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

ruff formatting

Browse Source
This commit is contained in:
Adrian Cowham
2024-10-11 11:35:02 -07:00
parent 083d221dd2
commit 79c8aa2c4a
8 changed files with 147 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
src/pipecat/processors/audio/audio_buffer_processor.py
View File

@@ -1,19 +1,23 @@
import wave
from io import BytesIO
from pipecat.frames.frames import (AudioRawFrame, BotInterruptionFrame,
BotStartedSpeakingFrame,
BotStoppedSpeakingFrame, Frame,
InputAudioRawFrame, OutputAudioRawFrame,
StartInterruptionFrame,
StopInterruptionFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame)
from pipecat.frames.frames import (
AudioRawFrame,
BotInterruptionFrame,
BotStartedSpeakingFrame,
BotStoppedSpeakingFrame,
Frame,
InputAudioRawFrame,
OutputAudioRawFrame,
StartInterruptionFrame,
StopInterruptionFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
class AudioBufferProcessor(FrameProcessor):
def __init__(self, **kwargs):
"""
Initialize the AudioBufferProcessor.
@@ -33,16 +37,13 @@ class AudioBufferProcessor(FrameProcessor):
self._sample_rate = None
def _buffer_has_audio(self, buffer: bytearray):
return (
buffer is not None and
len(buffer) > 0
)
return buffer is not None and len(buffer) > 0
def _has_audio(self):
return (
self._buffer_has_audio(self._user_audio_buffer) and
self._buffer_has_audio(self._assistant_audio_buffer) and
self._sample_rate is not None
self._buffer_has_audio(self._user_audio_buffer)
and self._buffer_has_audio(self._assistant_audio_buffer)
and self._sample_rate is not None
)
def _reset_audio_buffer(self):
@@ -51,13 +52,12 @@ class AudioBufferProcessor(FrameProcessor):
def _merge_audio_buffers(self):
with BytesIO() as buffer:
with wave.open(buffer, 'wb') as wf:
with wave.open(buffer, "wb") as wf:
wf.setnchannels(2)
wf.setsampwidth(2)
wf.setframerate(self._sample_rate)
# Interleave the two audio streams
max_length = max(len(self._user_audio_buffer),
len(self._assistant_audio_buffer))
max_length = max(len(self._user_audio_buffer), len(self._assistant_audio_buffer))
interleaved = bytearray(max_length * 2)
for i in range(0, max_length, 2):
@@ -89,7 +89,7 @@ class AudioBufferProcessor(FrameProcessor):
# Sync the assistant's buffer to the user's buffer by adding silence if needed
if len(self._user_audio_buffer) > len(self._assistant_audio_buffer):
silence_length = len(self._user_audio_buffer) - len(self._assistant_audio_buffer)
silence = b'\x00' * silence_length
silence = b"\x00" * silence_length
self._assistant_audio_buffer.extend(silence)
# if the assistant is speaking, include all audio from the assistant,

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

@@ -12,14 +12,14 @@ try:
except ModuleNotFoundError as e:
logger.error(f"Exception: {e}")
logger.error(
"In order to use Canonical Metrics, you need to `pip install pipecat-ai[canonical]`. " +
"Also, set the `CANONICAL_API_KEY` environment variable.")
"In order to use Canonical Metrics, you need to `pip install pipecat-ai[canonical]`. "
+ "Also, set the `CANONICAL_API_KEY` environment variable."
)
raise Exception(f"Missing module: {e}")
from pipecat.frames.frames import CancelFrame, EndFrame, Frame
from pipecat.processors.audio.audio_buffer_processor import \
AudioBufferProcessor
from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_services import AIService
@@ -56,15 +56,16 @@ class CanonicalMetricsService(AIService):
"""
def __init__(
self,
aiohttp_session: aiohttp.ClientSession,
audio_buffer_processor: AudioBufferProcessor,
call_id: str,
assistant: str,
api_key: str,
api_url: str = "https://voiceapp.canonical.chat/api/v1",
assistant_speaks_first: bool = True,
output_dir: str = "recordings"):
self,
aiohttp_session: aiohttp.ClientSession,
audio_buffer_processor: AudioBufferProcessor,
call_id: str,
assistant: str,
api_key: str,
api_url: str = "https://voiceapp.canonical.chat/api/v1",
assistant_speaks_first: bool = True,
output_dir: str = "recordings",
):
super().__init__()
self._aiohttp_session = aiohttp_session
self._audio_buffer_processor = audio_buffer_processor
@@ -92,7 +93,7 @@ class CanonicalMetricsService(AIService):
filename = self._get_output_filename()
wave_data = pipeline._merge_audio_buffers()
async with aiofiles.open(filename, 'wb') as file:
async with aiofiles.open(filename, "wb") as file:
await file.write(wave_data)
try:
@@ -109,10 +110,7 @@ class CanonicalMetricsService(AIService):
return f"{self._output_dir}/{timestamp}-{uuid.uuid4().hex}.wav"
def _request_headers(self):
return {
"Content-Type": "application/json",
"X-Canonical-Api-Key": self._api_key
}
return {"Content-Type": "application/json", "X-Canonical-Api-Key": self._api_key}
async def _multipart_upload(self, file_path: str):
upload_request, upload_response = await self._request_upload(file_path)
@@ -129,19 +127,14 @@ class CanonicalMetricsService(AIService):
numparts = int((filesize + PART_SIZE - 1) / PART_SIZE)
params = {
'filename': filename,
'parts': numparts,
'callId': self._call_id,
'assistant': {
'id': self._assistant,
'speaksFirst': self._assistant_speaks_first
}
"filename": filename,
"parts": numparts,
"callId": self._call_id,
"assistant": {"id": self._assistant, "speaksFirst": self._assistant_speaks_first},
}
logger.debug(f"Requesting presigned URLs for {numparts} parts")
response = await self._aiohttp_session.post(
f"{self._api_url}/recording/uploadRequest",
headers=self._request_headers(),
json=params
f"{self._api_url}/recording/uploadRequest", headers=self._request_headers(), json=params
)
if not response.ok:
logger.error(f"Failed to get presigned URLs: {await response.text()}")
@@ -149,15 +142,11 @@ class CanonicalMetricsService(AIService):
response_json = await response.json()
return params, response_json
async def _upload_parts(
self,
file_path: str,
upload_response: Dict) -> List[Dict]:
urls = upload_response['urls']
async def _upload_parts(self, file_path: str, upload_response: Dict) -> List[Dict]:
urls = upload_response["urls"]
parts = []
try:
async with aiofiles.open(file_path, 'rb') as file:
async with aiofiles.open(file_path, "rb") as file:
for partnum, upload_url in enumerate(urls, start=1):
data = await file.read(PART_SIZE)
if not data:
@@ -168,35 +157,29 @@ class CanonicalMetricsService(AIService):
logger.error(f"Failed to upload part {partnum}: {await response.text()}")
return None
etag = response.headers['ETag']
parts.append({'partnum': str(partnum), 'etag': etag})
etag = response.headers["ETag"]
parts.append({"partnum": str(partnum), "etag": etag})
except Exception as e:
logger.error(f"Multipart upload aborted, an error occurred: {str(e)}")
return parts
async def _upload_complete(
self,
parts: List[Dict],
upload_request: Dict,
upload_response: Dict):
self, parts: List[Dict], upload_request: Dict, upload_response: Dict
):
params = {
'filename': upload_request['filename'],
'parts': parts,
'slug': upload_response['slug'],
'callId': self._call_id,
'assistant': {
'id': self._assistant,
'speaksFirst': self._assistant_speaks_first
}
"filename": upload_request["filename"],
"parts": parts,
"slug": upload_response["slug"],
"callId": self._call_id,
"assistant": {"id": self._assistant, "speaksFirst": self._assistant_speaks_first},
}
logger.debug(f"Completing upload for {params['filename']}")
logger.debug(f"Slug: {params['slug']}")
response = await self._aiohttp_session.post(
f"{self._api_url}/recording/uploadComplete",
headers=self._request_headers(),
json=params
json=params,
)
if not response.ok:
logger.error(f"Failed to complete upload: {await response.text()}")