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

Merge pull request #235 from pipecat-ai/aleix/openpipe-refactoring

Browse Source 
openpipe refactoring
This commit is contained in:
Aleix Conchillo Flaqué
2024-06-14 01:28:50 +08:00
committed by GitHub
parent b43e0ed130 099e65f3b6
commit 77a3b2ea5c
21 changed files with 177 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
CHANGELOG.md
View File

@@ -9,22 +9,46 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Added
- Added a new `Service`. This service will let you run OpenAI through
- Added `OpenPipeLLMService`. This service will let you run OpenAI through
OpenPipe's SDK.
- Allow specifying frame processors' name through a new `name` constructor
argument.
### Changed
- `OpenPipe` can now be used. Can call OpenAI through OpenPipe SDK to get
LLM logging stored in OpenPipe.
- `FrameSerializer.deserialize()` can now return `None` in case it is not
possible to desearialize the given data.
- `daily_rest.DailyRoomProperties` now allows extra unknown parameters.
- Added `DeepgramSTTService`. This service has an ongoing websocket
connection. To handle this, it subclasses `AIService` instead of
`STTService`. The output of this service will be pushed from the same task,
except system frames like `StartFrame`, `CancelFrame` or
`StartInterruptionFrame`.
### Fixed
- None
- Fixed an issue where `DailyRoomProperties.exp` always had the same old
timestamp unless set by the user.
- Fixed a couple of issues with `WebsocketServerTransport`. It needed to use
`push_audio_frame()` and also VAD was not working properly.
- Fixed an issue that would cause LLM aggregator to fail with small
`VADParams.stop_secs` values.
- Fixed an issue where `BaseOutputTransport` would send longer audio frames
preventing interruptions.
### Other
- Added new `openpipe` example. This example shows how to use OpenPipe to run
OpenAI LLMs and get the logs stored in OpenPipe.
- Added new `07h-interruptible-openpipe.py` example. This example shows how to
use OpenPipe to run OpenAI LLMs and get the logs stored in OpenPipe.
- Added new `dialin-chatbot` example. This examples shows how to call the bot
using a phone number.
## [0.0.29] - 2024-06-12

33
examples/foundational/06b-listen-and-respond-openpipe.py → examples/foundational/07h-interruptible-openpipe.py
View File

@@ -12,12 +12,11 @@ import sys
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMAssistantResponseAggregator,
LLMUserResponseAggregator,
)
from pipecat.processors.logger import FrameLogger
from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.openpipe import OpenPipeLLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -36,9 +35,6 @@ logger.add(sys.stderr, level="DEBUG")
async def main(room_url: str, token):
timestamp = int(time.time())
async with aiohttp.ClientSession() as session:
transport = DailyTransport(
room_url,
@@ -58,16 +54,16 @@ async def main(room_url: str, token):
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
)
timestamp = int(time.time())
llm = OpenPipeLLMService(
api_key=os.getenv("OPENAI_API_KEY"),
openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
model="gpt-4o",
cli_id=f"cli-{timestamp}"
tags={
"conversation_id": f"pipecat-{timestamp}"
}
)
fl = FrameLogger("!!! after LLM", "red")
fltts = FrameLogger("@@@ out of tts", "green")
flend = FrameLogger("### out of the end", "magenta")
messages = [
{
"role": "system",
@@ -78,18 +74,15 @@ async def main(room_url: str, token):
tma_out = LLMAssistantResponseAggregator(messages)
pipeline = Pipeline([
transport.input(),
tma_in,
llm,
fl,
tts,
fltts,
transport.output(),
tma_out,
flend
transport.input(), # Transport user input
tma_in, # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
tma_out # Assistant spoken responses
])
task = PipelineTask(pipeline)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):

18
linux-py3.10-requirements.txt
View File

@@ -18,7 +18,9 @@ aiosignal==1.3.1
annotated-types==0.7.0
# via pydantic
anthropic==0.25.9
# via pipecat-ai (pyproject.toml)
# via
# openpipe
# pipecat-ai (pyproject.toml)
anyio==4.4.0
# via
# anthropic
@@ -29,7 +31,9 @@ async-timeout==4.0.3
# aiohttp
# langchain
attrs==23.2.0
# via aiohttp
# via
# aiohttp
# openpipe
av==12.1.0
# via faster-whisper
azure-cognitiveservices-speech==1.37.0
@@ -77,7 +81,7 @@ fal-client==0.4.0
# via pipecat-ai (pyproject.toml)
faster-whisper==1.0.2
# via pipecat-ai (pyproject.toml)
filelock==3.14.0
filelock==3.15.1
# via
# huggingface-hub
# pyht
@@ -150,6 +154,7 @@ httpx==0.27.0
# deepgram-sdk
# fal-client
# openai
# openpipe
httpx-sse==0.4.0
# via fal-client
huggingface-hub==0.23.3
@@ -264,8 +269,9 @@ onnxruntime==1.18.0
openai==1.26.0
# via
# langchain-openai
# openpipe
# pipecat-ai (pyproject.toml)
openpipe==4.13.0
openpipe==4.14.0
# via pipecat-ai (pyproject.toml)
orjson==3.10.4
# via langsmith
@@ -328,6 +334,8 @@ pytest==8.2.2
# via pytest-asyncio
pytest-asyncio==0.23.7
# via cartesia
python-dateutil==2.9.0.post0
# via openpipe
python-dotenv==1.0.1
# via pipecat-ai (pyproject.toml)
pyyaml==6.0.1
@@ -362,6 +370,8 @@ safetensors==0.4.3
# transformers
scipy==1.13.1
# via pyloudnorm
six==1.16.0
# via python-dateutil
sniffio==1.3.1
# via
# anthropic

18
macos-py3.10-requirements.txt
View File

@@ -18,7 +18,9 @@ aiosignal==1.3.1
annotated-types==0.7.0
# via pydantic
anthropic==0.25.9
# via pipecat-ai (pyproject.toml)
# via
# openpipe
# pipecat-ai (pyproject.toml)
anyio==4.4.0
# via
# anthropic
@@ -29,7 +31,9 @@ async-timeout==4.0.3
# aiohttp
# langchain
attrs==23.2.0
# via aiohttp
# via
# aiohttp
# openpipe
av==12.1.0
# via faster-whisper
azure-cognitiveservices-speech==1.37.0
@@ -77,7 +81,7 @@ fal-client==0.4.0
# via pipecat-ai (pyproject.toml)
faster-whisper==1.0.2
# via pipecat-ai (pyproject.toml)
filelock==3.14.0
filelock==3.15.1
# via
# huggingface-hub
# pyht
@@ -147,6 +151,7 @@ httpx==0.27.0
# deepgram-sdk
# fal-client
# openai
# openpipe
httpx-sse==0.4.0
# via fal-client
huggingface-hub==0.23.3
@@ -230,8 +235,9 @@ onnxruntime==1.18.0
openai==1.26.0
# via
# langchain-openai
# openpipe
# pipecat-ai (pyproject.toml)
openpipe==4.13.0
openpipe==4.14.0
# via pipecat-ai (pyproject.toml)
orjson==3.10.4
# via langsmith
@@ -294,6 +300,8 @@ pytest==8.2.2
# via pytest-asyncio
pytest-asyncio==0.23.7
# via cartesia
python-dateutil==2.9.0.post0
# via openpipe
python-dotenv==1.0.1
# via pipecat-ai (pyproject.toml)
pyyaml==6.0.1
@@ -328,6 +336,8 @@ safetensors==0.4.3
# transformers
scipy==1.13.1
# via pyloudnorm
six==1.16.0
# via python-dateutil
sniffio==1.3.1
# via
# anthropic

2
pyproject.toml
View File

@@ -47,11 +47,11 @@ langchain = [ "langchain~=0.2.1", "langchain-community~=0.2.1", "langchain-opena
local = [ "pyaudio~=0.2.0" ]
moondream = [ "einops~=0.8.0", "timm~=0.9.16", "transformers~=4.40.2" ]
openai = [ "openai~=1.26.0" ]
openpipe = [ "openpipe~=4.14.0" ]
playht = [ "pyht~=0.0.28" ]
silero = [ "torch~=2.3.0", "torchaudio~=2.3.0" ]
websocket = [ "websockets~=12.0" ]
whisper = [ "faster-whisper~=1.0.2" ]
openpipe = [ "openpipe~=4.13.0" ]
[tool.setuptools.packages.find]
# All the following settings are optional:

6
src/pipecat/processors/frame_processor.py
View File

@@ -22,7 +22,11 @@ class FrameDirection(Enum):
class FrameProcessor:
def __init__(self, name: str | None = None, loop: asyncio.AbstractEventLoop | None = None):
def __init__(
self,
name: str | None = None,
loop: asyncio.AbstractEventLoop | None = None,
**kwargs):
self.id: int = obj_id()
self.name = name or f"{self.__class__.__name__}#{obj_count(self)}"
self._prev: "FrameProcessor" | None = None

4
src/pipecat/processors/frameworks/langchain.py
View File

@@ -73,7 +73,7 @@ class LangchainProcessor(FrameProcessor):
await self.push_frame(TextFrame(self.__get_token_value(token)))
await self.push_frame(LLMResponseEndFrame())
except GeneratorExit:
logger.warning("Generator was closed prematurely")
logger.warning(f"{self} generator was closed prematurely")
except Exception as e:
logger.error(f"An unknown error occurred: {e}")
logger.error(f"{self} an unknown error occurred: {e}")
await self.push_frame(LLMFullResponseEndFrame())

2
src/pipecat/services/anthropic.py
View File

@@ -122,7 +122,7 @@ class AnthropicLLMService(LLMService):
await self.push_frame(LLMResponseEndFrame())
except Exception as e:
logger.error(f"Anthropic exception: {e}")
logger.error(f"{self} exception: {e}")
finally:
await self.push_frame(LLMFullResponseEndFrame())

6
src/pipecat/services/azure.py
View File

@@ -72,7 +72,7 @@ class AzureTTSService(TTSService):
cancellation_details = result.cancellation_details
logger.warning(f"Speech synthesis canceled: {cancellation_details.reason}")
if cancellation_details.reason == CancellationReason.Error:
logger.error(f"Error details: {cancellation_details.error_details}")
logger.error(f"{self} error: {cancellation_details.error_details}")
class AzureLLMService(BaseOpenAILLMService):
@@ -143,7 +143,7 @@ class AzureImageGenServiceREST(ImageGenService):
while status != "succeeded":
attempts_left -= 1
if attempts_left == 0:
logger.error("Image generation timed out")
logger.error(f"{self} error: image generation timed out")
yield ErrorFrame("Image generation timed out")
return
@@ -156,7 +156,7 @@ class AzureImageGenServiceREST(ImageGenService):
image_url = json_response["result"]["data"][0]["url"] if json_response else None
if not image_url:
logger.error("Image generation failed")
logger.error(f"{self} error: image generation failed")
yield ErrorFrame("Image generation failed")
return

4
src/pipecat/services/cartesia.py
View File

@@ -37,7 +37,7 @@ class CartesiaTTSService(TTSService):
voice_id = voices[self._voice_name]["id"]
self._voice = self._client.get_voice_embedding(voice_id=voice_id)
except Exception as e:
logger.error(f"Cartesia initialization error: {e}")
logger.error(f"{self} initialization error: {e}")
def can_generate_metrics(self) -> bool:
return True
@@ -60,4 +60,4 @@ class CartesiaTTSService(TTSService):
await self.stop_ttfb_metrics()
yield AudioRawFrame(chunk["audio"], chunk["sampling_rate"], 1)
except Exception as e:
logger.error(f"Cartesia exception: {e}")
logger.error(f"{self} exception: {e}")

4
src/pipecat/services/deepgram.py
View File

@@ -74,7 +74,7 @@ class DeepgramTTSService(TTSService):
return
logger.error(
f"Error getting audio (status: {r.status}, error: {response_text})")
f"{self} error getting audio (status: {r.status}, error: {response_text})")
yield ErrorFrame(f"Error getting audio (status: {r.status}, error: {response_text})")
return
@@ -83,7 +83,7 @@ class DeepgramTTSService(TTSService):
frame = AudioRawFrame(audio=data, sample_rate=16000, num_channels=1)
yield frame
except Exception as e:
logger.error(f"Deepgram exception: {e}")
logger.error(f"{self} exception: {e}")
class DeepgramSTTService(AIService):

2
src/pipecat/services/elevenlabs.py
View File

@@ -55,7 +55,7 @@ class ElevenLabsTTSService(TTSService):
async with self._aiohttp_session.post(url, json=payload, headers=headers, params=querystring) as r:
if r.status != 200:
text = await r.text()
logger.error(f"Error getting audio (status: {r.status}, error: {text})")
logger.error(f"{self} error getting audio (status: {r.status}, error: {text})")
yield ErrorFrame(f"Error getting audio (status: {r.status}, error: {text})")
return

2
src/pipecat/services/fal.py
View File

@@ -62,7 +62,7 @@ class FalImageGenService(ImageGenService):
image_url = response["images"][0]["url"] if response else None
if not image_url:
logger.error("Image generation failed")
logger.error(f"{self} error: image generation failed")
yield ErrorFrame("Image generation failed")
return

4
src/pipecat/services/google.py
View File

@@ -104,10 +104,10 @@ class GoogleLLMService(LLMService):
logger.debug(
f"LLM refused to generate content for safety reasons - {messages}.")
else:
logger.error(f"Error {e}")
logger.error(f"{self} error: {e}")
except Exception as e:
logger.error(f"Exception: {e}")
logger.error(f"{self} exception: {e}")
finally:
await self.push_frame(LLMFullResponseEndFrame())

2
src/pipecat/services/moondream.py
View File

@@ -71,7 +71,7 @@ class MoondreamService(VisionService):
async def run_vision(self, frame: VisionImageRawFrame) -> AsyncGenerator[Frame, None]:
if not self._model:
logger.error("Moondream model not available")
logger.error(f"{self} error: Moondream model not available")
yield ErrorFrame("Moondream model not available")
return

42
src/pipecat/services/openai.py
View File

@@ -9,7 +9,7 @@ import base64
import io
import json
from typing import AsyncGenerator, List, Literal
from typing import Any, AsyncGenerator, List, Literal
from loguru import logger
from PIL import Image
@@ -70,17 +70,29 @@ class BaseOpenAILLMService(LLMService):
def __init__(self, model: str, api_key=None, base_url=None, **kwargs):
super().__init__(**kwargs)
self._model: str = model
self._client = self.create_client(api_key=api_key, base_url=base_url)
self._client = self.create_client(api_key=api_key, base_url=base_url, **kwargs)
def create_client(self, api_key=None, base_url=None):
def create_client(self, api_key=None, base_url=None, **kwargs):
return AsyncOpenAI(api_key=api_key, base_url=base_url)
def can_generate_metrics(self) -> bool:
return True
async def get_chat_completions(
self,
context: OpenAILLMContext,
messages: List[ChatCompletionMessageParam]) -> AsyncStream[ChatCompletionChunk]:
chunks = await self._client.chat.completions.create(
model=self._model,
stream=True,
messages=messages,
tools=context.tools,
tool_choice=context.tool_choice,
)
return chunks
async def _stream_chat_completions(
self, context: OpenAILLMContext
) -> AsyncStream[ChatCompletionChunk]:
self, context: OpenAILLMContext) -> AsyncStream[ChatCompletionChunk]:
logger.debug(f"Generating chat: {context.get_messages_json()}")
messages: List[ChatCompletionMessageParam] = context.get_messages()
@@ -97,15 +109,10 @@ class BaseOpenAILLMService(LLMService):
del message["data"]
del message["mime_type"]
chunks: AsyncStream[ChatCompletionChunk] = (
await self._client.chat.completions.create(
model=self._model,
stream=True,
messages=messages,
tools=context.tools,
tool_choice=context.tool_choice,
)
)
try:
chunks = await self.get_chat_completions(context, messages)
except Exception as e:
logger.error(f"{self} exception: {e}")
return chunks
@@ -263,7 +270,7 @@ class OpenAIImageGenService(ImageGenService):
image_url = image.data[0].url
if not image_url:
logger.error(f"No image provided in response: {image}")
logger.error(f"{self} No image provided in response: {image}")
yield ErrorFrame("Image generation failed")
return
@@ -317,7 +324,8 @@ class OpenAITTSService(TTSService):
) as r:
if r.status_code != 200:
error = await r.text()
logger.error(f"Error getting audio (status: {r.status_code}, error: {error})")
logger.error(
f"{self} error getting audio (status: {r.status_code}, error: {error})")
yield ErrorFrame(f"Error getting audio (status: {r.status_code}, error: {error})")
return
async for chunk in r.iter_bytes(8192):
@@ -326,4 +334,4 @@ class OpenAITTSService(TTSService):
frame = AudioRawFrame(chunk, 24_000, 1)
yield frame
except BadRequestError as e:
logger.error(f"Error generating TTS: {e}")
logger.error(f"{self} error generating TTS: {e}")

197
src/pipecat/services/openpipe.py
View File

@@ -1,159 +1,70 @@
from pipecat.services.ai_services import LLMService
from openpipe import AsyncOpenAI as OpenPipeAI
from openpipe import AsyncStream
import os
#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
from typing import Dict, List
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.openai import BaseOpenAILLMService
from loguru import logger
import secrets
import time
import base64
from openai.types.chat import (ChatCompletionMessageParam, ChatCompletionChunk)
from typing import List
from pipecat.processors.frame_processor import FrameDirection
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext, OpenAILLMContextFrame
from pipecat.frames.frames import (
ErrorFrame,
Frame,
LLMFullResponseEndFrame,
LLMFullResponseStartFrame,
LLMMessagesFrame,
LLMResponseEndFrame,
LLMResponseStartFrame,
TextFrame,
URLImageRawFrame,
VisionImageRawFrame
)
try:
from openpipe import AsyncOpenAI as OpenPipeAI, AsyncStream
from openai.types.chat import (ChatCompletionMessageParam, ChatCompletionChunk)
except ModuleNotFoundError as e:
logger.error(f"Exception: {e}")
logger.error(
"In order to use OpenPipe, you need to `pip install pipecat-ai[openpipe]`. Also, set `OPENPIPE_API_KEY` and `OPENAI_API_KEY` environment variables.")
raise Exception(f"Missing module: {e}")
class BaseOpenPipeLLMService(LLMService):
class OpenPipeLLMService(BaseOpenAILLMService):
def __init__(
self,
model: str,
c_id=None,
api_key=None,
openpipe_api_key=None,
openpipe_base_url=None,
prompt=None):
super().__init__()
self._model = model
self._client = self.create_client(
api_key=api_key,
model: str = "gpt-4o",
api_key: str | None = None,
base_url: str | None = None,
openpipe_api_key: str | None = None,
openpipe_base_url: str = "https://app.openpipe.ai/api/v1",
tags: Dict[str, str] | None = None,
**kwargs):
super().__init__(
model,
api_key,
base_url,
openpipe_api_key=openpipe_api_key,
openpipe_base_url=openpipe_base_url)
self.c_id = c_id if c_id else secrets.token_urlsafe(16)
self.prompt = prompt
logger.debug(f"Client Created: {self._client}")
openpipe_base_url=openpipe_base_url,
**kwargs)
self._tags = tags
def create_client(self, api_key=None, openpipe_api_key=None, openpipe_base_url=None):
# Set up the OpenPipe client with the provided API keys and base URL
def create_client(self, api_key=None, base_url=None, **kwargs):
openpipe_api_key = kwargs.get("openpipe_api_key") or ""
openpipe_base_url = kwargs.get("openpipe_base_url") or ""
client = OpenPipeAI(
api_key=api_key or os.environ.get("OPENAI_API_KEY"),
api_key=api_key,
base_url=base_url,
openpipe={
"api_key": openpipe_api_key or os.environ.get("OPENPIPE_API_KEY"),
"base_url": openpipe_base_url or "https://app.openpipe.ai/api/v1"
"api_key": openpipe_api_key,
"base_url": openpipe_base_url
}
)
return client
async def _stream_chat_completions(self, context):
logger.debug(f"Generating chat: {context.get_messages_json()}")
messages: List[ChatCompletionMessageParam] = context.get_messages()
# base64 encode any images
for message in messages:
if message.get("mime_type") == "image/jpeg":
encoded_image = base64.b64encode(message["data"].getvalue()).decode("utf-8")
text = message["content"]
message["content"] = [
{"type": "text", "text": text},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{encoded_image}"}}
]
del message["data"]
del message["mime_type"]
start_time = time.time()
# Stream chat completions using the OpenPipe client
chunks = (
await self._client.chat.completions.create(
model=self._model,
stream=True,
messages=messages,
openpipe={
"tags": {"conversation_id": self.c_id,
"prompt": self.prompt},
"log_request": True
}
)
async def get_chat_completions(
self,
context: OpenAILLMContext,
messages: List[ChatCompletionMessageParam]) -> AsyncStream[ChatCompletionChunk]:
chunks = await self._client.chat.completions.create(
model=self._model,
stream=True,
messages=messages,
openpipe={
"tags": self._tags,
"log_request": True
}
)
logger.debug(f"OpenPipe LLM TTFB: {time.time() - start_time}")
return chunks
async def _process_context(self, context):
function_name = ""
arguments = ""
chunk_stream: AsyncStream[ChatCompletionChunk] = (
await self._stream_chat_completions(context)
)
await self.push_frame(LLMFullResponseStartFrame())
async for chunk in chunk_stream:
if len(chunk.choices) == 0:
continue
if chunk.choices[0].delta.tool_calls:
# We're streaming the LLM response to enable the fastest response times.
# For text, we just yield each chunk as we receive it and count on consumers
# to do whatever coalescing they need (eg. to pass full sentences to TTS)
#
# If the LLM is a function call, we'll do some coalescing here.
# If the response contains a function name, we'll yield a frame to tell consumers
# that they can start preparing to call the function with that name.
# We accumulate all the arguments for the rest of the streamed response, then when
# the response is done, we package up all the arguments and the function name and
# yield a frame containing the function name and the arguments.
tool_call = chunk.choices[0].delta.tool_calls[0]
if tool_call.function and tool_call.function.name:
function_name += tool_call.function.name
# yield LLMFunctionStartFrame(function_name=tool_call.function.name)
if tool_call.function and tool_call.function.arguments:
# Keep iterating through the response to collect all the argument fragments and
# yield a complete LLMFunctionCallFrame after run_llm_async
# completes
arguments += tool_call.function.arguments
elif chunk.choices[0].delta.content:
await self.push_frame(LLMResponseStartFrame())
await self.push_frame(TextFrame(chunk.choices[0].delta.content))
await self.push_frame(LLMResponseEndFrame())
await self.push_frame(LLMFullResponseEndFrame())
# if we got a function name and arguments, yield the frame with all the info so
# frame consumers can take action based on the function call.
# if function_name and arguments:
# yield LLMFunctionCallFrame(function_name=function_name, arguments=arguments)
async def process_frame(self, frame: Frame, direction: FrameDirection):
context = None
if isinstance(frame, OpenAILLMContextFrame):
context: OpenAILLMContext = frame.context
elif isinstance(frame, LLMMessagesFrame):
context = OpenAILLMContext.from_messages(frame.messages)
elif isinstance(frame, VisionImageRawFrame):
context = OpenAILLMContext.from_image_frame(frame)
else:
await self.push_frame(frame, direction)
if context:
await self._process_context(context)
class OpenPipeLLMService(BaseOpenPipeLLMService):
def __init__(self, model="gpt-4o", cli_id=None, **kwargs):
super().__init__(model, cli_id, **kwargs)

2
src/pipecat/services/playht.py
View File

@@ -80,4 +80,4 @@ class PlayHTTTSService(TTSService):
frame = AudioRawFrame(chunk, 16000, 1)
yield frame
except Exception as e:
logger.error(f"Error generating TTS: {e}")
logger.error(f"{self} error generating TTS: {e}")

2
src/pipecat/services/whisper.py
View File

@@ -72,8 +72,8 @@ class WhisperSTTService(STTService):
async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
"""Transcribes given audio using Whisper"""
if not self._model:
logger.error(f"{self} error: Whisper model not available")
yield ErrorFrame("Whisper model not available")
logger.error("Whisper model not available")
return
await self.start_ttfb_metrics()

2
src/pipecat/transports/base_input.py
View File

@@ -186,4 +186,4 @@ class BaseInputTransport(FrameProcessor):
except queue.Empty:
pass
except BaseException as e:
logger.error(f"Error reading audio frames: {e}")
logger.error(f"{self} error reading audio frames: {e}")

6
src/pipecat/transports/base_output.py
View File

@@ -201,7 +201,7 @@ class BaseOutputTransport(FrameProcessor):
except queue.Empty:
pass
except BaseException as e:
logger.error(f"Error processing sink queue: {e}")
logger.error(f"{self} error processing sink queue: {e}")
#
# Push frames task
@@ -270,7 +270,7 @@ class BaseOutputTransport(FrameProcessor):
except queue.Empty:
pass
except Exception as e:
logger.error(f"Error writing to camera: {e}")
logger.error(f"{self} error writing to camera: {e}")
#
# Audio out
@@ -286,5 +286,5 @@ class BaseOutputTransport(FrameProcessor):
buffer = buffer[self._audio_chunk_size:]
return buffer
except BaseException as e:
logger.error(f"Error writing audio frames: {e}")
logger.error(f"{self} error writing audio frames: {e}")
return buffer