_end_marker]
self._current_sentence = self._current_sentence[eos_end_marker:]
text = self._text_aggregator.aggregate(frame.text)
if text:
await self._push_tts_frames(text)
@@ -428,11 +597,16 @@ class TTSService(AIService):
self._processing_text = True
await self.start_processing_metrics()
if self._text_filter:
self._text_filter.reset_interruption()
text = self._text_filter.filter(text)
# Process all filter.
for filter in self._text_filters:
filter.reset_interruption()
text = filter.filter(text)
await self.process_generator(self.run_tts(text))
await self.stop_processing_metrics()
if self._push_text_frames:
# We send the original text after the audio. This way, if we are
# interrupted, the text is not added to the assistant context.
@@ -533,11 +707,25 @@ class WordTTSService(TTSService):
class WebsocketTTSService(TTSService, WebsocketService):
"""This is a base class for websocket-based TTS services."""
"""This is a base class for websocket-based TTS services.
def __init__(self, **kwargs):
If an error occurs with the websocket, an "on_connection_error" event will
be triggered:
@tts.event_handler("on_connection_error")
async def on_connection_error(tts: TTSService, error: str):
...
"""
def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
TTSService.__init__(self, **kwargs)
WebsocketService.__init__(self)
WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
self._register_event_handler("on_connection_error")
async def _report_error(self, error: ErrorFrame):
await self._call_event_handler("on_connection_error", error.error)
await self.push_error(error)
class InterruptibleTTSService(WebsocketTTSService):
@@ -574,11 +762,23 @@ class WebsocketWordTTSService(WordTTSService, WebsocketService):
"""This is a base class for websocket-based TTS services that support word
timestamps.
If an error occurs with the websocket a "on_connection_error" event will be
triggered:
@tts.event_handler("on_connection_error")
async def on_connection_error(tts: TTSService, error: str):
...
"""
def __init__(self, **kwargs):
def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
WordTTSService.__init__(self, **kwargs)
WebsocketService.__init__(self)
WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
self._register_event_handler("on_connection_error")
async def _report_error(self, error: ErrorFrame):
await self._call_event_handler("on_connection_error", error.error)
await self.push_error(error)
class InterruptibleWordTTSService(WebsocketWordTTSService):
@@ -762,11 +962,9 @@ class STTService(AIService):
def sample_rate(self) -> int:
return self._sample_rate
@abstractmethod
async def set_model(self, model: str):
self.set_model_name(model)
@abstractmethod
async def set_language(self, language: Language):
pass
@@ -797,8 +995,6 @@ class STTService(AIService):
return
await self.process_generator(self.run_stt(frame.audio))
if self._audio_passthrough:
await self.push_frame(frame, direction)
async def process_frame(self, frame: Frame, direction: FrameDirection):
"""Processes a frame of audio data, either buffering or transcribing it."""
@@ -809,6 +1005,8 @@ class STTService(AIService):
# push a TextFrame. We also push audio downstream in case someone
# else needs it.
await self.process_audio_frame(frame, direction)
if self._audio_passthrough:
await self.push_frame(frame, direction)
elif isinstance(frame, STTUpdateSettingsFrame):
await self._update_settings(frame.settings)
elif isinstance(frame, STTMuteFrame):
@@ -819,79 +1017,64 @@ class STTService(AIService):
class SegmentedSTTService(STTService):
"""SegmentedSTTService is an STTService that will detect speech and will run
speech-to-text on speech segments only, instead of a continous stream.
"""SegmentedSTTService is an STTService that uses VAD events to detect
speech and will run speech-to-text on speech segments only, instead of a
continous stream. Since it uses VAD it means that VAD needs to be enabled in
the pipeline.
This service always keeps a small audio buffer to take into account that VAD
events are delayed from when the user speech really starts.
"""
def __init__(
self,
*,
min_volume: float = 0.6,
max_silence_secs: float = 0.3,
max_buffer_secs: float = 1.5,
sample_rate: Optional[int] = None,
**kwargs,
):
def __init__(self, *, sample_rate: Optional[int] = None, **kwargs):
super().__init__(sample_rate=sample_rate, **kwargs)
self._min_volume = min_volume
self._max_silence_secs = max_silence_secs
self._max_buffer_secs = max_buffer_secs
self._content = None
self._wave = None
self._silence_num_frames = 0
# Volume exponential smoothing
self._smoothing_factor = 0.2
self._prev_volume = 0
async def process_audio_frame(self, frame: AudioRawFrame, direction: FrameDirection):
# Try to filter out empty background noise
volume = self._get_smoothed_volume(frame)
if volume >= self._min_volume:
# If volume is high enough, write new data to wave file
self._wave.writeframes(frame.audio)
self._silence_num_frames = 0
else:
self._silence_num_frames += frame.num_frames
self._prev_volume = volume
# If buffer is not empty and we have enough data or there's been a long
# silence, transcribe the audio gathered so far.
silence_secs = self._silence_num_frames / self.sample_rate
buffer_secs = self._wave.getnframes() / self.sample_rate
if self._content.tell() > 0 and (
buffer_secs > self._max_buffer_secs or silence_secs > self._max_silence_secs
):
self._silence_num_frames = 0
self._wave.close()
self._content.seek(0)
await self.process_generator(self.run_stt(self._content.read()))
(self._content, self._wave) = self._new_wave()
self._audio_buffer = bytearray()
self._audio_buffer_size_1s = 0
self._user_speaking = False
async def start(self, frame: StartFrame):
await super().start(frame)
if not self._wave:
(self._content, self._wave) = self._new_wave()
self._audio_buffer_size_1s = self.sample_rate * 2
async def stop(self, frame: EndFrame):
await super().stop(frame)
self._wave.close()
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
async def cancel(self, frame: CancelFrame):
await super().cancel(frame)
self._wave.close()
if isinstance(frame, UserStartedSpeakingFrame):
await self._handle_user_started_speaking(frame)
elif isinstance(frame, UserStoppedSpeakingFrame):
await self._handle_user_stopped_speaking(frame)
async def _handle_user_started_speaking(self, frame: UserStartedSpeakingFrame):
self._user_speaking = True
async def _handle_user_stopped_speaking(self, frame: UserStoppedSpeakingFrame):
self._user_speaking = False
def _new_wave(self):
content = io.BytesIO()
ww = wave.open(content, "wb")
ww.setsampwidth(2)
ww.setnchannels(1)
ww.setframerate(self.sample_rate)
return (content, ww)
wav = wave.open(content, "wb")
wav.setsampwidth(2)
wav.setnchannels(1)
wav.setframerate(self.sample_rate)
wav.writeframes(self._audio_buffer)
wav.close()
content.seek(0)
def _get_smoothed_volume(self, frame: AudioRawFrame) -> float:
volume = calculate_audio_volume(frame.audio, frame.sample_rate)
return exp_smoothing(volume, self._prev_volume, self._smoothing_factor)
await self.process_generator(self.run_stt(content.read()))
# Start clean.
self._audio_buffer.clear()
async def process_audio_frame(self, frame: AudioRawFrame, direction: FrameDirection):
# If the user is speaking the audio buffer will keep growin.
self._audio_buffer += frame.audio
# If the user is not speaking we keep just a little bit of audio.
if not self._user_speaking and len(self._audio_buffer) > self._audio_buffer_size_1s:
discarded = len(self._audio_buffer) - self._audio_buffer_size_1s
self._audio_buffer = self._audio_buffer[discarded:]
class ImageGenService(AIService):

212
src/pipecat/services/anthropic.py
View File

@@ -21,19 +21,16 @@ from pydantic import BaseModel, Field
from pipecat.adapters.services.anthropic_adapter import AnthropicLLMAdapter
from pipecat.frames.frames import (
Frame,
FunctionCallCancelFrame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
FunctionCallResultProperties,
LLMEnablePromptCachingFrame,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
LLMMessagesFrame,
LLMTextFrame,
LLMUpdateSettingsFrame,
OpenAILLMContextAssistantTimestampFrame,
StartInterruptionFrame,
UserImageRawFrame,
UserImageRequestFrame,
VisionImageRawFrame,
)
from pipecat.metrics.metrics import LLMTokenUsage
@@ -47,7 +44,6 @@ from pipecat.processors.aggregators.openai_llm_context import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import LLMService
from pipecat.utils.time import time_now_iso8601
try:
from anthropic import NOT_GIVEN, AsyncAnthropic, NotGiven
@@ -60,13 +56,6 @@ except ModuleNotFoundError as e:
raise Exception(f"Missing module: {e}")
# internal use only -- todo: refactor
@dataclass
class AnthropicImageMessageFrame(Frame):
user_image_raw_frame: UserImageRawFrame
text: Optional[str] = None
@dataclass
class AnthropicContextAggregatorPair:
_user: "AnthropicUserContextAggregator"
@@ -683,42 +672,7 @@ class AnthropicLLMContext(OpenAILLMContext):
class AnthropicUserContextAggregator(LLMUserContextAggregator):
def __init__(self, context: OpenAILLMContext | AnthropicLLMContext, **kwargs):
super().__init__(context=context, **kwargs)
async def process_frame(self, frame, direction):
await super().process_frame(frame, direction)
# Our parent method has already called push_frame(). So we can't interrupt the
# flow here and we don't need to call push_frame() ourselves. Possibly something
# to talk through (tagging @aleix). At some point we might need to refactor these
# context aggregators.
try:
if isinstance(frame, UserImageRequestFrame):
# The LLM sends a UserImageRequestFrame upstream. Cache any context provided with
# that frame so we can use it when we assemble the image message in the assistant
# context aggregator.
if frame.context:
if isinstance(frame.context, str):
self._context._user_image_request_context[frame.user_id] = frame.context
else:
logger.error(
f"Unexpected UserImageRequestFrame context type: {type(frame.context)}"
)
del self._context._user_image_request_context[frame.user_id]
else:
if frame.user_id in self._context._user_image_request_context:
del self._context._user_image_request_context[frame.user_id]
elif isinstance(frame, UserImageRawFrame):
# Push a new AnthropicImageMessageFrame with the text context we cached
# downstream to be handled by our assistant context aggregator. This is
# necessary so that we add the message to the context in the right order.
text = self._context._user_image_request_context.get(frame.user_id) or ""
if text:
del self._context._user_image_request_context[frame.user_id]
frame = AnthropicImageMessageFrame(user_image_raw_frame=frame, text=text)
await self.push_frame(frame)
except Exception as e:
logger.error(f"Error processing frame: {e}")
pass
#
@@ -732,112 +686,64 @@ class AnthropicUserContextAggregator(LLMUserContextAggregator):
class AnthropicAssistantContextAggregator(LLMAssistantContextAggregator):
def __init__(self, context: OpenAILLMContext | AnthropicLLMContext, **kwargs):
super().__init__(context=context, **kwargs)
self._function_call_in_progress = None
self._function_call_result = None
self._pending_image_frame_message = None
async def handle_function_call_in_progress(self, frame: FunctionCallInProgressFrame):
assistant_message = {"role": "assistant", "content": []}
assistant_message["content"].append(
{
"type": "tool_use",
"id": frame.tool_call_id,
"name": frame.function_name,
"input": frame.arguments,
}
)
self._context.add_message(assistant_message)
self._context.add_message(
{
"role": "user",
"content": [
{
"type": "tool_result",
"tool_use_id": frame.tool_call_id,
"content": "IN_PROGRESS",
}
],
}
)
async def process_frame(self, frame, direction):
await super().process_frame(frame, direction)
# See note above about not calling push_frame() here.
if isinstance(frame, StartInterruptionFrame):
self._function_call_in_progress = None
self._function_call_finished = None
elif isinstance(frame, FunctionCallInProgressFrame):
self._function_call_in_progress = frame
elif isinstance(frame, FunctionCallResultFrame):
if (
self._function_call_in_progress
and self._function_call_in_progress.tool_call_id == frame.tool_call_id
):
self._function_call_in_progress = None
self._function_call_result = frame
await self.push_aggregation()
else:
logger.warning(
"FunctionCallResultFrame tool_call_id != InProgressFrame tool_call_id"
)
self._function_call_in_progress = None
self._function_call_result = None
elif isinstance(frame, AnthropicImageMessageFrame):
self._pending_image_frame_message = frame
await self.push_aggregation()
async def handle_function_call_result(self, frame: FunctionCallResultFrame):
if frame.result:
result = json.dumps(frame.result)
await self._update_function_call_result(frame.function_name, frame.tool_call_id, result)
else:
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, "COMPLETED"
)
async def push_aggregation(self):
if not (
self._aggregation or self._function_call_result or self._pending_image_frame_message
):
return
async def handle_function_call_cancel(self, frame: FunctionCallCancelFrame):
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, "CANCELLED"
)
run_llm = False
properties: Optional[FunctionCallResultProperties] = None
async def _update_function_call_result(
self, function_name: str, tool_call_id: str, result: str
):
for message in self._context.messages:
if message["role"] == "user":
for content in message["content"]:
if (
isinstance(content, dict)
and content["type"] == "tool_result"
and content["tool_use_id"] == tool_call_id
):
content["content"] = result
aggregation = self._aggregation.strip()
self.reset()
try:
if aggregation:
self._context.add_message({"role": "assistant", "content": aggregation})
if self._function_call_result:
frame = self._function_call_result
properties = frame.properties
self._function_call_result = None
if frame.result:
assistant_message = {"role": "assistant", "content": []}
assistant_message["content"].append(
{
"type": "tool_use",
"id": frame.tool_call_id,
"name": frame.function_name,
"input": frame.arguments,
}
)
self._context.add_message(assistant_message)
self._context.add_message(
{
"role": "user",
"content": [
{
"type": "tool_result",
"tool_use_id": frame.tool_call_id,
"content": json.dumps(frame.result),
}
],
}
)
if properties and properties.run_llm is not None:
# If the tool call result has a run_llm property, use it
run_llm = properties.run_llm
else:
# Default behavior
run_llm = True
if self._pending_image_frame_message:
frame = self._pending_image_frame_message
self._pending_image_frame_message = None
self._context.add_image_frame_message(
format=frame.user_image_raw_frame.format,
size=frame.user_image_raw_frame.size,
image=frame.user_image_raw_frame.image,
text=frame.text,
)
run_llm = True
if run_llm:
await self.push_context_frame(FrameDirection.UPSTREAM)
# Emit the on_context_updated callback once the function call result is added to the context
if properties and properties.on_context_updated is not None:
await properties.on_context_updated()
# Push context frame
await self.push_context_frame()
# Push timestamp frame with current time
timestamp_frame = OpenAILLMContextAssistantTimestampFrame(timestamp=time_now_iso8601())
await self.push_frame(timestamp_frame)
except Exception as e:
logger.error(f"Error processing frame: {e}")
async def handle_user_image_frame(self, frame: UserImageRawFrame):
await self._update_function_call_result(
frame.request.function_name, frame.request.tool_call_id, "COMPLETED"
)
self._context.add_image_frame_message(
format=frame.format,
size=frame.size,
image=frame.image,
text=frame.request.context,
)

13
src/pipecat/services/aws.py
View File

@@ -248,16 +248,3 @@ class PollyTTSService(TTSService):
finally:
yield TTSStoppedFrame()
class AWSTTSService(PollyTTSService):
def __init__(self, **kwargs):
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'AWSTTSService' is deprecated, use 'PollyTTSService' instead.", DeprecationWarning
)

7
src/pipecat/services/azure.py
View File

@@ -686,8 +686,11 @@ class AzureSTTService(STTService):
):
super().__init__(sample_rate=sample_rate, **kwargs)
self._speech_config = SpeechConfig(subscription=api_key, region=region)
self._speech_config.speech_recognition_language = language
self._speech_config = SpeechConfig(
subscription=api_key,
region=region,
speech_recognition_language=language_to_azure_language(language),
)
self._audio_stream = None
self._speech_recognizer = None

7
src/pipecat/services/cartesia.py
View File

@@ -26,6 +26,8 @@ from pipecat.frames.frames import (
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import AudioContextWordTTSService, TTSService
from pipecat.transcriptions.language import Language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
from pipecat.utils.text.skip_tags_aggregator import SkipTagsAggregator
# See .env.example for Cartesia configuration needed
try:
@@ -89,6 +91,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
encoding: str = "pcm_s16le",
container: str = "raw",
params: InputParams = InputParams(),
text_aggregator: Optional[BaseTextAggregator] = None,
**kwargs,
):
# Aggregating sentences still gives cleaner-sounding results and fewer
@@ -106,6 +109,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
push_text_frames=False,
pause_frame_processing=True,
sample_rate=sample_rate,
text_aggregator=text_aggregator or SkipTagsAggregator([("<spell>", "</spell>")]),
**kwargs,
)
@@ -183,7 +187,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
async def _connect(self):
await self._connect_websocket()
if not self._receive_task:
self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
async def _disconnect(self):
if self._receive_task:
@@ -203,6 +207,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
except Exception as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
try:

7
src/pipecat/services/elevenlabs.py
View File

@@ -102,6 +102,8 @@ def language_to_elevenlabs_language(language: Language) -> Optional[str]:
def output_format_from_sample_rate(sample_rate: int) -> str:
match sample_rate:
case 8000:
return "pcm_8000"
case 16000:
return "pcm_16000"
case 22050:
@@ -113,7 +115,7 @@ def output_format_from_sample_rate(sample_rate: int) -> str:
logger.warning(
f"ElevenLabsTTSService: No output format available for {sample_rate} sample rate"
)
return "pcm_16000"
return "pcm_24000"
def build_elevenlabs_voice_settings(
@@ -309,7 +311,7 @@ class ElevenLabsTTSService(InterruptibleWordTTSService):
await self._connect_websocket()
if not self._receive_task:
self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
if not self._keepalive_task:
self._keepalive_task = self.create_task(self._keepalive_task_handler())
@@ -364,6 +366,7 @@ class ElevenLabsTTSService(InterruptibleWordTTSService):
except Exception as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
try:

227
src/pipecat/services/fal.py
View File

@@ -7,6 +7,7 @@
import asyncio
import io
import os
import wave
from typing import AsyncGenerator, Dict, Optional, Union
import aiohttp
@@ -14,8 +15,10 @@ from loguru import logger
from PIL import Image
from pydantic import BaseModel
from pipecat.frames.frames import ErrorFrame, Frame, URLImageRawFrame
from pipecat.services.ai_services import ImageGenService
from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame, URLImageRawFrame
from pipecat.services.ai_services import ImageGenService, SegmentedSTTService
from pipecat.transcriptions.language import Language
from pipecat.utils.time import time_now_iso8601
try:
import fal_client
@@ -27,6 +30,120 @@ except ModuleNotFoundError as e:
raise Exception(f"Missing module: {e}")
def language_to_fal_language(language: Language) -> Optional[str]:
"""Language support for Fal's Wizper API."""
BASE_LANGUAGES = {
Language.AF: "af",
Language.AM: "am",
Language.AR: "ar",
Language.AS: "as",
Language.AZ: "az",
Language.BA: "ba",
Language.BE: "be",
Language.BG: "bg",
Language.BN: "bn",
Language.BO: "bo",
Language.BR: "br",
Language.BS: "bs",
Language.CA: "ca",
Language.CS: "cs",
Language.CY: "cy",
Language.DA: "da",
Language.DE: "de",
Language.EL: "el",
Language.EN: "en",
Language.ES: "es",
Language.ET: "et",
Language.EU: "eu",
Language.FA: "fa",
Language.FI: "fi",
Language.FO: "fo",
Language.FR: "fr",
Language.GL: "gl",
Language.GU: "gu",
Language.HA: "ha",
Language.HE: "he",
Language.HI: "hi",
Language.HR: "hr",
Language.HT: "ht",
Language.HU: "hu",
Language.HY: "hy",
Language.ID: "id",
Language.IS: "is",
Language.IT: "it",
Language.JA: "ja",
Language.JW: "jw",
Language.KA: "ka",
Language.KK: "kk",
Language.KM: "km",
Language.KN: "kn",
Language.KO: "ko",
Language.LA: "la",
Language.LB: "lb",
Language.LN: "ln",
Language.LO: "lo",
Language.LT: "lt",
Language.LV: "lv",
Language.MG: "mg",
Language.MI: "mi",
Language.MK: "mk",
Language.ML: "ml",
Language.MN: "mn",
Language.MR: "mr",
Language.MS: "ms",
Language.MT: "mt",
Language.MY: "my",
Language.NE: "ne",
Language.NL: "nl",
Language.NN: "nn",
Language.NO: "no",
Language.OC: "oc",
Language.PA: "pa",
Language.PL: "pl",
Language.PS: "ps",
Language.PT: "pt",
Language.RO: "ro",
Language.RU: "ru",
Language.SA: "sa",
Language.SD: "sd",
Language.SI: "si",
Language.SK: "sk",
Language.SL: "sl",
Language.SN: "sn",
Language.SO: "so",
Language.SQ: "sq",
Language.SR: "sr",
Language.SU: "su",
Language.SV: "sv",
Language.SW: "sw",
Language.TA: "ta",
Language.TE: "te",
Language.TG: "tg",
Language.TH: "th",
Language.TK: "tk",
Language.TL: "tl",
Language.TR: "tr",
Language.TT: "tt",
Language.UK: "uk",
Language.UR: "ur",
Language.UZ: "uz",
Language.VI: "vi",
Language.YI: "yi",
Language.YO: "yo",
Language.ZH: "zh",
}
result = BASE_LANGUAGES.get(language)
# If not found in base languages, try to find the base language from a variant
if not result:
lang_str = str(language.value)
base_code = lang_str.split("-")[0].lower()
result = base_code if base_code in BASE_LANGUAGES.values() else None
return result
class FalImageGenService(ImageGenService):
class InputParams(BaseModel):
seed: Optional[int] = None
@@ -84,3 +201,109 @@ class FalImageGenService(ImageGenService):
frame = URLImageRawFrame(url=image_url, image=image_bytes, size=size, format=format)
yield frame
class FalSTTService(SegmentedSTTService):
"""Speech-to-text service using Fal's Wizper API.
This service uses Fal's Wizper API to perform speech-to-text transcription on audio
segments. It inherits from SegmentedSTTService to handle audio buffering and speech detection.
Args:
api_key: Fal API key. If not provided, will check FAL_KEY environment variable.
sample_rate: Audio sample rate in Hz. If not provided, uses the pipeline's rate.
params: Configuration parameters for the Wizper API.
**kwargs: Additional arguments passed to SegmentedSTTService.
"""
class InputParams(BaseModel):
"""Configuration parameters for Fal's Wizper API.
Attributes:
language: Language of the audio input. Defaults to English.
task: Task to perform ('transcribe' or 'translate'). Defaults to 'transcribe'.
chunk_level: Level of chunking ('segment'). Defaults to 'segment'.
version: Version of Wizper model to use. Defaults to '3'.
"""
language: Optional[Language] = Language.EN
task: str = "transcribe"
chunk_level: str = "segment"
version: str = "3"
def __init__(
self,
*,
api_key: Optional[str] = None,
sample_rate: Optional[int] = None,
params: InputParams = InputParams(),
**kwargs,
):
super().__init__(
sample_rate=sample_rate,
**kwargs,
)
if api_key:
os.environ["FAL_KEY"] = api_key
elif "FAL_KEY" not in os.environ:
raise ValueError(
"FAL_KEY must be provided either through api_key parameter or environment variable"
)
self._fal_client = fal_client.AsyncClient(key=api_key or os.getenv("FAL_KEY"))
self._settings = {
"task": params.task,
"language": self.language_to_service_language(params.language)
if params.language
else "en",
"chunk_level": params.chunk_level,
"version": params.version,
}
def can_generate_metrics(self) -> bool:
return True
def language_to_service_language(self, language: Language) -> Optional[str]:
return language_to_fal_language(language)
async def set_language(self, language: Language):
logger.info(f"Switching STT language to: [{language}]")
self._settings["language"] = self.language_to_service_language(language)
async def set_model(self, model: str):
await super().set_model(model)
logger.info(f"Switching STT model to: [{model}]")
async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
"""Transcribes an audio segment using Fal's Wizper API.
Args:
audio: Raw audio bytes in WAV format (already converted by base class).
Yields:
Frame: TranscriptionFrame containing the transcribed text.
Note:
The audio is already in WAV format from the SegmentedSTTService.
Only non-empty transcriptions are yielded.
"""
try:
# Send to Fal directly (audio is already in WAV format from base class)
data_uri = fal_client.encode(audio, "audio/x-wav")
response = await self._fal_client.run(
"fal-ai/wizper",
arguments={"audio_url": data_uri, **self._settings},
)
if response and "text" in response:
text = response["text"].strip()
if text: # Only yield non-empty text
logger.debug(f"Transcription: [{text}]")
yield TranscriptionFrame(
text, "", time_now_iso8601(), Language(self._settings["language"])
)
except Exception as e:
logger.error(f"Fal Wizper error: {e}")
yield ErrorFrame(f"Fal Wizper error: {str(e)}")

11
src/pipecat/services/fish.py
View File

@@ -107,7 +107,7 @@ class FishAudioTTSService(InterruptibleTTSService):
async def _connect(self):
await self._connect_websocket()
if not self._receive_task:
self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
async def _disconnect(self):
if self._receive_task:
@@ -132,6 +132,7 @@ class FishAudioTTSService(InterruptibleTTSService):
except Exception as e:
logger.error(f"Fish Audio initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
try:
@@ -148,6 +149,14 @@ class FishAudioTTSService(InterruptibleTTSService):
except Exception as e:
logger.error(f"Error closing websocket: {e}")
async def flush_audio(self):
"""Flush any buffered audio by sending a flush event to Fish Audio."""
logger.trace(f"{self}: Flushing audio buffers")
if not self._websocket:
return
flush_message = {"event": "flush"}
await self._get_websocket().send(ormsgpack.packb(flush_message))
def _get_websocket(self):
if self._websocket:
return self._websocket

29
src/pipecat/services/gemini_multimodal_live/gemini.py
View File

@@ -39,6 +39,8 @@ from pipecat.frames.frames import (
TTSAudioRawFrame,
TTSStartedFrame,
TTSStoppedFrame,
TTSTextFrame,
UserImageRawFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
@@ -118,10 +120,10 @@ class GeminiMultimodalLiveUserContextAggregator(OpenAIUserContextAggregator):
class GeminiMultimodalLiveAssistantContextAggregator(OpenAIAssistantContextAggregator):
async def push_aggregation(self):
# We don't want to store any images in the context. Revisit this later when the API evolves.
self._pending_image_frame_message = None
await super().push_aggregation()
async def handle_user_image_frame(self, frame: UserImageRawFrame):
# We don't want to store any images in the context. Revisit this later
# when the API evolves.
pass
@dataclass
@@ -314,6 +316,7 @@ class GeminiMultimodalLiveLLMService(LLMService):
# context.add_message({"role": "assistant", "content": [{"type": "text", "text": text}]})
await self.push_frame(LLMFullResponseStartFrame())
await self.push_frame(LLMTextFrame(text=text))
await self.push_frame(TTSTextFrame(text=text))
await self.push_frame(LLMFullResponseEndFrame())
async def _transcribe_audio(self, audio, context):
@@ -341,10 +344,8 @@ class GeminiMultimodalLiveLLMService(LLMService):
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
# logger.debug(f"Processing frame: {frame}")
if isinstance(frame, TranscriptionFrame):
pass
await self.push_frame(frame, direction)
elif isinstance(frame, OpenAILLMContextFrame):
context: GeminiMultimodalLiveContext = GeminiMultimodalLiveContext.upgrade(
frame.context
@@ -361,31 +362,35 @@ class GeminiMultimodalLiveLLMService(LLMService):
# Support just one tool call per context frame for now
tool_result_message = context.messages[-1]
await self._tool_result(tool_result_message)
elif isinstance(frame, InputAudioRawFrame):
await self._send_user_audio(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, InputImageRawFrame):
await self._send_user_video(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, StartInterruptionFrame):
await self._handle_interruption()
await self.push_frame(frame, direction)
elif isinstance(frame, UserStartedSpeakingFrame):
await self._handle_user_started_speaking(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, UserStoppedSpeakingFrame):
await self._handle_user_stopped_speaking(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, BotStartedSpeakingFrame):
# Ignore this frame. Use the serverContent API message instead
pass
await self.push_frame(frame, direction)
elif isinstance(frame, BotStoppedSpeakingFrame):
# ignore this frame. Use the serverContent.turnComplete API message
pass
await self.push_frame(frame, direction)
elif isinstance(frame, LLMMessagesAppendFrame):
await self._create_single_response(frame.messages)
elif isinstance(frame, LLMUpdateSettingsFrame):
await self._update_settings(frame.settings)
elif isinstance(frame, LLMSetToolsFrame):
await self._update_settings()
await self.push_frame(frame, direction)
else:
await self.push_frame(frame, direction)
#
# websocket communication

242
src/pipecat/services/google/google.py
View File

@@ -10,6 +10,7 @@ import io
import json
import os
import time
import uuid
from google.api_core.exceptions import DeadlineExceeded
from openai import AsyncStream
@@ -33,20 +34,22 @@ from pipecat.frames.frames import (
EndFrame,
ErrorFrame,
Frame,
FunctionCallResultProperties,
FunctionCallCancelFrame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
InterimTranscriptionFrame,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
LLMMessagesFrame,
LLMTextFrame,
LLMUpdateSettingsFrame,
OpenAILLMContextAssistantTimestampFrame,
StartFrame,
TranscriptionFrame,
TTSAudioRawFrame,
TTSStartedFrame,
TTSStoppedFrame,
URLImageRawFrame,
UserImageRawFrame,
VisionImageRawFrame,
)
from pipecat.metrics.metrics import LLMTokenUsage
@@ -58,7 +61,6 @@ from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import ImageGenService, LLMService, STTService, TTSService
from pipecat.services.google.frames import LLMSearchResponseFrame
from pipecat.services.openai import (
BaseOpenAILLMService,
OpenAIAssistantContextAggregator,
OpenAILLMService,
OpenAIUnhandledFunctionException,
@@ -72,6 +74,7 @@ try:
import google.generativeai as gai
from google import genai
from google.api_core.client_options import ClientOptions
from google.auth.transport.requests import Request
from google.cloud import speech_v2, texttospeech_v1
from google.cloud.speech_v2.types import cloud_speech
from google.genai import types
@@ -565,91 +568,76 @@ class GoogleUserContextAggregator(OpenAIUserContextAggregator):
class GoogleAssistantContextAggregator(OpenAIAssistantContextAggregator):
async def push_aggregation(self):
if not (
self._aggregation or self._function_call_result or self._pending_image_frame_message
):
return
async def handle_aggregation(self, aggregation: str):
self._context.add_message(glm.Content(role="model", parts=[glm.Part(text=aggregation)]))
run_llm = False
properties: Optional[FunctionCallResultProperties] = None
aggregation = self._aggregation.strip()
self.reset()
try:
if aggregation:
self._context.add_message(
glm.Content(role="model", parts=[glm.Part(text=aggregation)])
)
if self._function_call_result:
frame = self._function_call_result
properties = frame.properties
self._function_call_result = None
if frame.result:
logger.debug(f"FunctionCallResultFrame result: {frame.arguments}")
self._context.add_message(
glm.Content(
role="model",
parts=[
glm.Part(
function_call=glm.FunctionCall(
name=frame.function_name, args=frame.arguments
)
)
],
async def handle_function_call_in_progress(self, frame: FunctionCallInProgressFrame):
self._context.add_message(
glm.Content(
role="model",
parts=[
glm.Part(
function_call=glm.FunctionCall(
id=frame.tool_call_id, name=frame.function_name, args=frame.arguments
)
)
response = frame.result
if isinstance(response, str):
response = {"response": response}
self._context.add_message(
glm.Content(
role="user",
parts=[
glm.Part(
function_response=glm.FunctionResponse(
name=frame.function_name, response=response
)
)
],
],
)
)
self._context.add_message(
glm.Content(
role="user",
parts=[
glm.Part(
function_response=glm.FunctionResponse(
id=frame.tool_call_id,
name=frame.function_name,
response={"response": "IN_PROGRESS"},
)
)
if properties and properties.run_llm is not None:
# If the tool call result has a run_llm property, use it
run_llm = properties.run_llm
else:
# Default behavior is to run the LLM if there are no function calls in progress
run_llm = not bool(self._function_calls_in_progress)
],
)
)
if self._pending_image_frame_message:
frame = self._pending_image_frame_message
self._pending_image_frame_message = None
self._context.add_image_frame_message(
format=frame.user_image_raw_frame.format,
size=frame.user_image_raw_frame.size,
image=frame.user_image_raw_frame.image,
text=frame.text,
)
run_llm = True
async def handle_function_call_result(self, frame: FunctionCallResultFrame):
if frame.result:
if not isinstance(frame.result, str):
return
if run_llm:
await self.push_context_frame(FrameDirection.UPSTREAM)
response = {"response": frame.result}
# Emit the on_context_updated callback once the function call result is added to the context
if properties and properties.on_context_updated is not None:
await properties.on_context_updated()
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, response
)
else:
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, "COMPLETED"
)
# Push context frame
await self.push_context_frame()
async def handle_function_call_cancel(self, frame: FunctionCallCancelFrame):
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, "CANCELLED"
)
# Push timestamp frame with current time
timestamp_frame = OpenAILLMContextAssistantTimestampFrame(timestamp=time_now_iso8601())
await self.push_frame(timestamp_frame)
async def _update_function_call_result(
self, function_name: str, tool_call_id: str, result: Any
):
for message in self._context.messages:
if message.role == "user":
for part in message.parts:
if part.function_response and part.function_response.id == tool_call_id:
part.function_response.response = {"response": result}
except Exception as e:
logger.exception(f"Error processing frame: {e}")
async def handle_user_image_frame(self, frame: UserImageRawFrame):
await self._update_function_call_result(
frame.request.function_name, frame.request.tool_call_id, "COMPLETED"
)
self._context.add_image_frame_message(
format=frame.format,
size=frame.size,
image=frame.image,
text=frame.request.context,
)
@dataclass
@@ -1071,7 +1059,7 @@ class GoogleLLMService(LLMService):
args = type(c.function_call).to_dict(c.function_call).get("args", {})
await self.call_function(
context=context,
tool_call_id="what_should_this_be",
tool_call_id=str(uuid.uuid4()),
function_name=c.function_call.name,
arguments=args,
)
@@ -1334,6 +1322,82 @@ class GoogleLLMOpenAIBetaService(OpenAILLMService):
)
class GoogleVertexLLMService(OpenAILLMService):
"""Implements inference with Google's AI models via Vertex AI while
maintaining OpenAI API compatibility.
Reference:
https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/call-vertex-using-openai-library
"""
class InputParams(OpenAILLMService.InputParams):
"""Input parameters specific to Vertex AI."""
# https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations
location: str = "us-east4"
project_id: str
def __init__(
self,
*,
credentials: Optional[str] = None,
credentials_path: Optional[str] = None,
model: str = "google/gemini-2.0-flash-001",
params: InputParams = OpenAILLMService.InputParams(),
**kwargs,
):
"""Initializes the VertexLLMService.
Args:
credentials (Optional[str]): JSON string of service account credentials.
credentials_path (Optional[str]): Path to the service account JSON file.
model (str): Model identifier. Defaults to "google/gemini-2.0-flash-001".
params (InputParams): Vertex AI input parameters.
**kwargs: Additional arguments for OpenAILLMService.
"""
base_url = self._get_base_url(params)
self._api_key = self._get_api_token(credentials, credentials_path)
super().__init__(api_key=self._api_key, base_url=base_url, model=model, **kwargs)
@staticmethod
def _get_base_url(params: InputParams) -> str:
"""Constructs the base URL for Vertex AI API."""
return (
f"https://{params.location}-aiplatform.googleapis.com/v1/"
f"projects/{params.project_id}/locations/{params.location}/endpoints/openapi"
)
@staticmethod
def _get_api_token(credentials: Optional[str], credentials_path: Optional[str]) -> str:
"""Retrieves an authentication token using Google service account credentials.
Args:
credentials (Optional[str]): JSON string of service account credentials.
credentials_path (Optional[str]): Path to the service account JSON file.
Returns:
str: OAuth token for API authentication.
"""
creds: Optional[service_account.Credentials] = None
if credentials:
# Parse and load credentials from JSON string
creds = service_account.Credentials.from_service_account_info(
json.loads(credentials), scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
elif credentials_path:
# Load credentials from JSON file
creds = service_account.Credentials.from_service_account_file(
credentials_path, scopes=["https://www.googleapis.com/auth/cloud-platform"]
)
if not creds:
raise ValueError("No valid credentials provided.")
creds.refresh(Request()) # Ensure token is up-to-date, lifetime is 1 hour.
return creds.token
class GoogleTTSService(TTSService):
class InputParams(BaseModel):
pitch: Optional[str] = None
@@ -1448,10 +1512,13 @@ class GoogleTTSService(TTSService):
try:
await self.start_ttfb_metrics()
# Check if the voice is a Chirp voice (including Chirp 3) or Journey voice
is_chirp_voice = "chirp" in self._voice_id.lower()
is_journey_voice = "journey" in self._voice_id.lower()
# Create synthesis input based on voice_id
if is_journey_voice:
if is_chirp_voice or is_journey_voice:
# Chirp and Journey voices don't support SSML, use plain text
synthesis_input = texttospeech_v1.SynthesisInput(text=text)
else:
ssml = self._construct_ssml(text)
@@ -1727,6 +1794,17 @@ class GoogleSTTService(STTService):
await self._disconnect()
await self._connect()
async def set_language(self, language: Language):
"""Update the service's recognition language.
A convenience method for setting a single language.
Args:
language: New language for recognition.
"""
logger.debug(f"Switching STT language to: {language}")
await self.set_languages([language])
async def set_languages(self, languages: List[Language]):
"""Update the service's recognition languages.
@@ -1959,7 +2037,8 @@ class GoogleSTTService(STTService):
break
except Exception as e:
logger.error(f"Stream error, attempting to reconnect: {e}")
logger.warning(f"{self} Reconnecting: {e}")
await asyncio.sleep(1) # Brief delay before reconnecting
self._stream_start_time = int(time.time() * 1000)
continue
@@ -2012,3 +2091,6 @@ class GoogleSTTService(STTService):
except Exception as e:
logger.error(f"Error processing Google STT responses: {e}")
# Re-raise the exception to let it propagate (e.g. in the case of a timeout, propagate to _stream_audio to reconnect)
raise

85
src/pipecat/services/grok.py
View File

@@ -25,94 +25,15 @@ from pipecat.services.openai import (
)
class GrokAssistantContextAggregator(OpenAIAssistantContextAggregator):
"""Custom assistant context aggregator for Grok that handles empty content requirement."""
async def push_aggregation(self):
if not (
self._aggregation or self._function_call_result or self._pending_image_frame_message
):
return
run_llm = False
properties: Optional[FunctionCallResultProperties] = None
aggregation = self._aggregation.strip()
self.reset()
try:
if aggregation:
self._context.add_message({"role": "assistant", "content": aggregation})
if self._function_call_result:
frame = self._function_call_result
properties = frame.properties
self._function_call_result = None
if frame.result:
# Grok requires an empty content field for function calls
self._context.add_message(
{
"role": "assistant",
"content": "", # Required by Grok
"tool_calls": [
{
"id": frame.tool_call_id,
"function": {
"name": frame.function_name,
"arguments": json.dumps(frame.arguments),
},
"type": "function",
}
],
}
)
self._context.add_message(
{
"role": "tool",
"content": json.dumps(frame.result),
"tool_call_id": frame.tool_call_id,
}
)
if properties and properties.run_llm is not None:
# If the tool call result has a run_llm property, use it
run_llm = properties.run_llm
else:
# Default behavior is to run the LLM if there are no function calls in progress
run_llm = not bool(self._function_calls_in_progress)
if self._pending_image_frame_message:
frame = self._pending_image_frame_message
self._pending_image_frame_message = None
self._context.add_image_frame_message(
format=frame.user_image_raw_frame.format,
size=frame.user_image_raw_frame.size,
image=frame.user_image_raw_frame.image,
text=frame.text,
)
run_llm = True
if run_llm:
await self.push_context_frame(FrameDirection.UPSTREAM)
# Emit the on_context_updated callback once the function call result is added to the context
if properties and properties.on_context_updated is not None:
await properties.on_context_updated()
await self.push_context_frame()
except Exception as e:
logger.error(f"Error processing frame: {e}")
@dataclass
class GrokContextAggregatorPair:
_user: "OpenAIUserContextAggregator"
_assistant: "GrokAssistantContextAggregator"
_assistant: "OpenAIAssistantContextAggregator"
def user(self) -> "OpenAIUserContextAggregator":
return self._user
def assistant(self) -> "GrokAssistantContextAggregator":
def assistant(self) -> "OpenAIAssistantContextAggregator":
return self._assistant
@@ -235,5 +156,5 @@ class GrokLLMService(OpenAILLMService):
context.set_llm_adapter(self.get_llm_adapter())
user = OpenAIUserContextAggregator(context, **user_kwargs)
assistant = GrokAssistantContextAggregator(context, **assistant_kwargs)
assistant = OpenAIAssistantContextAggregator(context, **assistant_kwargs)
return GrokContextAggregatorPair(_user=user, _assistant=assistant)

8
src/pipecat/services/lmnt.py
View File

@@ -112,7 +112,7 @@ class LmntTTSService(InterruptibleTTSService):
await self._connect_websocket()
if not self._receive_task:
self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
async def _disconnect(self):
if self._receive_task:
@@ -147,6 +147,7 @@ class LmntTTSService(InterruptibleTTSService):
except Exception as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
"""Disconnect from LMNT websocket."""
@@ -170,6 +171,11 @@ class LmntTTSService(InterruptibleTTSService):
return self._websocket
raise Exception("Websocket not connected")
async def flush_audio(self):
if not self._websocket:
return
await self._get_websocket().send(json.dumps({"flush": True}))
async def _receive_messages(self):
"""Receive messages from LMNT websocket."""
async for message in self._get_websocket():

345
src/pipecat/services/neuphonic.py Normal file
View File

@@ -0,0 +1,345 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import base64
import json
from typing import Any, AsyncGenerator, Mapping, Optional
from loguru import logger
from pydantic import BaseModel
from pipecat.frames.frames import (
BotStoppedSpeakingFrame,
CancelFrame,
EndFrame,
ErrorFrame,
Frame,
LLMFullResponseEndFrame,
StartFrame,
StartInterruptionFrame,
TTSAudioRawFrame,
TTSSpeakFrame,
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import InterruptibleTTSService, TTSService
from pipecat.transcriptions.language import Language
# See .env.example for Neuphonic configuration needed
try:
import websockets
from pyneuphonic import Neuphonic, TTSConfig
except ModuleNotFoundError as e:
logger.error(f"Exception: {e}")
logger.error(
"In order to use Neuphonic, you need to `pip install pipecat-ai[neuphonic]`. Also, set `NEUPHONIC_API_KEY` environment variable."
)
raise Exception(f"Missing module: {e}")
def language_to_neuphonic_lang_code(language: Language) -> Optional[str]:
BASE_LANGUAGES = {
Language.DE: "de",
Language.EN: "en",
Language.ES: "es",
Language.NL: "nl",
Language.AR: "ar",
Language.FR: "fr",
Language.PT: "pt",
Language.RU: "ru",
Language.HI: "HI",
Language.ZH: "zh",
}
result = BASE_LANGUAGES.get(language)
# If not found in base languages, try to find the base language from a variant
if not result:
# Convert enum value to string and get the base language part (e.g. es-ES -> es)
lang_str = str(language.value)
base_code = lang_str.split("-")[0].lower()
# Look up the base code in our supported languages
result = base_code if base_code in BASE_LANGUAGES.values() else None
return result
class NeuphonicTTSService(InterruptibleTTSService):
class InputParams(BaseModel):
language: Optional[Language] = Language.EN
speed: Optional[float] = 1.0
def __init__(
self,
*,
api_key: str,
voice_id: Optional[str] = None,
url: str = "wss://api.neuphonic.com",
sample_rate: Optional[int] = 22050,
encoding: str = "pcm_linear",
params: InputParams = InputParams(),
**kwargs,
):
super().__init__(
aggregate_sentences=True,
push_text_frames=False,
push_stop_frames=True,
stop_frame_timeout_s=2.0,
sample_rate=sample_rate,
**kwargs,
)
self._api_key = api_key
self._url = url
self._settings = {
"lang_code": self.language_to_service_language(params.language),
"speed": params.speed,
"encoding": encoding,
"sampling_rate": sample_rate,
}
self.set_voice(voice_id)
# Indicates if we have sent TTSStartedFrame. It will reset to False when
# there's an interruption or TTSStoppedFrame.
self._started = False
self._cumulative_time = 0
def can_generate_metrics(self) -> bool:
return True
def language_to_service_language(self, language: Language) -> Optional[str]:
return language_to_neuphonic_lang_code(language)
async def _update_settings(self, settings: Mapping[str, Any]):
if "voice_id" in settings:
self.set_voice(settings["voice_id"])
await super()._update_settings(settings)
await self._disconnect()
await self._connect()
logger.info(f"Switching TTS to settings: [{self._settings}]")
async def start(self, frame: StartFrame):
await super().start(frame)
await self._connect()
async def stop(self, frame: EndFrame):
await super().stop(frame)
await self._disconnect()
async def cancel(self, frame: CancelFrame):
await super().cancel(frame)
await self._disconnect()
async def flush_audio(self):
if self._websocket:
msg = {"text": "<STOP>"}
await self._websocket.send(json.dumps(msg))
async def push_frame(self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM):
await super().push_frame(frame, direction)
if isinstance(frame, (TTSStoppedFrame, StartInterruptionFrame)):
self._started = False
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
# If we received a TTSSpeakFrame and the LLM response included text (it
# might be that it's only a function calling response) we pause
# processing more frames until we receive a BotStoppedSpeakingFrame.
if isinstance(frame, TTSSpeakFrame):
await self.pause_processing_frames()
elif isinstance(frame, LLMFullResponseEndFrame) and self._started:
await self.pause_processing_frames()
elif isinstance(frame, BotStoppedSpeakingFrame):
await self.resume_processing_frames()
async def _connect(self):
await self._connect_websocket()
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
self._keepalive_task = self.create_task(self._keepalive_task_handler())
async def _disconnect(self):
if self._receive_task:
await self.cancel_task(self._receive_task)
self._receive_task = None
if self._keepalive_task:
await self.cancel_task(self._keepalive_task)
self._keepalive_task = None
await self._disconnect_websocket()
async def _connect_websocket(self):
try:
logger.debug("Connecting to Neuphonic")
tts_config = {
**self._settings,
"voice_id": self._voice_id,
}
query_params = [f"api_key={self._api_key}"]
for key, value in tts_config.items():
if value is not None:
query_params.append(f"{key}={value}")
url = f"{self._url}/speak/{self._settings['lang_code']}?{'&'.join(query_params)}"
self._websocket = await websockets.connect(url)
except Exception as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
try:
await self.stop_all_metrics()
if self._websocket:
logger.debug("Disconnecting from Neuphonic")
await self._websocket.close()
self._websocket = None
self._started = False
except Exception as e:
logger.error(f"{self} error closing websocket: {e}")
async def _receive_messages(self):
async for message in self._websocket:
if isinstance(message, str):
msg = json.loads(message)
if msg.get("data", {}).get("audio") is not None:
await self.stop_ttfb_metrics()
audio = base64.b64decode(msg["data"]["audio"])
frame = TTSAudioRawFrame(audio, self.sample_rate, 1)
await self.push_frame(frame)
async def _keepalive_task_handler(self):
while True:
await asyncio.sleep(10)
await self._send_text("")
async def _send_text(self, text: str):
if self._websocket:
msg = {"text": text}
logger.debug(f"Sending text to websocket: {msg}")
await self._websocket.send(json.dumps(msg))
async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
logger.debug(f"Generating TTS: [{text}]")
try:
if not self._websocket:
await self._connect()
try:
if not self._started:
await self.start_ttfb_metrics()
yield TTSStartedFrame()
self._started = True
self._cumulative_time = 0
await self._send_text(text)
await self.start_tts_usage_metrics(text)
except Exception as e:
logger.error(f"{self} error sending message: {e}")
yield TTSStoppedFrame()
await self._disconnect()
await self._connect()
return
yield None
except Exception as e:
logger.error(f"{self} exception: {e}")
class NeuphonicHttpTTSService(TTSService):
"""Neuphonic Text-to-Speech service using HTTP streaming.
Args:
api_key: Neuphonic API key
voice_id: ID of the voice to use
url: Base URL for the Neuphonic API (default: "https://api.neuphonic.com")
sample_rate: Sample rate for audio output (default: 22050Hz)
encoding: Audio encoding format (default: "pcm_linear")
params: Additional parameters for TTS generation including language and speed
**kwargs: Additional keyword arguments passed to the parent class
"""
class InputParams(BaseModel):
language: Optional[Language] = Language.EN
speed: Optional[float] = 1.0
def __init__(
self,
*,
api_key: str,
voice_id: Optional[str] = None,
url: str = "https://api.neuphonic.com",
sample_rate: Optional[int] = 22050,
encoding: str = "pcm_linear",
params: InputParams = InputParams(),
**kwargs,
):
super().__init__(sample_rate=sample_rate, **kwargs)
self._api_key = api_key
self._url = url
self._settings = {
"lang_code": self.language_to_service_language(params.language),
"speed": params.speed,
"encoding": encoding,
"sampling_rate": sample_rate,
}
self.set_voice(voice_id)
def can_generate_metrics(self) -> bool:
return True
async def start(self, frame: StartFrame):
await super().start(frame)
async def flush_audio(self):
pass
async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
"""Generate speech from text using Neuphonic streaming API.
Args:
text: The text to convert to speech
Yields:
Frames containing audio data and status information
"""
logger.debug(f"Generating TTS: [{text}]")
client = Neuphonic(api_key=self._api_key, base_url=self._url.replace("https://", ""))
sse = client.tts.AsyncSSEClient()
try:
await self.start_ttfb_metrics()
response = sse.send(text, TTSConfig(**self._settings, voice_id=self._voice_id))
await self.start_tts_usage_metrics(text)
yield TTSStartedFrame()
async for message in response:
if message.status_code != 200:
logger.error(f"{self} error: {message.errors}")
yield ErrorFrame(error=f"Neuphonic API error: {message.errors}")
await self.stop_ttfb_metrics()
yield TTSAudioRawFrame(message.data.audio, self.sample_rate, 1)
except Exception as e:
logger.error(f"Error in run_tts: {e}")
yield ErrorFrame(error=str(e))
finally:
yield TTSStoppedFrame()

248
src/pipecat/services/openai.py
View File

@@ -27,23 +27,20 @@ from pydantic import BaseModel, Field
from pipecat.frames.frames import (
ErrorFrame,
Frame,
FunctionCallCancelFrame,
FunctionCallInProgressFrame,
FunctionCallResultFrame,
FunctionCallResultProperties,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
LLMMessagesFrame,
LLMTextFrame,
LLMUpdateSettingsFrame,
OpenAILLMContextAssistantTimestampFrame,
StartFrame,
StartInterruptionFrame,
TTSAudioRawFrame,
TTSStartedFrame,
TTSStoppedFrame,
URLImageRawFrame,
UserImageRawFrame,
UserImageRequestFrame,
VisionImageRawFrame,
)
from pipecat.metrics.metrics import LLMTokenUsage
@@ -63,7 +60,6 @@ from pipecat.services.ai_services import (
)
from pipecat.services.base_whisper import BaseWhisperSTTService, Transcription
from pipecat.transcriptions.language import Language
from pipecat.utils.time import time_now_iso8601
ValidVoice = Literal["alloy", "echo", "fable", "onyx", "nova", "shimmer"]
@@ -116,6 +112,7 @@ class BaseOpenAILLMService(LLMService):
base_url=None,
organization=None,
project=None,
default_headers: Mapping[str, str] | None = None,
params: InputParams = InputParams(),
**kwargs,
):
@@ -132,10 +129,23 @@ class BaseOpenAILLMService(LLMService):
}
self.set_model_name(model)
self._client = self.create_client(
api_key=api_key, base_url=base_url, organization=organization, project=project, **kwargs
api_key=api_key,
base_url=base_url,
organization=organization,
project=project,
default_headers=default_headers,
**kwargs,
)
def create_client(self, api_key=None, base_url=None, organization=None, project=None, **kwargs):
def create_client(
self,
api_key=None,
base_url=None,
organization=None,
project=None,
default_headers=None,
**kwargs,
):
return AsyncOpenAI(
api_key=api_key,
base_url=base_url,
@@ -146,6 +156,7 @@ class BaseOpenAILLMService(LLMService):
max_keepalive_connections=100, max_connections=1000, keepalive_expiry=None
)
),
default_headers=default_headers,
)
def can_generate_metrics(self) -> bool:
@@ -413,13 +424,13 @@ class OpenAIImageGenService(ImageGenService):
class OpenAISTTService(BaseWhisperSTTService):
"""OpenAI Whisper speech-to-text service.
"""OpenAI Speech-to-Text service that generates text from audio.
Uses OpenAI's Whisper API to convert audio to text. Requires an OpenAI API key
Uses OpenAI's transcription API to convert audio to text. Requires an OpenAI API key
set via the api_key parameter or OPENAI_API_KEY environment variable.
Args:
model: Whisper model to use. Defaults to "whisper-1".
model: Model to use — either gpt-4o or Whisper. Defaults to "gpt-4o-transcribe".
api_key: OpenAI API key. Defaults to None.
base_url: API base URL. Defaults to None.
language: Language of the audio input. Defaults to English.
@@ -431,7 +442,7 @@ class OpenAISTTService(BaseWhisperSTTService):
def __init__(
self,
*,
model: str = "whisper-1",
model: str = "gpt-4o-transcribe",
api_key: Optional[str] = None,
base_url: Optional[str] = None,
language: Optional[Language] = Language.EN,
@@ -472,22 +483,16 @@ class OpenAITTSService(TTSService):
"""OpenAI Text-to-Speech service that generates audio from text.
This service uses the OpenAI TTS API to generate PCM-encoded audio at 24kHz.
When using with DailyTransport, configure the sample rate in DailyParams
as shown below:
DailyParams(
audio_out_enabled=True,
audio_out_sample_rate=24_000,
)
Args:
api_key: OpenAI API key. Defaults to None.
voice: Voice ID to use. Defaults to "alloy".
model: TTS model to use ("tts-1" or "tts-1-hd"). Defaults to "tts-1".
sample_rate: Output audio sample rate in Hz. Defaults to 24000.
model: TTS model to use. Defaults to "gpt-4o-mini-tts".
sample_rate: Output audio sample rate in Hz. Defaults to None.
**kwargs: Additional keyword arguments passed to TTSService.
The service returns PCM-encoded audio at the specified sample rate.
"""
OPENAI_SAMPLE_RATE = 24000 # OpenAI TTS always outputs at 24kHz
@@ -497,7 +502,7 @@ class OpenAITTSService(TTSService):
*,
api_key: Optional[str] = None,
voice: str = "alloy",
model: Literal["tts-1", "tts-1-hd"] = "tts-1",
model: str = "gpt-4o-mini-tts",
sample_rate: Optional[int] = None,
**kwargs,
):
@@ -564,156 +569,67 @@ class OpenAITTSService(TTSService):
logger.exception(f"{self} error generating TTS: {e}")
# internal use only -- todo: refactor
@dataclass
class OpenAIImageMessageFrame(Frame):
user_image_raw_frame: UserImageRawFrame
text: Optional[str] = None
class OpenAIUserContextAggregator(LLMUserContextAggregator):
def __init__(self, context: OpenAILLMContext, **kwargs):
super().__init__(context=context, **kwargs)
async def process_frame(self, frame, direction):
await super().process_frame(frame, direction)
# Our parent method has already called push_frame(). So we can't interrupt the
# flow here and we don't need to call push_frame() ourselves.
try:
if isinstance(frame, UserImageRequestFrame):
# The LLM sends a UserImageRequestFrame upstream. Cache any context provided with
# that frame so we can use it when we assemble the image message in the assistant
# context aggregator.
if frame.context:
if isinstance(frame.context, str):
self._context._user_image_request_context[frame.user_id] = frame.context
else:
logger.error(
f"Unexpected UserImageRequestFrame context type: {type(frame.context)}"
)
del self._context._user_image_request_context[frame.user_id]
else:
if frame.user_id in self._context._user_image_request_context:
del self._context._user_image_request_context[frame.user_id]
elif isinstance(frame, UserImageRawFrame):
# Push a new OpenAIImageMessageFrame with the text context we cached
# downstream to be handled by our assistant context aggregator. This is
# necessary so that we add the message to the context in the right order.
text = self._context._user_image_request_context.get(frame.user_id) or ""
if text:
del self._context._user_image_request_context[frame.user_id]
frame = OpenAIImageMessageFrame(user_image_raw_frame=frame, text=text)
await self.push_frame(frame)
except Exception as e:
logger.error(f"Error processing frame: {e}")
pass
class OpenAIAssistantContextAggregator(LLMAssistantContextAggregator):
def __init__(self, context: OpenAILLMContext, **kwargs):
super().__init__(context=context, **kwargs)
self._function_calls_in_progress = {}
self._function_call_result = None
self._pending_image_frame_message = None
async def handle_function_call_in_progress(self, frame: FunctionCallInProgressFrame):
self._context.add_message(
{
"role": "assistant",
"tool_calls": [
{
"id": frame.tool_call_id,
"function": {
"name": frame.function_name,
"arguments": json.dumps(frame.arguments),
},
"type": "function",
}
],
}
)
self._context.add_message(
{
"role": "tool",
"content": "IN_PROGRESS",
"tool_call_id": frame.tool_call_id,
}
)
async def process_frame(self, frame, direction):
await super().process_frame(frame, direction)
# See note above about not calling push_frame() here.
if isinstance(frame, StartInterruptionFrame):
self._function_calls_in_progress.clear()
self._function_call_finished = None
elif isinstance(frame, FunctionCallInProgressFrame):
logger.debug(f"FunctionCallInProgressFrame: {frame}")
self._function_calls_in_progress[frame.tool_call_id] = frame
elif isinstance(frame, FunctionCallResultFrame):
logger.debug(f"FunctionCallResultFrame: {frame}")
if frame.tool_call_id in self._function_calls_in_progress:
del self._function_calls_in_progress[frame.tool_call_id]
self._function_call_result = frame
# TODO-CB: Kwin wants us to refactor this out of here but I REFUSE
await self.push_aggregation()
else:
logger.warning(
"FunctionCallResultFrame tool_call_id does not match any function call in progress"
)
self._function_call_result = None
elif isinstance(frame, OpenAIImageMessageFrame):
self._pending_image_frame_message = frame
await self.push_aggregation()
async def handle_function_call_result(self, frame: FunctionCallResultFrame):
if frame.result:
result = json.dumps(frame.result)
await self._update_function_call_result(frame.function_name, frame.tool_call_id, result)
else:
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, "COMPLETED"
)
async def push_aggregation(self):
if not (
self._aggregation or self._function_call_result or self._pending_image_frame_message
):
return
async def handle_function_call_cancel(self, frame: FunctionCallCancelFrame):
await self._update_function_call_result(
frame.function_name, frame.tool_call_id, "CANCELLED"
)
run_llm = False
properties: Optional[FunctionCallResultProperties] = None
async def _update_function_call_result(
self, function_name: str, tool_call_id: str, result: str
):
for message in self._context.messages:
if (
message["role"] == "tool"
and message["tool_call_id"]
and message["tool_call_id"] == tool_call_id
):
message["content"] = result
aggregation = self._aggregation.strip()
self.reset()
try:
if aggregation:
self._context.add_message({"role": "assistant", "content": aggregation})
if self._function_call_result:
frame = self._function_call_result
properties = frame.properties
self._function_call_result = None
if frame.result:
self._context.add_message(
{
"role": "assistant",
"tool_calls": [
{
"id": frame.tool_call_id,
"function": {
"name": frame.function_name,
"arguments": json.dumps(frame.arguments),
},
"type": "function",
}
],
}
)
self._context.add_message(
{
"role": "tool",
"content": json.dumps(frame.result),
"tool_call_id": frame.tool_call_id,
}
)
if properties and properties.run_llm is not None:
# If the tool call result has a run_llm property, use it
run_llm = properties.run_llm
else:
# Default behavior is to run the LLM if there are no function calls in progress
run_llm = not bool(self._function_calls_in_progress)
if self._pending_image_frame_message:
frame = self._pending_image_frame_message
self._pending_image_frame_message = None
self._context.add_image_frame_message(
format=frame.user_image_raw_frame.format,
size=frame.user_image_raw_frame.size,
image=frame.user_image_raw_frame.image,
text=frame.text,
)
run_llm = True
if run_llm:
await self.push_context_frame(FrameDirection.UPSTREAM)
# Emit the on_context_updated callback once the function call result is added to the context
if properties and properties.on_context_updated is not None:
await properties.on_context_updated()
# Push context frame
await self.push_context_frame()
# Push timestamp frame with current time
timestamp_frame = OpenAILLMContextAssistantTimestampFrame(timestamp=time_now_iso8601())
await self.push_frame(timestamp_frame)
except Exception as e:
logger.error(f"Error processing frame: {e}")
async def handle_user_image_frame(self, frame: UserImageRawFrame):
await self._update_function_call_result(
frame.request.function_name, frame.request.tool_call_id, "COMPLETED"
)
self._context.add_image_frame_message(
format=frame.format,
size=frame.size,
image=frame.image,
text=frame.request.context,
)

8
src/pipecat/services/openai_realtime_beta/__init__.py
View File

@@ -1,3 +1,9 @@
from .azure import AzureRealtimeBetaLLMService
from .events import InputAudioTranscription, SessionProperties, TurnDetection
from .events import (
InputAudioNoiseReduction,
InputAudioTranscription,
SemanticTurnDetection,
SessionProperties,
TurnDetection,
)
from .openai import OpenAIRealtimeBetaLLMService

72
src/pipecat/services/openai_realtime_beta/context.py
View File

@@ -12,6 +12,7 @@ from loguru import logger
from pipecat.frames.frames import (
Frame,
FunctionCallResultFrame,
FunctionCallResultProperties,
LLMMessagesUpdateFrame,
LLMSetToolsFrame,
@@ -174,67 +175,12 @@ class OpenAIRealtimeUserContextAggregator(OpenAIUserContextAggregator):
class OpenAIRealtimeAssistantContextAggregator(OpenAIAssistantContextAggregator):
async def push_aggregation(self):
# the only thing we implement here is function calling. in all other cases, messages
# are added to the context when we receive openai realtime api events
if not self._function_call_result:
return
async def handle_function_call_result(self, frame: FunctionCallResultFrame):
await super().handle_function_call_result(frame)
properties: Optional[FunctionCallResultProperties] = None
self.reset()
try:
run_llm = True
frame = self._function_call_result
properties = frame.properties
self._function_call_result = None
if frame.result:
# The "tool_call" message from the LLM that triggered the function call
self._context.add_message(
{
"role": "assistant",
"tool_calls": [
{
"id": frame.tool_call_id,
"function": {
"name": frame.function_name,
"arguments": json.dumps(frame.arguments),
},
"type": "function",
}
],
}
)
# The result of the function call. Need to add this both to our context here and to
# the openai realtime api context.
result_message = {
"role": "tool",
"content": json.dumps(frame.result),
"tool_call_id": frame.tool_call_id,
}
self._context.add_message(result_message)
# The standard function callback code path pushes the FunctionCallResultFrame from the llm itself,
# so we didn't have a chance to add the result to the openai realtime api context. Let's push a
# special frame to do that.
await self.push_frame(
RealtimeFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
)
if properties and properties.run_llm is not None:
# If the tool call result has a run_llm property, use it
run_llm = properties.run_llm
else:
# Default behavior is to run the LLM if there are no function calls in progress
run_llm = not bool(self._function_calls_in_progress)
if run_llm:
await self.push_context_frame(FrameDirection.UPSTREAM)
# Emit the on_context_updated callback once the function call result is added to the context
if properties and properties.on_context_updated is not None:
await properties.on_context_updated()
await self.push_context_frame()
except Exception as e:
logger.error(f"Error processing frame: {e}")
# The standard function callback code path pushes the FunctionCallResultFrame from the llm itself,
# so we didn't have a chance to add the result to the openai realtime api context. Let's push a
# special frame to do that.
await self.push_frame(
RealtimeFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
)

60
src/pipecat/services/openai_realtime_beta/events.py
View File

@@ -17,7 +17,29 @@ from pydantic import BaseModel, Field
class InputAudioTranscription(BaseModel):
model: Optional[str] = "whisper-1"
"""Configuration for audio transcription settings.
Attributes:
model: Transcription model to use (e.g., "gpt-4o-transcribe", "whisper-1").
language: Optional language code for transcription.
prompt: Optional transcription hint text.
"""
model: str = "gpt-4o-transcribe"
language: Optional[str]
prompt: Optional[str]
def __init__(
self,
model: Optional[str] = "gpt-4o-transcribe",
language: Optional[str] = None,
prompt: Optional[str] = None,
):
super().__init__(model=model, language=language, prompt=prompt)
if self.model != "gpt-4o-transcribe" and (self.language or self.prompt):
raise ValueError(
"Fields 'language' and 'prompt' are only supported when model is 'gpt-4o-transcribe'"
)
class TurnDetection(BaseModel):
@@ -27,6 +49,17 @@ class TurnDetection(BaseModel):
silence_duration_ms: Optional[int] = 800
class SemanticTurnDetection(BaseModel):
type: Optional[Literal["semantic_vad"]] = "semantic_vad"
eagerness: Optional[Literal["low", "medium", "high", "auto"]] = None
create_response: Optional[bool] = None
interrupt_response: Optional[bool] = None
class InputAudioNoiseReduction(BaseModel):
type: Optional[Literal["near_field", "far_field"]]
class SessionProperties(BaseModel):
modalities: Optional[List[Literal["text", "audio"]]] = None
instructions: Optional[str] = None
@@ -34,8 +67,11 @@ class SessionProperties(BaseModel):
input_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None
output_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None
input_audio_transcription: Optional[InputAudioTranscription] = None
input_audio_noise_reduction: Optional[InputAudioNoiseReduction] = None
# set turn_detection to False to disable turn detection
turn_detection: Optional[Union[TurnDetection, bool]] = Field(default=None)
turn_detection: Optional[Union[TurnDetection, SemanticTurnDetection, bool]] = Field(
default=None
)
tools: Optional[List[Dict]] = None
tool_choice: Optional[Literal["auto", "none", "required"]] = None
temperature: Optional[float] = None
@@ -93,6 +129,7 @@ class RealtimeError(BaseModel):
code: Optional[str] = ""
message: str
param: Optional[str] = None
event_id: Optional[str] = None
#
@@ -150,6 +187,11 @@ class ConversationItemDeleteEvent(ClientEvent):
item_id: str
class ConversationItemRetrieveEvent(ClientEvent):
type: Literal["conversation.item.retrieve"] = "conversation.item.retrieve"
item_id: str
class ResponseCreateEvent(ClientEvent):
type: Literal["response.create"] = "response.create"
response: Optional[ResponseProperties] = None
@@ -193,6 +235,13 @@ class ConversationItemCreated(ServerEvent):
item: ConversationItem
class ConversationItemInputAudioTranscriptionDelta(ServerEvent):
type: Literal["conversation.item.input_audio_transcription.delta"]
item_id: str
content_index: int
delta: str
class ConversationItemInputAudioTranscriptionCompleted(ServerEvent):
type: Literal["conversation.item.input_audio_transcription.completed"]
item_id: str
@@ -219,6 +268,11 @@ class ConversationItemDeleted(ServerEvent):
item_id: str
class ConversationItemRetrieved(ServerEvent):
type: Literal["conversation.item.retrieved"]
item: ConversationItem
class ResponseCreated(ServerEvent):
type: Literal["response.created"]
response: "Response"
@@ -400,10 +454,12 @@ _server_event_types = {
"input_audio_buffer.speech_started": InputAudioBufferSpeechStarted,
"input_audio_buffer.speech_stopped": InputAudioBufferSpeechStopped,
"conversation.item.created": ConversationItemCreated,
"conversation.item.input_audio_transcription.delta": ConversationItemInputAudioTranscriptionDelta,
"conversation.item.input_audio_transcription.completed": ConversationItemInputAudioTranscriptionCompleted,
"conversation.item.input_audio_transcription.failed": ConversationItemInputAudioTranscriptionFailed,
"conversation.item.truncated": ConversationItemTruncated,
"conversation.item.deleted": ConversationItemDeleted,
"conversation.item.retrieved": ConversationItemRetrieved,
"response.created": ResponseCreated,
"response.done": ResponseDone,
"response.output_item.added": ResponseOutputItemAdded,

82
src/pipecat/services/openai_realtime_beta/openai.py
View File

@@ -30,6 +30,7 @@ from pipecat.frames.frames import (
ErrorFrame,
Frame,
InputAudioRawFrame,
InterimTranscriptionFrame,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
LLMMessagesAppendFrame,
@@ -43,6 +44,7 @@ from pipecat.frames.frames import (
TTSAudioRawFrame,
TTSStartedFrame,
TTSStoppedFrame,
TTSTextFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
@@ -114,12 +116,35 @@ class OpenAIRealtimeBetaLLMService(LLMService):
self._messages_added_manually = {}
self._user_and_response_message_tuple = None
self._register_event_handler("on_conversation_item_created")
self._register_event_handler("on_conversation_item_updated")
self._retrieve_conversation_item_futures = {}
def can_generate_metrics(self) -> bool:
return True
def set_audio_input_paused(self, paused: bool):
self._audio_input_paused = paused
async def retrieve_conversation_item(self, item_id: str):
future = self.get_event_loop().create_future()
retrieval_in_flight = False
if not self._retrieve_conversation_item_futures.get(item_id):
self._retrieve_conversation_item_futures[item_id] = []
else:
retrieval_in_flight = True
self._retrieve_conversation_item_futures[item_id].append(future)
if not retrieval_in_flight:
await self.send_client_event(
# Set event_id to "rci_{item_id}" so that we can identify an
# error later if the retrieval fails. We don't need a UUID
# suffix to the event_id because we're ensuring only one
# in-flight retrieval per item_id. (Note: "rci" = "retrieve
# conversation item")
events.ConversationItemRetrieveEvent(item_id=item_id, event_id=f"rci_{item_id}")
)
return await future
#
# standard AIService frame handling
#
@@ -353,8 +378,12 @@ class OpenAIRealtimeBetaLLMService(LLMService):
await self._handle_evt_audio_done(evt)
elif evt.type == "conversation.item.created":
await self._handle_evt_conversation_item_created(evt)
elif evt.type == "conversation.item.input_audio_transcription.delta":
await self._handle_evt_input_audio_transcription_delta(evt)
elif evt.type == "conversation.item.input_audio_transcription.completed":
await self.handle_evt_input_audio_transcription_completed(evt)
elif evt.type == "conversation.item.retrieved":
await self._handle_conversation_item_retrieved(evt)
elif evt.type == "response.done":
await self._handle_evt_response_done(evt)
elif evt.type == "input_audio_buffer.speech_started":
@@ -364,9 +393,10 @@ class OpenAIRealtimeBetaLLMService(LLMService):
elif evt.type == "response.audio_transcript.delta":
await self._handle_evt_audio_transcript_delta(evt)
elif evt.type == "error":
await self._handle_evt_error(evt)
# errors are fatal, so exit the receive loop
return
if not await self._maybe_handle_evt_retrieve_conversation_item_error(evt):
await self._handle_evt_error(evt)
# errors are fatal, so exit the receive loop
return
async def _handle_evt_session_created(self, evt):
# session.created is received right after connecting. Send a message
@@ -408,6 +438,8 @@ class OpenAIRealtimeBetaLLMService(LLMService):
# receive a BotStoppedSpeakingFrame from the output transport.
async def _handle_evt_conversation_item_created(self, evt):
await self._call_event_handler("on_conversation_item_created", evt.item.id, evt.item)
# This will get sent from the server every time a new "message" is added
# to the server's conversation state, whether we create it via the API
# or the server creates it from LLM output.
@@ -424,7 +456,16 @@ class OpenAIRealtimeBetaLLMService(LLMService):
self._current_assistant_response = evt.item
await self.push_frame(LLMFullResponseStartFrame())
async def _handle_evt_input_audio_transcription_delta(self, evt):
if self._send_transcription_frames:
await self.push_frame(
# no way to get a language code?
InterimTranscriptionFrame(evt.delta, "", time_now_iso8601())
)
async def handle_evt_input_audio_transcription_completed(self, evt):
await self._call_event_handler("on_conversation_item_updated", evt.item_id, None)
if self._send_transcription_frames:
await self.push_frame(
# no way to get a language code?
@@ -442,6 +483,12 @@ class OpenAIRealtimeBetaLLMService(LLMService):
# User message without preceding conversation.item.created. Bug?
logger.warning(f"Transcript for unknown user message: {evt}")
async def _handle_conversation_item_retrieved(self, evt: events.ConversationItemRetrieved):
futures = self._retrieve_conversation_item_futures.pop(evt.item.id, None)
if futures:
for future in futures:
future.set_result(evt.item)
async def _handle_evt_response_done(self, evt):
# todo: figure out whether there's anything we need to do for "cancelled" events
# usage metrics
@@ -454,7 +501,15 @@ class OpenAIRealtimeBetaLLMService(LLMService):
await self.stop_processing_metrics()
await self.push_frame(LLMFullResponseEndFrame())
self._current_assistant_response = None
# error handling
if evt.response.status == "failed":
await self.push_error(
ErrorFrame(error=evt.response.status_details["error"]["message"], fatal=True)
)
return
# response content
for item in evt.response.output:
await self._call_event_handler("on_conversation_item_updated", item.id, item)
pair = self._user_and_response_message_tuple
if pair:
user, assistant = pair
@@ -471,6 +526,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
async def _handle_evt_audio_transcript_delta(self, evt):
if evt.delta:
await self.push_frame(LLMTextFrame(evt.delta))
await self.push_frame(TTSTextFrame(evt.delta))
async def _handle_evt_speech_started(self, evt):
await self._truncate_current_audio_response()
@@ -485,6 +541,22 @@ class OpenAIRealtimeBetaLLMService(LLMService):
await self.push_frame(StopInterruptionFrame())
await self.push_frame(UserStoppedSpeakingFrame())
async def _maybe_handle_evt_retrieve_conversation_item_error(self, evt: events.ErrorEvent):
"""If the given error event is an error retrieving a conversation item:
- set an exception on the future that retrieve_conversation_item() is waiting on
- return true
Otherwise:
- return false
"""
if evt.error.code == "item_retrieve_invalid_item_id":
item_id = evt.error.event_id.split("_", 1)[1] # event_id is of the form "rci_{item_id}"
futures = self._retrieve_conversation_item_futures.pop(item_id, None)
if futures:
for future in futures:
future.set_exception(Exception(evt.error.message))
return True
return False
async def _handle_evt_error(self, evt):
# Errors are fatal to this connection. Send an ErrorFrame.
await self.push_error(ErrorFrame(error=f"Error: {evt}", fatal=True))
@@ -507,7 +579,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
arguments = json.loads(item.arguments)
if self.has_function(function_name):
run_llm = index == total_items - 1
if function_name in self._callbacks.keys():
if function_name in self._functions.keys():
await self.call_function(
context=self._context,
tool_call_id=tool_id,
@@ -515,7 +587,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
arguments=arguments,
run_llm=run_llm,
)
elif None in self._callbacks.keys():
elif None in self._functions.keys():
await self.call_function(
context=self._context,
tool_call_id=tool_id,

8
src/pipecat/services/playht.py
View File

@@ -160,7 +160,7 @@ class PlayHTTTSService(InterruptibleTTSService):
await self._connect_websocket()
if not self._receive_task:
self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
async def _disconnect(self):
if self._receive_task:
@@ -183,12 +183,14 @@ class PlayHTTTSService(InterruptibleTTSService):
raise ValueError("WebSocket URL is not a string")
self._websocket = await websockets.connect(self._websocket_url)
except ValueError as ve:
logger.error(f"{self} initialization error: {ve}")
except ValueError as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
except Exception as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
try:

9
src/pipecat/services/rime.py
View File

@@ -27,6 +27,8 @@ from pipecat.frames.frames import (
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import AudioContextWordTTSService, TTSService
from pipecat.transcriptions.language import Language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
from pipecat.utils.text.skip_tags_aggregator import SkipTagsAggregator
try:
import websockets
@@ -78,6 +80,7 @@ class RimeTTSService(AudioContextWordTTSService):
model: str = "mistv2",
sample_rate: Optional[int] = None,
params: InputParams = InputParams(),
text_aggregator: Optional[BaseTextAggregator] = None,
**kwargs,
):
"""Initialize Rime TTS service.
@@ -97,6 +100,7 @@ class RimeTTSService(AudioContextWordTTSService):
push_stop_frames=True,
pause_frame_processing=True,
sample_rate=sample_rate,
text_aggregator=text_aggregator or SkipTagsAggregator([("spell(", ")")]),
**kwargs,
)
@@ -167,7 +171,7 @@ class RimeTTSService(AudioContextWordTTSService):
await self._connect_websocket()
if not self._receive_task:
self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
async def _disconnect(self):
"""Close websocket connection and clean up tasks."""
@@ -190,6 +194,7 @@ class RimeTTSService(AudioContextWordTTSService):
except Exception as e:
logger.error(f"{self} initialization error: {e}")
self._websocket = None
await self._call_event_handler("on_connection_error", f"{e}")
async def _disconnect_websocket(self):
"""Close websocket connection and reset state."""
@@ -249,7 +254,9 @@ class RimeTTSService(AudioContextWordTTSService):
async def flush_audio(self):
if not self._context_id or not self._websocket:
return
logger.trace(f"{self}: flushing audio")
await self._get_websocket().send(json.dumps({"text": " "}))
self._context_id = None
async def _receive_messages(self):

7
src/pipecat/services/tavus.py
View File

@@ -37,6 +37,7 @@ class TavusVideoService(AIService):
replica_id: str,
persona_id: str = "pipecat0", # Use `pipecat0` so that your TTS voice is used in place of the Tavus persona
session: aiohttp.ClientSession,
sample_rate: int = 16000,
**kwargs,
) -> None:
super().__init__(**kwargs)
@@ -44,6 +45,7 @@ class TavusVideoService(AIService):
self._replica_id = replica_id
self._persona_id = persona_id
self._session = session
self._sample_rate = sample_rate
self._conversation_id: str
@@ -94,7 +96,7 @@ class TavusVideoService(AIService):
async def _encode_audio_and_send(self, audio: bytes, in_rate: int, done: bool) -> None:
"""Encodes audio to base64 and sends it to Tavus"""
if not done:
audio = await self._resampler.resample(audio, in_rate, 16000)
audio = await self._resampler.resample(audio, in_rate, self._sample_rate)
audio_base64 = base64.b64encode(audio).decode("utf-8")
logger.trace(f"{self}: sending {len(audio)} bytes")
await self._send_audio_message(audio_base64, done=done)
@@ -108,7 +110,7 @@ class TavusVideoService(AIService):
elif isinstance(frame, TTSAudioRawFrame):
await self._encode_audio_and_send(frame.audio, frame.sample_rate, done=False)
elif isinstance(frame, TTSStoppedFrame):
await self._encode_audio_and_send(b"\x00", 16000, done=True)
await self._encode_audio_and_send(b"\x00", self._sample_rate, done=True)
await self.stop_ttfb_metrics()
await self.stop_processing_metrics()
elif isinstance(frame, StartInterruptionFrame):
@@ -137,6 +139,7 @@ class TavusVideoService(AIService):
"inference_id": self._current_idx_str,
"audio": audio_base64,
"done": done,
"sample_rate": self._sample_rate,
},
}
)

403
src/pipecat/services/ultravox.py Normal file
View File

@@ -0,0 +1,403 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
"""This module implements Ultravox speech-to-text with a locally-loaded model."""
import json
import os
import time
from typing import AsyncGenerator, List, Optional
import numpy as np
from huggingface_hub import login
from loguru import logger
from pipecat.frames.frames import (
AudioRawFrame,
CancelFrame,
EndFrame,
ErrorFrame,
Frame,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
LLMTextFrame,
StartFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import AIService
try:
from transformers import AutoTokenizer
from vllm import AsyncLLMEngine, SamplingParams
from vllm.engine.arg_utils import AsyncEngineArgs
except ModuleNotFoundError as e:
logger.error(f"Exception: {e}")
logger.error("In order to use Ultravox, you need to `pip install pipecat-ai[ultravox]`.")
raise Exception(f"Missing module: {e}")
class AudioBuffer:
"""Buffer to collect audio frames before processing.
Attributes:
frames: List of AudioRawFrames to process
started_at: Timestamp when speech started
is_processing: Flag to prevent concurrent processing
"""
def __init__(self):
self.frames: List[AudioRawFrame] = []
self.started_at: Optional[float] = None
self.is_processing: bool = False
class UltravoxModel:
"""Model wrapper for the Ultravox multimodal model.
This class handles loading and running the Ultravox model for speech-to-text.
Args:
model_name: The name or path of the Ultravox model to load
Attributes:
model_name: The name of the loaded model
engine: The vLLM engine for model inference
tokenizer: The tokenizer for the model
stop_token_ids: Optional token IDs to stop generation
"""
def __init__(self, model_name: str = "fixie-ai/ultravox-v0_4_1-llama-3_1-8b"):
self.model_name = model_name
self._initialize_engine()
self._initialize_tokenizer()
self.stop_token_ids = None
def _initialize_engine(self):
"""Initialize the vLLM engine for inference."""
engine_args = AsyncEngineArgs(
model=self.model_name,
gpu_memory_utilization=0.9,
max_model_len=8192,
trust_remote_code=True,
)
self.engine = AsyncLLMEngine.from_engine_args(engine_args)
def _initialize_tokenizer(self):
"""Initialize the tokenizer for the model."""
self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
def format_prompt(self, messages: list):
"""Format chat messages into a prompt for the model.
Args:
messages: List of message dictionaries with 'role' and 'content'
Returns:
str: Formatted prompt string
"""
return self.tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
async def generate(
self,
messages: list,
temperature: float = 0.7,
max_tokens: int = 100,
audio: np.ndarray = None,
):
"""Generate text from audio input using the model.
Args:
messages: List of message dictionaries
temperature: Sampling temperature
max_tokens: Maximum tokens to generate
audio: Audio data as numpy array
Yields:
str: JSON chunks of the generated response
"""
sampling_params = SamplingParams(
temperature=temperature, max_tokens=max_tokens, stop_token_ids=self.stop_token_ids
)
mm_data = {"audio": audio}
inputs = {"prompt": self.format_prompt(messages), "multi_modal_data": mm_data}
results_generator = self.engine.generate(inputs, sampling_params, str(time.time()))
previous_text = ""
first_chunk = True
async for output in results_generator:
prompt_output = output.outputs
new_text = prompt_output[0].text[len(previous_text) :]
previous_text = prompt_output[0].text
# Construct OpenAI-compatible chunk
chunk = {
"id": str(int(time.time() * 1000)),
"object": "chat.completion.chunk",
"created": int(time.time()),
"model": self.model_name,
"choices": [
{
"index": 0,
"delta": {},
"finish_reason": None,
}
],
}
# Include the role in the first chunk
if first_chunk:
chunk["choices"][0]["delta"]["role"] = "assistant"
first_chunk = False
# Add new text to the delta if any
if new_text:
chunk["choices"][0]["delta"]["content"] = new_text
# Capture a finish reason if it's provided
finish_reason = prompt_output[0].finish_reason or None
if finish_reason and finish_reason != "none":
chunk["choices"][0]["finish_reason"] = finish_reason
yield json.dumps(chunk)
class UltravoxSTTService(AIService):
"""Service to transcribe audio using the Ultravox multimodal model.
This service collects audio frames and processes them with Ultravox
to generate text transcriptions.
Args:
model_size: The Ultravox model to use (ModelSize enum or string)
hf_token: Hugging Face token for model access
temperature: Sampling temperature for generation
max_tokens: Maximum tokens to generate
**kwargs: Additional arguments passed to AIService
Attributes:
model: The UltravoxModel instance
buffer: Buffer to collect audio frames
temperature: Temperature for text generation
max_tokens: Maximum tokens to generate
_connection_active: Flag indicating if service is active
"""
def __init__(
self,
*,
model_size: str = "fixie-ai/ultravox-v0_4_1-llama-3_1-8b",
hf_token: Optional[str] = None,
temperature: float = 0.7,
max_tokens: int = 100,
**kwargs,
):
super().__init__(**kwargs)
# Authenticate with Hugging Face if token provided
if hf_token:
login(token=hf_token)
elif os.environ.get("HF_TOKEN"):
login(token=os.environ.get("HF_TOKEN"))
else:
logger.warning("No Hugging Face token provided. Model may not load correctly.")
# Initialize model
model_name = model_size if isinstance(model_size, str) else model_size.value
self._model = UltravoxModel(model_name=model_name)
# Initialize service state
self._buffer = AudioBuffer()
self._temperature = temperature
self._max_tokens = max_tokens
self._connection_active = False
logger.info(f"Initialized UltravoxSTTService with model: {model_name}")
def can_generate_metrics(self) -> bool:
"""Indicates whether this service can generate metrics.
Returns:
bool: True, as this service supports metric generation.
"""
return True
async def start(self, frame: StartFrame):
"""Handle service start.
Args:
frame: StartFrame that triggered this method
"""
await super().start(frame)
self._connection_active = True
logger.info("UltravoxSTTService started")
async def stop(self, frame: EndFrame):
"""Handle service stop.
Args:
frame: EndFrame that triggered this method
"""
await super().stop(frame)
self._connection_active = False
logger.info("UltravoxSTTService stopped")
async def cancel(self, frame: CancelFrame):
"""Handle service cancellation.
Args:
frame: CancelFrame that triggered this method
"""
await super().cancel(frame)
self._connection_active = False
self._buffer = AudioBuffer()
logger.info("UltravoxSTTService cancelled")
async def process_frame(self, frame: Frame, direction: FrameDirection):
"""Process incoming frames.
This method collects audio frames and processes them when speech ends.
Args:
frame: The frame to process
direction: Direction of the frame (input/output)
"""
await super().process_frame(frame, direction)
if isinstance(frame, UserStartedSpeakingFrame):
logger.info("Speech started")
self._buffer = AudioBuffer()
self._buffer.started_at = time.time()
elif isinstance(frame, AudioRawFrame) and self._buffer.started_at is not None:
self._buffer.frames.append(frame)
elif isinstance(frame, UserStoppedSpeakingFrame):
if self._buffer.frames and not self._buffer.is_processing:
logger.info("Speech ended, processing buffer...")
await self.process_generator(self._process_audio_buffer())
return # Return early to avoid pushing None frame
# Only push the original frame if we haven't processed audio
if frame is not None:
await self.push_frame(frame, direction)
async def _process_audio_buffer(self) -> AsyncGenerator[Frame, None]:
"""Process collected audio frames with Ultravox.
This method concatenates audio frames, processes them with the model,
and yields the resulting text frames.
Yields:
Frame: TextFrame containing the transcribed text
"""
try:
self._buffer.is_processing = True
# Check if we have valid frames before processing
if not self._buffer.frames:
logger.warning("No audio frames to process")
yield ErrorFrame("No audio frames to process")
return
# Process audio frames
audio_arrays = []
for f in self._buffer.frames:
if hasattr(f, "audio") and f.audio:
# Handle bytes data - these are int16 PCM samples
if isinstance(f.audio, bytes):
try:
# Convert bytes to int16 array
arr = np.frombuffer(f.audio, dtype=np.int16)
if arr.size > 0: # Check if array is not empty
audio_arrays.append(arr)
except Exception as e:
logger.error(f"Error processing bytes audio frame: {e}")
# Handle numpy array data
elif isinstance(f.audio, np.ndarray):
if f.audio.size > 0: # Check if array is not empty
# Ensure it's int16 data
if f.audio.dtype != np.int16:
logger.info(f"Converting array from {f.audio.dtype} to int16")
audio_arrays.append(f.audio.astype(np.int16))
else:
audio_arrays.append(f.audio)
# Only proceed if we have valid audio arrays
if not audio_arrays:
logger.warning("No valid audio data found in frames")
yield ErrorFrame("No valid audio data found in frames")
return
# Concatenate audio frames - all should be int16 now
audio_data = np.concatenate(audio_arrays)
audio_int16 = audio_data # Already in int16 format
# Save int16 audio
# Convert int16 to float32 and normalize for model input
audio_float32 = audio_int16.astype(np.float32) / 32768.0
# Generate text using the model
if self._model:
try:
logger.info("Generating text from audio using model...")
full_response = ""
# Start metrics tracking
await self.start_ttfb_metrics()
await self.start_processing_metrics()
async for response in self.model.generate(
messages=[{"role": "user", "content": "<|audio|>\n"}],
temperature=self.temperature,
max_tokens=self.max_tokens,
audio=audio_float32,
):
# Stop TTFB metrics after first response
await self.stop_ttfb_metrics()
chunk = json.loads(response)
if "choices" in chunk and len(chunk["choices"]) > 0:
delta = chunk["choices"][0]["delta"]
if "content" in delta:
new_text = delta["content"]
full_response += new_text
# Stop processing metrics after completion
await self.stop_processing_metrics()
logger.info(f"Generated text: {full_response}")
# Create a transcription frame with the generated text
yield LLMFullResponseStartFrame()
text_frame = LLMTextFrame(text=full_response.strip())
yield text_frame
yield LLMFullResponseEndFrame()
except Exception as e:
logger.error(f"Error generating text from model: {e}")
yield ErrorFrame(f"Error generating text: {str(e)}")
else:
logger.warning("No model available for text generation")
yield ErrorFrame("No model available for text generation")
except Exception as e:
logger.error(f"Error processing audio buffer: {e}")
import traceback
logger.error(traceback.format_exc())
yield ErrorFrame(f"Error processing audio: {str(e)}")
finally:
self._buffer.is_processing = False
self._buffer.frames = []
self._buffer.started_at = None

40
src/pipecat/services/websocket_service.py
View File

@@ -19,9 +19,10 @@ from pipecat.utils.network import exponential_backoff_time
class WebsocketService(ABC):
"""Base class for websocket-based services with reconnection logic."""
def __init__(self):
def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
"""Initialize websocket attributes."""
self._websocket: Optional[websockets.WebSocketClientProtocol] = None
self._reconnect_on_error = reconnect_on_error
async def _verify_connection(self) -> bool:
"""Verify websocket connection is working.
@@ -72,24 +73,29 @@ class WebsocketService(ABC):
self._websocket.close_rcvd_then_sent,
)
except Exception as e:
retry_count += 1
if retry_count >= MAX_RETRIES:
message = f"{self} error receiving messages: {e}"
logger.error(message)
await report_error(ErrorFrame(message, fatal=True))
message = f"{self} error receiving messages: {e}"
logger.error(message)
if self._reconnect_on_error:
retry_count += 1
if retry_count >= MAX_RETRIES:
await report_error(ErrorFrame(message, fatal=True))
break
logger.warning(f"{self} connection error, will retry: {e}")
await report_error(ErrorFrame(message))
try:
if await self._reconnect_websocket(retry_count):
retry_count = 0 # Reset counter on successful reconnection
wait_time = exponential_backoff_time(retry_count)
await asyncio.sleep(wait_time)
except Exception as reconnect_error:
logger.error(f"{self} reconnection failed: {reconnect_error}")
else:
await report_error(ErrorFrame(message))
break
logger.warning(f"{self} connection error, will retry: {e}")
try:
if await self._reconnect_websocket(retry_count):
retry_count = 0 # Reset counter on successful reconnection
wait_time = exponential_backoff_time(retry_count)
await asyncio.sleep(wait_time)
except Exception as reconnect_error:
logger.error(f"{self} reconnection failed: {reconnect_error}")
continue
@abstractmethod
async def _connect(self):
"""Implement service-specific connection logic. This function will

48
src/pipecat/tests/utils.py
View File

@@ -6,7 +6,7 @@
import asyncio
from dataclasses import dataclass
from typing import Any, Awaitable, Callable, Dict, Sequence, Tuple
from typing import Any, Awaitable, Callable, Dict, Optional, Sequence, Tuple
from pipecat.frames.frames import (
EndFrame,
@@ -80,8 +80,8 @@ async def run_test(
processor: FrameProcessor,
*,
frames_to_send: Sequence[Frame],
expected_down_frames: Sequence[type],
expected_up_frames: Sequence[type] = [],
expected_down_frames: Optional[Sequence[type]] = None,
expected_up_frames: Optional[Sequence[type]] = None,
ignore_start: bool = True,
start_metadata: Dict[str, Any] = {},
send_end_frame: bool = True,
@@ -101,7 +101,11 @@ async def run_test(
pipeline = Pipeline([source, processor, sink])
task = PipelineTask(pipeline, params=PipelineParams(start_metadata=start_metadata))
task = PipelineTask(
pipeline,
params=PipelineParams(start_metadata=start_metadata),
cancel_on_idle_timeout=False,
)
async def push_frames():
# Just give a little head start to the runner.
@@ -122,33 +126,35 @@ async def run_test(
# Down frames
#
received_down_frames: Sequence[Frame] = []
while not received_down.empty():
frame = await received_down.get()
if not isinstance(frame, EndFrame) or not send_end_frame:
received_down_frames.append(frame)
if expected_down_frames is not None:
while not received_down.empty():
frame = await received_down.get()
if not isinstance(frame, EndFrame) or not send_end_frame:
received_down_frames.append(frame)
print("received DOWN frames =", received_down_frames)
print("expected DOWN frames =", expected_down_frames)
print("received DOWN frames =", received_down_frames)
print("expected DOWN frames =", expected_down_frames)
assert len(received_down_frames) == len(expected_down_frames)
assert len(received_down_frames) == len(expected_down_frames)
for real, expected in zip(received_down_frames, expected_down_frames):
assert isinstance(real, expected)
for real, expected in zip(received_down_frames, expected_down_frames):
assert isinstance(real, expected)
#
# Up frames
#
received_up_frames: Sequence[Frame] = []
while not received_up.empty():
frame = await received_up.get()
received_up_frames.append(frame)
if expected_up_frames is not None:
while not received_up.empty():
frame = await received_up.get()
received_up_frames.append(frame)
print("received UP frames =", received_up_frames)
print("expected UP frames =", expected_up_frames)
print("received UP frames =", received_up_frames)
print("expected UP frames =", expected_up_frames)
assert len(received_up_frames) == len(expected_up_frames)
assert len(received_up_frames) == len(expected_up_frames)
for real, expected in zip(received_up_frames, expected_up_frames):
assert isinstance(real, expected)
for real, expected in zip(received_up_frames, expected_up_frames):
assert isinstance(real, expected)
return (received_down_frames, received_up_frames)

61
src/pipecat/transcriptions/language.py
View File

@@ -54,6 +54,9 @@ class Language(StrEnum):
AZ = "az"
AZ_AZ = "az-AZ"
# Bashkir
BA = "ba"
# Belarusian
BE = "be"
@@ -66,6 +69,12 @@ class Language(StrEnum):
BN_BD = "bn-BD"
BN_IN = "bn-IN"
# Tibetan
BO = "bo"
# Breton
BR = "br"
# Bosnian
BS = "bs"
BS_BA = "bs-BA"
@@ -159,6 +168,9 @@ class Language(StrEnum):
FIL = "fil"
FIL_PH = "fil-PH"
# Faroese
FO = "fo"
# French
FR = "fr"
FR_BE = "fr-BE"
@@ -178,6 +190,9 @@ class Language(StrEnum):
GU = "gu"
GU_IN = "gu-IN"
# Hausa
HA = "ha"
# Hebrew
HE = "he"
HE_IL = "he-IL"
@@ -190,6 +205,9 @@ class Language(StrEnum):
HR = "hr"
HR_HR = "hr-HR"
# Haitian Creole
HT = "ht"
# Hungarian
HU = "hu"
HU_HU = "hu-HU"
@@ -224,6 +242,7 @@ class Language(StrEnum):
# Javanese
JV = "jv"
JV_ID = "jv-ID"
JW = "jw" # Fal requires for Javanese
# Georgian
KA = "ka"
@@ -245,6 +264,15 @@ class Language(StrEnum):
KO = "ko"
KO_KR = "ko-KR"
# Latin
LA = "la"
# Luxembourgish
LB = "lb"
# Lingala
LN = "ln"
# Lao
LO = "lo"
LO_LA = "lo-LA"
@@ -257,6 +285,9 @@ class Language(StrEnum):
LV = "lv"
LV_LV = "lv-LV"
# Malagasy
MG = "mg"
# Macedonian
MK = "mk"
MK_MK = "mk-MK"
@@ -289,9 +320,10 @@ class Language(StrEnum):
MY_MM = "my-MM"
# Norwegian
NB = "nb"
NB = "nb" # Norwegian Bokmål
NB_NO = "nb-NO"
NO = "no"
NN = "nn" # Norwegian Nynorsk
# Nepali
NE = "ne"
@@ -302,6 +334,9 @@ class Language(StrEnum):
NL_BE = "nl-BE"
NL_NL = "nl-NL"
# Occitan
OC = "oc"
# Odia
OR = "or"
OR_IN = "or-IN"
@@ -331,6 +366,12 @@ class Language(StrEnum):
RU = "ru"
RU_RU = "ru-RU"
# Sanskrit
SA = "sa"
# Sindhi
SD = "sd"
# Sinhala
SI = "si"
SI_LK = "si-LK"
@@ -343,6 +384,9 @@ class Language(StrEnum):
SL = "sl"
SL_SI = "sl-SI"
# Shona
SN = "sn"
# Somali
SO = "so"
SO_SO = "so-SO"
@@ -384,14 +428,23 @@ class Language(StrEnum):
TE = "te"
TE_IN = "te-IN"
# Tajik
TG = "tg"
# Thai
TH = "th"
TH_TH = "th-TH"
# Turkmen
TK = "tk"
# Turkish
TR = "tr"
TR_TR = "tr-TR"
# Tatar
TT = "tt"
# Ukrainian
UK = "uk"
UK_UA = "uk-UA"
@@ -413,6 +466,12 @@ class Language(StrEnum):
WUU = "wuu"
WUU_CN = "wuu-CN"
# Yiddish
YI = "yi"
# Yoruba
YO = "yo"
# Yue Chinese
YUE = "yue"
YUE_CN = "yue-CN"

4
src/pipecat/transports/base_input.py
View File

@@ -152,6 +152,7 @@ class BaseInputTransport(FrameProcessor):
async def _handle_user_interruption(self, frame: Frame):
if isinstance(frame, UserStartedSpeakingFrame):
logger.debug("User started speaking")
await self.push_frame(frame)
# Make sure we notify about interruptions quickly out-of-band.
if self.interruptions_allowed:
await self._start_interruption()
@@ -161,12 +162,11 @@ class BaseInputTransport(FrameProcessor):
await self.push_frame(StartInterruptionFrame())
elif isinstance(frame, UserStoppedSpeakingFrame):
logger.debug("User stopped speaking")
await self.push_frame(frame)
if self.interruptions_allowed:
await self._stop_interruption()
await self.push_frame(StopInterruptionFrame())
await self.push_frame(frame)
#
# Audio input
#

18
src/pipecat/transports/network/fastapi_websocket.py
View File

@@ -102,11 +102,13 @@ class FastAPIWebsocketClient:
class FastAPIWebsocketInputTransport(BaseInputTransport):
def __init__(
self,
transport: BaseTransport,
client: FastAPIWebsocketClient,
params: FastAPIWebsocketParams,
**kwargs,
):
super().__init__(params, **kwargs)
self._transport = transport
self._client = client
self._params = params
self._receive_task = None
@@ -139,6 +141,10 @@ class FastAPIWebsocketInputTransport(BaseInputTransport):
await self._stop_tasks()
await self._client.disconnect()
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def _receive_messages(self):
try:
async for message in self._client.receive():
@@ -165,11 +171,14 @@ class FastAPIWebsocketInputTransport(BaseInputTransport):
class FastAPIWebsocketOutputTransport(BaseOutputTransport):
def __init__(
self,
transport: BaseTransport,
client: FastAPIWebsocketClient,
params: FastAPIWebsocketParams,
**kwargs,
):
super().__init__(params, **kwargs)
self._transport = transport
self._client = client
self._params = params
@@ -194,6 +203,10 @@ class FastAPIWebsocketOutputTransport(BaseOutputTransport):
await super().cancel(frame)
await self._client.disconnect()
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
@@ -266,6 +279,7 @@ class FastAPIWebsocketTransport(BaseTransport):
output_name: Optional[str] = None,
):
super().__init__(input_name=input_name, output_name=output_name)
self._params = params
self._callbacks = FastAPIWebsocketCallbacks(
@@ -278,10 +292,10 @@ class FastAPIWebsocketTransport(BaseTransport):
self._client = FastAPIWebsocketClient(websocket, is_binary, self._callbacks)
self._input = FastAPIWebsocketInputTransport(
self._client, self._params, name=self._input_name
self, self._client, self._params, name=self._input_name
)
self._output = FastAPIWebsocketOutputTransport(
self._client, self._params, name=self._output_name
self, self._client, self._params, name=self._output_name
)
# Register supported handlers. The user will only be able to register

28
src/pipecat/transports/network/websocket_client.py
View File

@@ -118,9 +118,15 @@ class WebsocketClientSession:
class WebsocketClientInputTransport(BaseInputTransport):
def __init__(self, session: WebsocketClientSession, params: WebsocketClientParams):
def __init__(
self,
transport: BaseTransport,
session: WebsocketClientSession,
params: WebsocketClientParams,
):
super().__init__(params)
self._transport = transport
self._session = session
self._params = params
@@ -138,6 +144,10 @@ class WebsocketClientInputTransport(BaseInputTransport):
await super().cancel(frame)
await self._session.disconnect()
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def on_message(self, websocket, message):
frame = await self._params.serializer.deserialize(message)
if not frame:
@@ -149,9 +159,15 @@ class WebsocketClientInputTransport(BaseInputTransport):
class WebsocketClientOutputTransport(BaseOutputTransport):
def __init__(self, session: WebsocketClientSession, params: WebsocketClientParams):
def __init__(
self,
transport: BaseTransport,
session: WebsocketClientSession,
params: WebsocketClientParams,
):
super().__init__(params)
self._transport = transport
self._session = session
self._params = params
@@ -178,6 +194,10 @@ class WebsocketClientOutputTransport(BaseOutputTransport):
await super().cancel(frame)
await self._session.disconnect()
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def send_message(self, frame: TransportMessageFrame | TransportMessageUrgentFrame):
await self._write_frame(frame)
@@ -250,12 +270,12 @@ class WebsocketClientTransport(BaseTransport):
def input(self) -> WebsocketClientInputTransport:
if not self._input:
self._input = WebsocketClientInputTransport(self._session, self._params)
self._input = WebsocketClientInputTransport(self, self._session, self._params)
return self._input
def output(self) -> WebsocketClientOutputTransport:
if not self._output:
self._output = WebsocketClientOutputTransport(self._session, self._params)
self._output = WebsocketClientOutputTransport(self, self._session, self._params)
return self._output
async def _on_connected(self, websocket):

19
src/pipecat/transports/network/websocket_server.py
View File

@@ -55,6 +55,7 @@ class WebsocketServerCallbacks(BaseModel):
class WebsocketServerInputTransport(BaseInputTransport):
def __init__(
self,
transport: BaseTransport,
host: str,
port: int,
params: WebsocketServerParams,
@@ -63,6 +64,7 @@ class WebsocketServerInputTransport(BaseInputTransport):
):
super().__init__(params, **kwargs)
self._transport = transport
self._host = host
self._port = port
self._params = params
@@ -102,6 +104,10 @@ class WebsocketServerInputTransport(BaseInputTransport):
await self.cancel_task(self._server_task)
self._server_task = None
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def _server_task_handler(self):
logger.info(f"Starting websocket server on {self._host}:{self._port}")
async with websockets.serve(self._client_handler, self._host, self._port) as server:
@@ -163,9 +169,10 @@ class WebsocketServerInputTransport(BaseInputTransport):
class WebsocketServerOutputTransport(BaseOutputTransport):
def __init__(self, params: WebsocketServerParams, **kwargs):
def __init__(self, transport: BaseTransport, params: WebsocketServerParams, **kwargs):
super().__init__(params, **kwargs)
self._transport = transport
self._params = params
self._websocket: Optional[websockets.WebSocketServerProtocol] = None
@@ -189,6 +196,10 @@ class WebsocketServerOutputTransport(BaseOutputTransport):
await self._params.serializer.setup(frame)
self._send_interval = (self._audio_chunk_size / self.sample_rate) / 2
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
@@ -283,13 +294,15 @@ class WebsocketServerTransport(BaseTransport):
def input(self) -> WebsocketServerInputTransport:
if not self._input:
self._input = WebsocketServerInputTransport(
self._host, self._port, self._params, self._callbacks, name=self._input_name
self, self._host, self._port, self._params, self._callbacks, name=self._input_name
)
return self._input
def output(self) -> WebsocketServerOutputTransport:
if not self._output:
self._output = WebsocketServerOutputTransport(self._params, name=self._output_name)
self._output = WebsocketServerOutputTransport(
self, self._params, name=self._output_name
)
return self._output
async def _on_client_connected(self, websocket):

60
src/pipecat/transports/services/daily.py
View File

@@ -6,7 +6,6 @@
import asyncio
import time
import warnings
from concurrent.futures import ThreadPoolExecutor
from dataclasses import dataclass
from typing import Any, Awaitable, Callable, Mapping, Optional
@@ -18,7 +17,7 @@ from daily import (
VirtualSpeakerDevice,
)
from loguru import logger
from pydantic import BaseModel, model_validator
from pydantic import BaseModel
from pipecat.audio.vad.vad_analyzer import VADAnalyzer, VADParams
from pipecat.frames.frames import (
@@ -124,7 +123,6 @@ class DailyTranscriptionSettings(BaseModel):
Attributes:
language: ISO language code for transcription (e.g. "en").
tier: Deprecated. Use model instead.
model: Transcription model to use (e.g. "nova-2-general").
profanity_filter: Whether to filter profanity from transcripts.
redact: Whether to redact sensitive information.
@@ -135,7 +133,6 @@ class DailyTranscriptionSettings(BaseModel):
"""
language: str = "en"
tier: Optional[str] = None
model: str = "nova-2-general"
profanity_filter: bool = True
redact: bool = False
@@ -144,16 +141,6 @@ class DailyTranscriptionSettings(BaseModel):
includeRawResponse: bool = True
extra: Mapping[str, Any] = {"interim_results": True}
@model_validator(mode="before")
def check_deprecated_fields(cls, values):
with warnings.catch_warnings():
warnings.simplefilter("always")
if "tier" in values:
warnings.warn(
"Field 'tier' is deprecated, use 'model' instead.", DeprecationWarning
)
return values
class DailyParams(TransportParams):
"""Configuration parameters for Daily transport.
@@ -824,9 +811,16 @@ class DailyInputTransport(BaseInputTransport):
params: Configuration parameters.
"""
def __init__(self, client: DailyTransportClient, params: DailyParams, **kwargs):
def __init__(
self,
transport: BaseTransport,
client: DailyTransportClient,
params: DailyParams,
**kwargs,
):
super().__init__(params, **kwargs)
self._transport = transport
self._client = client
self._params = params
@@ -894,6 +888,7 @@ class DailyInputTransport(BaseInputTransport):
async def cleanup(self):
await super().cleanup()
await self._client.cleanup()
await self._transport.cleanup()
#
# FrameProcessor
@@ -903,7 +898,7 @@ class DailyInputTransport(BaseInputTransport):
await super().process_frame(frame, direction)
if isinstance(frame, UserImageRequestFrame):
await self.request_participant_image(frame.user_id)
await self.request_participant_image(frame)
#
# Frames
@@ -940,16 +935,16 @@ class DailyInputTransport(BaseInputTransport):
self._video_renderers[participant_id] = {
"framerate": framerate,
"timestamp": 0,
"render_next_frame": False,
"render_next_frame": [],
}
await self._client.capture_participant_video(
participant_id, self._on_participant_video_frame, framerate, video_source, color_format
)
async def request_participant_image(self, participant_id: str):
if participant_id in self._video_renderers:
self._video_renderers[participant_id]["render_next_frame"] = True
async def request_participant_image(self, frame: UserImageRequestFrame):
if frame.user_id in self._video_renderers:
self._video_renderers[frame.user_id]["render_next_frame"].append(frame)
async def _on_participant_video_frame(self, participant_id: str, buffer, size, format):
render_frame = False
@@ -958,17 +953,24 @@ class DailyInputTransport(BaseInputTransport):
prev_time = self._video_renderers[participant_id]["timestamp"]
framerate = self._video_renderers[participant_id]["framerate"]
# Some times we render frames because of a request.
request_frame = None
if framerate > 0:
next_time = prev_time + 1 / framerate
render_frame = (next_time - curr_time) < 0.1
elif self._video_renderers[participant_id]["render_next_frame"]:
self._video_renderers[participant_id]["render_next_frame"] = False
request_frame = self._video_renderers[participant_id]["render_next_frame"].pop(0)
render_frame = True
if render_frame:
frame = UserImageRawFrame(
user_id=participant_id, image=buffer, size=size, format=format
user_id=participant_id,
request=request_frame,
image=buffer,
size=size,
format=format,
)
await self.push_frame(frame)
self._video_renderers[participant_id]["timestamp"] = curr_time
@@ -984,9 +986,12 @@ class DailyOutputTransport(BaseOutputTransport):
params: Configuration parameters.
"""
def __init__(self, client: DailyTransportClient, params: DailyParams, **kwargs):
def __init__(
self, transport: BaseTransport, client: DailyTransportClient, params: DailyParams, **kwargs
):
super().__init__(params, **kwargs)
self._transport = transport
self._client = client
# Whether we have seen a StartFrame already.
@@ -1021,6 +1026,7 @@ class DailyOutputTransport(BaseOutputTransport):
async def cleanup(self):
await super().cleanup()
await self._client.cleanup()
await self._transport.cleanup()
async def send_message(self, frame: TransportMessageFrame | TransportMessageUrgentFrame):
await self._client.send_message(frame)
@@ -1122,12 +1128,16 @@ class DailyTransport(BaseTransport):
def input(self) -> DailyInputTransport:
if not self._input:
self._input = DailyInputTransport(self._client, self._params, name=self._input_name)
self._input = DailyInputTransport(
self, self._client, self._params, name=self._input_name
)
return self._input
def output(self) -> DailyOutputTransport:
if not self._output:
self._output = DailyOutputTransport(self._client, self._params, name=self._output_name)
self._output = DailyOutputTransport(
self, self._client, self._params, name=self._output_name
)
return self._output
#

40
src/pipecat/transports/services/livekit.py
View File

@@ -345,9 +345,17 @@ class LiveKitTransportClient:
class LiveKitInputTransport(BaseInputTransport):
def __init__(self, client: LiveKitTransportClient, params: LiveKitParams, **kwargs):
def __init__(
self,
transport: BaseTransport,
client: LiveKitTransportClient,
params: LiveKitParams,
**kwargs,
):
super().__init__(params, **kwargs)
self._transport = transport
self._client = client
self._audio_in_task = None
self._vad_analyzer: Optional[VADAnalyzer] = params.vad_analyzer
self._resampler = create_default_resampler()
@@ -377,6 +385,10 @@ class LiveKitInputTransport(BaseInputTransport):
if self._audio_in_task and (self._params.audio_in_enabled or self._params.vad_enabled):
await self.cancel_task(self._audio_in_task)
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def push_app_message(self, message: Any, sender: str):
frame = LiveKitTransportMessageUrgentFrame(message=message, participant_id=sender)
await self.push_frame(frame)
@@ -414,8 +426,15 @@ class LiveKitInputTransport(BaseInputTransport):
class LiveKitOutputTransport(BaseOutputTransport):
def __init__(self, client: LiveKitTransportClient, params: LiveKitParams, **kwargs):
def __init__(
self,
transport: BaseTransport,
client: LiveKitTransportClient,
params: LiveKitParams,
**kwargs,
):
super().__init__(params, **kwargs)
self._transport = transport
self._client = client
async def start(self, frame: StartFrame):
@@ -433,6 +452,10 @@ class LiveKitOutputTransport(BaseOutputTransport):
await super().cancel(frame)
await self._client.disconnect()
async def cleanup(self):
await super().cleanup()
await self._transport.cleanup()
async def send_message(self, frame: TransportMessageFrame | TransportMessageUrgentFrame):
if isinstance(frame, (LiveKitTransportMessageFrame, LiveKitTransportMessageUrgentFrame)):
await self._client.send_data(frame.message.encode(), frame.participant_id)
@@ -499,13 +522,15 @@ class LiveKitTransport(BaseTransport):
def input(self) -> LiveKitInputTransport:
if not self._input:
self._input = LiveKitInputTransport(self._client, self._params, name=self._input_name)
self._input = LiveKitInputTransport(
self, self._client, self._params, name=self._input_name
)
return self._input
def output(self) -> LiveKitOutputTransport:
if not self._output:
self._output = LiveKitOutputTransport(
self._client, self._params, name=self._output_name
self, self._client, self._params, name=self._output_name
)
return self._output
@@ -574,13 +599,6 @@ class LiveKitTransport(BaseTransport):
)
await self._output.send_message(frame)
async def cleanup(self):
if self._input:
await self._input.cleanup()
if self._output:
await self._output.cleanup()
await self._client.disconnect()
async def on_room_event(self, event):
# Handle room events
pass

29
src/pipecat/utils/base_object.py
View File

@@ -4,6 +4,7 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import inspect
from abc import ABC
from typing import Optional
@@ -17,8 +18,15 @@ class BaseObject(ABC):
def __init__(self, *, name: Optional[str] = None):
self._id: int = obj_id()
self._name = name or f"{self.__class__.__name__}#{obj_count(self)}"
# Registered event handlers.
self._event_handlers: dict = {}
# Set of tasks being executed. When a task finishes running it gets
# automatically removed from the set. When we cleanup we wait for all
# event tasks still being executed.
self._event_tasks = set()
@property
def id(self) -> int:
return self._id
@@ -27,6 +35,12 @@ class BaseObject(ABC):
def name(self) -> str:
return self._name
async def cleanup(self):
if self._event_tasks:
event_names, tasks = zip(*self._event_tasks)
logger.debug(f"{self} wating on event handlers to finish {list(event_names)}...")
await asyncio.wait(tasks)
def event_handler(self, event_name: str):
def decorator(handler):
self.add_event_handler(event_name, handler)
@@ -45,6 +59,16 @@ class BaseObject(ABC):
self._event_handlers[event_name] = []
async def _call_event_handler(self, event_name: str, *args, **kwargs):
# Create the task.
task = asyncio.create_task(self._run_task(event_name, *args, **kwargs))
# Add it to our list of event tasks.
self._event_tasks.add((event_name, task))
# Remove the task from the event tasks list when the task completes.
task.add_done_callback(self._event_task_finished)
async def _run_task(self, event_name: str, *args, **kwargs):
try:
for handler in self._event_handlers[event_name]:
if inspect.iscoroutinefunction(handler):
@@ -54,5 +78,10 @@ class BaseObject(ABC):
except Exception as e:
logger.exception(f"Exception in event handler {event_name}: {e}")
def _event_task_finished(self, task: asyncio.Task):
tuple_to_remove = next((t for t in self._event_tasks if t[1] == task), None)
if tuple_to_remove:
self._event_tasks.discard(tuple_to_remove)
def __str__(self):
return self.name

109
src/pipecat/utils/string.py
View File

@@ -5,10 +5,12 @@
#
import re
from typing import Optional, Sequence, Tuple
ENDOFSENTENCE_PATTERN_STR = r"""
(?<![A-Z]) # Negative lookbehind: not preceded by an uppercase letter (e.g., "U.S.A.")
(?<!\d) # Negative lookbehind: not preceded by a digit (e.g., "1. Let's start")
(?<!\d\.\d) # Not preceded by a decimal number (e.g., "3.14159")
(?<!^\d\.) # Not preceded by a numbered list item (e.g., "1. Let's start")
(?<!\d\s[ap]) # Negative lookbehind: not preceded by time (e.g., "3:00 a.m.")
(?<!Mr|Ms|Dr) # Negative lookbehind: not preceded by Mr, Ms, Dr (combined bc. length is the same)
(?<!Mrs) # Negative lookbehind: not preceded by "Mrs"
@@ -17,9 +19,112 @@ ENDOFSENTENCE_PATTERN_STR = r"""
(\。\s*\。\s*\。|[。？！；।]) # the full-width version (mainly used in East Asian languages such as Chinese, Hindi)
$ # End of string
"""
ENDOFSENTENCE_PATTERN = re.compile(ENDOFSENTENCE_PATTERN_STR, re.VERBOSE)
EMAIL_PATTERN = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")
NUMBER_PATTERN = re.compile(r"[+-]?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?")
StartEndTags = Tuple[str, str]
def replace_match(text: str, match: re.Match, old: str, new: str) -> str:
"""Replace occurrences of a substring within a matched section of a given
text.
Args:
text (str): The input text in which replacements will be made.
match (re.Match): A regex match object representing the section of text to modify.
old (str): The substring to be replaced.
new (str): The substring to replace `old` with.
Returns:
str: The modified text with the specified replacements made within the matched section.
"""
start = match.start()
end = match.end()
replacement = text[start:end].replace(old, new)
text = text[:start] + replacement + text[end:]
return text
def match_endofsentence(text: str) -> int:
match = ENDOFSENTENCE_PATTERN.search(text.rstrip())
"""Finds the position of the end of a sentence in the provided text string.
This function processes the input text by replacing periods in email
addresses and numbers with ampersands to prevent them from being
misidentified as sentence terminals. It then searches for the end of a
sentence using a specified regex pattern.
Args:
text (str): The input text in which to find the end of the sentence.
Returns:
int: The position of the end of the sentence if found, otherwise 0.
"""
text = text.rstrip()
# Replace email dots by ampersands so we can find the end of sentence. For
# example, first.last@email.com becomes first&last@email&com.
emails = list(EMAIL_PATTERN.finditer(text))
for email_match in emails:
text = replace_match(text, email_match, ".", "&")
# Replace number dots by ampersands so we can find the end of sentence.
numbers = list(NUMBER_PATTERN.finditer(text))
for number_match in numbers:
text = replace_match(text, number_match, ".", "&")
# Match against the new text.
match = ENDOFSENTENCE_PATTERN.search(text)
return match.end() if match else 0
def parse_start_end_tags(
text: str,
tags: Sequence[StartEndTags],
current_tag: Optional[StartEndTags],
current_tag_index: int,
) -> Tuple[Optional[StartEndTags], int]:
"""Parses the given text to identify a pair of start/end tags.
If a start tag was previously found (i.e. current_tags is valid), wait for
the corresponding end tag. Otherwise, wait for a start tag.
This function will return the index in the text that we should start parsing
in the next call and the current or new tags.
Parameters:
- text (str): The text to be parsed.
- tags (Sequence[StartEndTags]): List of tuples containing start and end tags.
- current_tags (Optional[StartEndTags]): The currently active tags, if any.
- current_tags_index (int): The current index in the text.
Returns:
Tuple[Optional[StartEndTags], int]: A tuple containing None or the current
tag and the index of the text.
"""
# If we are already inside a tag, check if the end tag is in the text.
if current_tag:
_, end_tag = current_tag
if end_tag in text[current_tag_index:]:
return (None, len(text))
return (current_tag, current_tag_index)
# Check if any start tag appears in the text
for start_tag, end_tag in tags:
start_tag_count = text[current_tag_index:].count(start_tag)
end_tag_count = text[current_tag_index:].count(end_tag)
if start_tag_count == 0 and end_tag_count == 0:
return (None, current_tag_index)
elif start_tag_count > end_tag_count:
return ((start_tag, end_tag), len(text))
elif start_tag_count == end_tag_count:
return (None, len(text))
return (None, current_tag_index)

48
src/pipecat/utils/test_frame_processor.py
View File

@@ -1,48 +0,0 @@
from typing import List
from pipecat.processors.frame_processor import FrameProcessor
class TestException(Exception):
pass
class TestFrameProcessor(FrameProcessor):
__test__ = False # Prevents pytest from collecting this class as a test
def __init__(self, test_frames):
self.test_frames = test_frames
self._list_counter = 0
super().__init__()
async def process_frame(self, frame, direction):
await super().process_frame(frame, direction)
if not self.test_frames[
0
]: # then we've run out of required frames but the generator is still going?
raise TestException(f"Oops, got an extra frame, {frame}")
if isinstance(self.test_frames[0], List):
# We need to consume frames until we see the next frame type after this
next_frame = self.test_frames[1]
if isinstance(frame, next_frame):
# we're done iterating the list I guess
print(f"TestFrameProcessor got expected list exit frame: {frame}")
# pop twice to get rid of the list, as well as the next frame
self.test_frames.pop(0)
self.test_frames.pop(0)
self.list_counter = 0
else:
fl = self.test_frames[0]
fl_el = fl[self._list_counter % len(fl)]
if isinstance(frame, fl_el):
print(f"TestFrameProcessor got expected list frame: {frame}")
self._list_counter += 1
else:
raise TestException(f"Inside a list, expected {fl_el} but got {frame}")
else:
if not isinstance(frame, self.test_frames[0]):
raise TestException(f"Expected {self.test_frames[0]}, but got {frame}")
print(f"TestFrameProcessor got expected frame: {frame}")
self.test_frames.pop(0)

57
src/pipecat/utils/text/base_text_aggregator.py Normal file
View File

@@ -0,0 +1,57 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
from abc import ABC, abstractmethod
from typing import Optional
class BaseTextAggregator(ABC):
"""This is the base class for text aggregators. Text aggregators are usually
used by the TTS service to aggregate LLM tokens and decide when the
aggregated text should be pushed to the TTS service.
Text aggregators can also be used to manipulate text while it's being
aggregated (e.g. reasoning blocks can be removed).
"""
@property
@abstractmethod
def text(self) -> str:
"""Returns the currently aggregated text."""
pass
@abstractmethod
def aggregate(self, text: str) -> Optional[str]:
"""Aggregates the specified text with the currently accumulated text.
This method should be implemented to define how the new text contributes
to the aggregation process. It returns the updated aggregated text if
it's ready to be processed, or None otherwise.
Args:
text (str): The text to be aggregated.
Returns:
Optional[str]: The updated aggregated text or None if aggregated
text is not ready.
"""
pass
@abstractmethod
def handle_interruption(self):
"""Handles interruptions. When an interruption occurs it is possible
that we might want to discard the aggregated text or do some internal
modifications to the aggregated text.
"""
pass
@abstractmethod
def reset(self):
"""Clears the internally aggregated text."""
pass

262
src/pipecat/utils/text/pattern_pair_aggregator.py Normal file
View File

@@ -0,0 +1,262 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import re
from typing import Callable, Optional, Tuple
from loguru import logger
from pipecat.utils.string import match_endofsentence
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
class PatternMatch:
"""Represents a matched pattern pair with its content.
A PatternMatch object is created when a complete pattern pair is found
in the text. It contains information about which pattern was matched,
the full matched text (including start and end patterns), and the
content between the patterns.
Attributes:
pattern_id: The identifier of the matched pattern pair.
full_match: The complete text including start and end patterns.
content: The text content between the start and end patterns.
"""
def __init__(self, pattern_id: str, full_match: str, content: str):
"""Initialize a pattern match.
Args:
pattern_id: ID of the pattern pair.
full_match: Complete matched text including start and end patterns.
content: Content between the start and end patterns.
"""
self.pattern_id = pattern_id
self.full_match = full_match
self.content = content
def __str__(self) -> str:
"""Return a string representation of the pattern match.
Returns:
A string describing the pattern match.
"""
return f"PatternMatch(id={self.pattern_id}, content={self.content})"
class PatternPairAggregator(BaseTextAggregator):
"""Aggregator that identifies and processes content between pattern pairs.
This aggregator buffers text until it can identify complete pattern pairs
(defined by start and end patterns), processes the content between these
patterns using registered handlers, and returns text at sentence boundaries.
It's particularly useful for processing structured content in streaming text,
such as XML tags, markdown formatting, or custom delimiters.
The aggregator ensures that patterns spanning multiple text chunks are
correctly identified and handles cases where patterns contain sentence
boundaries.
"""
def __init__(self):
"""Initialize the pattern pair aggregator.
Creates an empty aggregator with no patterns or handlers registered.
"""
self._text = ""
self._patterns = {}
self._handlers = {}
@property
def text(self) -> str:
"""Get the currently buffered text.
Returns:
The current text buffer content.
"""
return self._text
def add_pattern_pair(
self, pattern_id: str, start_pattern: str, end_pattern: str, remove_match: bool = True
) -> "PatternPairAggregator":
"""Add a pattern pair to detect in the text.
Registers a new pattern pair with a unique identifier. The aggregator
will look for text that starts with the start pattern and ends with
the end pattern, and treat the content between them as a match.
Args:
pattern_id: Unique identifier for this pattern pair.
start_pattern: Pattern that marks the beginning of content.
end_pattern: Pattern that marks the end of content.
remove_match: Whether to remove the matched content from the text.
Returns:
Self for method chaining.
"""
self._patterns[pattern_id] = {
"start": start_pattern,
"end": end_pattern,
"remove_match": remove_match,
}
return self
def on_pattern_match(
self, pattern_id: str, handler: Callable[[PatternMatch], None]
) -> "PatternPairAggregator":
"""Register a handler for when a pattern pair is matched.
The handler will be called whenever a complete match for the
specified pattern ID is found in the text.
Args:
pattern_id: ID of the pattern pair to match.
handler: Function to call when pattern is matched.
The function should accept a PatternMatch object.
Returns:
Self for method chaining.
"""
self._handlers[pattern_id] = handler
return self
def _process_complete_patterns(self, text: str) -> Tuple[str, bool]:
"""Process all complete pattern pairs in the text.
Searches for all complete pattern pairs in the text, calls the
appropriate handlers, and optionally removes the matches.
Args:
text: The text to process.
Returns:
Tuple of (processed_text, was_modified) where:
- processed_text is the text after processing patterns
- was_modified indicates whether any changes were made
"""
processed_text = text
modified = False
for pattern_id, pattern_info in self._patterns.items():
# Escape special regex characters in the patterns
start = re.escape(pattern_info["start"])
end = re.escape(pattern_info["end"])
remove_match = pattern_info["remove_match"]
# Create regex to match from start pattern to end pattern
# The .*? is non-greedy to handle nested patterns
regex = f"{start}(.*?){end}"
# Find all matches
match_iter = re.finditer(regex, processed_text, re.DOTALL)
matches = list(match_iter) # Convert to list for safe iteration
for match in matches:
content = match.group(1) # Content between patterns
full_match = match.group(0) # Full match including patterns
# Create pattern match object
pattern_match = PatternMatch(
pattern_id=pattern_id, full_match=full_match, content=content
)
# Call the appropriate handler if registered
if pattern_id in self._handlers:
try:
self._handlers[pattern_id](pattern_match)
except Exception as e:
logger.error(f"Error in pattern handler for {pattern_id}: {e}")
# Remove the pattern from the text if configured
if remove_match:
processed_text = processed_text.replace(full_match, "", 1)
modified = True
return processed_text, modified
def _has_incomplete_patterns(self, text: str) -> bool:
"""Check if text contains incomplete pattern pairs.
Determines whether the text contains any start patterns without
matching end patterns, which would indicate incomplete content.
Args:
text: The text to check.
Returns:
True if there are incomplete patterns, False otherwise.
"""
for pattern_id, pattern_info in self._patterns.items():
start = pattern_info["start"]
end = pattern_info["end"]
# Count occurrences
start_count = text.count(start)
end_count = text.count(end)
# If there are more starts than ends, we have incomplete patterns
if start_count > end_count:
return True
return False
def aggregate(self, text: str) -> Optional[str]:
"""Aggregate text and process pattern pairs.
This method adds the new text to the buffer, processes any complete pattern
pairs, and returns processed text up to sentence boundaries if possible.
If there are incomplete patterns (start without matching end), it will
continue buffering text.
Args:
text: New text to add to the buffer.
Returns:
Processed text up to a sentence boundary, or None if more
text is needed to form a complete sentence or pattern.
"""
# Add new text to buffer
self._text += text
# Process any complete patterns in the buffer
processed_text, modified = self._process_complete_patterns(self._text)
# Only update the buffer if modifications were made
if modified:
self._text = processed_text
# Check if we have incomplete patterns
if self._has_incomplete_patterns(self._text):
# Still waiting for complete patterns
return None
# Find sentence boundary if no incomplete patterns
eos_marker = match_endofsentence(self._text)
if eos_marker:
# Extract text up to the sentence boundary
result = self._text[:eos_marker]
self._text = self._text[eos_marker:]
return result
# No complete sentence found yet
return None
def handle_interruption(self):
"""Handle interruptions by clearing the buffer.
Called when an interruption occurs in the processing pipeline,
to reset the state and discard any partially aggregated text.
"""
self._text = ""
def reset(self):
"""Clear the internally aggregated text.
Resets the aggregator to its initial state, discarding any
buffered text.
"""
self._text = ""

42
src/pipecat/utils/text/simple_text_aggregator.py Normal file
View File

@@ -0,0 +1,42 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
from typing import Optional
from pipecat.utils.string import match_endofsentence
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
class SimpleTextAggregator(BaseTextAggregator):
"""This is a simple text aggregator. It aggregates text until an end of
sentence is found.
"""
def __init__(self):
self._text = ""
@property
def text(self) -> str:
return self._text
def aggregate(self, text: str) -> Optional[str]:
result: Optional[str] = None
self._text += text
eos_end_marker = match_endofsentence(self._text)
if eos_end_marker:
result = self._text[:eos_end_marker]
self._text = self._text[eos_end_marker:]
return result
def handle_interruption(self):
self._text = ""
def reset(self):
self._text = ""

94
src/pipecat/utils/text/skip_tags_aggregator.py Normal file
View File

@@ -0,0 +1,94 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
from typing import Optional, Sequence
from pipecat.utils.string import StartEndTags, match_endofsentence, parse_start_end_tags
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
class SkipTagsAggregator(BaseTextAggregator):
"""Aggregator that prevents end of sentence matching between start/end tags.
This aggregator buffers text until it finds an end of sentence or a start
tag. If a start tag is found the aggregator will keep aggregating text
unconditionally until the corresponding end tag is found. It's particularly
useful for processing content with custom delimiters that should prevent
text from being considered for end of sentence matching..
The aggregator ensures that tags spanning multiple text chunks are correctly
identified.
"""
def __init__(self, tags: Sequence[StartEndTags]):
"""Initialize the pattern pair aggregator.
Creates an empty aggregator with no patterns or handlers registered.
"""
self._text = ""
self._tags = tags
self._current_tag: Optional[StartEndTags] = None
self._current_tag_index: int = 0
@property
def text(self) -> str:
"""Get the currently buffered text.
Returns:
The current text buffer content.
"""
return self._text
def aggregate(self, text: str) -> Optional[str]:
"""Aggregate text and process pattern pairs.
This method adds the new text to the buffer, processes any complete pattern
pairs, and returns processed text up to sentence boundaries if possible.
If there are incomplete patterns (start without matching end), it will
continue buffering text.
Args:
text: New text to add to the buffer.
Returns:
Processed text up to a sentence boundary, or None if more
text is needed to form a complete sentence or pattern.
"""
# Add new text to buffer
self._text += text
(self._current_tag, self._current_tag_index) = parse_start_end_tags(
self._text, self._tags, self._current_tag, self._current_tag_index
)
# Find sentence boundary if no incomplete patterns
if not self._current_tag:
eos_marker = match_endofsentence(self._text)
if eos_marker:
# Extract text up to the sentence boundary
result = self._text[:eos_marker]
self._text = self._text[eos_marker:]
return result
# No complete sentence found yet
return None
def handle_interruption(self):
"""Handle interruptions by clearing the buffer.
Called when an interruption occurs in the processing pipeline,
to reset the state and discard any partially aggregated text.
"""
self._text = ""
def reset(self):
"""Clear the internally aggregated text.
Resets the aggregator to its initial state, discarding any
buffered text.
"""
self._text = ""

0
src/pipecat/vad/__init__.py
View File

16
src/pipecat/vad/silero.py
View File

@@ -1,16 +0,0 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Package `pipecat.vad` is deprecated, use `pipecat.audio.vad` instead", DeprecationWarning
)
from ..audio.vad.silero import SileroVADAnalyzer
from ..processors.audio.vad.silero import SileroVAD

15
src/pipecat/vad/vad_analyzer.py
View File

@@ -1,15 +0,0 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Package `pipecat.vad` is deprecated, use `pipecat.audio.vad` instead", DeprecationWarning
)
from ..audio.vad.vad_analyzer import VADAnalyzer, VADParams, VADState