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

Switch questions

Browse Source
This commit is contained in:
James Hush
2024-11-27 15:10:50 +08:00
parent 909bb30517
commit f34e6bce94
2 changed files with 66 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
examples/foundational/07-interruptible.py
View File

@@ -10,11 +10,12 @@ import os
import sys
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.frames.frames import BotSpeakingFrame, Frame, InputAudioRawFrame, LLMMessagesFrame, TTSAudioRawFrame, TextFrame, UserStoppedSpeakingFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -30,6 +31,22 @@ load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
class DebugProcessor(FrameProcessor):
def __init__(self, name, **kwargs):
self._name = name
super().__init__(**kwargs)
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if not (
isinstance(frame, InputAudioRawFrame)
or isinstance(frame, BotSpeakingFrame)
or isinstance(frame, TTSAudioRawFrame)
or isinstance(frame, TextFrame)
):
logger.debug(f"--- {self._name}: {frame} {direction}")
await self.push_frame(frame, direction)
async def main():
async with aiohttp.ClientSession() as session:
@@ -63,11 +80,14 @@ async def main():
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
dp = DebugProcessor("dp")
pipeline = Pipeline(
[
transport.input(), # Transport user input
context_aggregator.user(), # User responses
dp,
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output

83
examples/foundational/race_bot.py
View File

@@ -14,12 +14,19 @@ from loguru import logger
from runner import configure
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (BotSpeakingFrame, EndFrame, Frame,
InputAudioRawFrame, StartInterruptionFrame,
StopInterruptionFrame, TextFrame,
TranscriptionFrame, TTSAudioRawFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame)
from pipecat.frames.frames import (
BotSpeakingFrame,
EndFrame,
Frame,
InputAudioRawFrame,
StartInterruptionFrame,
StopInterruptionFrame,
TextFrame,
TranscriptionFrame,
TTSAudioRawFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -56,11 +63,15 @@ async def main():
(room_url, _) = await configure(session)
transport = DailyTransport(
room_url, None, "AI Bot", DailyParams(
audio_out_enabled=True,
room_url,
None,
"AI Bot",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),)
vad_analyzer=SileroVADAnalyzer(),
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
@@ -88,8 +99,8 @@ async def main():
[
# transport.input(),
context_aggregator.user(),
dp,
llm,
dp,
tts,
transport.output(),
context_aggregator.assistant(),
@@ -106,7 +117,7 @@ async def main():
async def on_first_participant_joined(transport, participant):
participant_id = participant.get("info", {}).get("participantId", "")
# Create frames for 60 seconds
# Create frames for 600 seconds
start_time = time.time()
while time.time() - start_time < 300:
elapsed_time = round(time.time() - start_time)
@@ -114,62 +125,58 @@ async def main():
await task.queue_frame(
StartInterruptionFrame(),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frame(
UserStartedSpeakingFrame(),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frame(
TranscriptionFrame("Tell a joke about dogs.", participant_id, time.time()),
TranscriptionFrame("Tell me more about your company.", participant_id, time.time()),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frame(
StopInterruptionFrame(),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frame(
UserStoppedSpeakingFrame(),
)
await asyncio.sleep(5)
await task.queue_frame(
StartInterruptionFrame()
)
await asyncio.sleep(1)
await asyncio.sleep(5)
await task.queue_frame(StartInterruptionFrame())
await asyncio.sleep(1)
await task.queue_frame(
UserStartedSpeakingFrame(),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frame(
TranscriptionFrame("Tell a joke about cats.", participant_id, time.time()),
TranscriptionFrame("Give me a list of appointment dates.", participant_id, time.time()),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frames(
StopInterruptionFrame(),
)
await asyncio.sleep(1)
await asyncio.sleep(1)
await task.queue_frame(
UserStoppedSpeakingFrame(),
)
await asyncio.sleep(5)
await task.queue_frame(EndFrame())
# @transport.event_handler("on_first_participant_joined")
# async def on_first_participant_joined(transport, participant):
# await transport.capture_participant_transcription(participant["id"])