0a163201ea
- Enhance TranscriptHandler to aggregate transcript fragments into complete sentences using match_endofsentence() - Add Whisker debugger integration for real-time pipeline visualization - Implement sentence buffering for both user and assistant messages - Add finalize_partial_sentences() method to handle incomplete sentences on disconnect - Improves transcript readability by reducing fragmented output Changes: - Import match_endofsentence utility for sentence boundary detection - Add pipecat_whisker.WhiskerObserver for debugging capabilities - Modify on_transcript_update() to accumulate and aggregate messages - Create _save_sentence() helper method for complete sentence handling - Update client disconnect handler to preserve partial sentences
255 lines
9.9 KiB
Python
255 lines
9.9 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import os
|
||
from typing import List, Optional
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||
from pipecat.frames.frames import LLMRunFrame, TranscriptionMessage, TranscriptionUpdateFrame
|
||
from pipecat.pipeline.pipeline import Pipeline
|
||
from pipecat.pipeline.runner import PipelineRunner
|
||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||
from pipecat.processors.transcript_processor import TranscriptProcessor
|
||
from pipecat.runner.types import RunnerArguments
|
||
from pipecat.runner.utils import create_transport
|
||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.daily.transport import DailyParams
|
||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||
from pipecat.utils.string import match_endofsentence
|
||
|
||
logger.info("Loading Whisker debugger...")
|
||
from pipecat_whisker import WhiskerObserver
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
class TranscriptHandler:
|
||
"""Handles real-time transcript processing and output.
|
||
|
||
Maintains a list of conversation messages and outputs them either to a log
|
||
or to a file as they are received. Each message includes its timestamp and role.
|
||
|
||
Attributes:
|
||
messages: List of all processed transcript messages
|
||
output_file: Optional path to file where transcript is saved. If None, outputs to log only.
|
||
"""
|
||
|
||
def __init__(self, output_file: Optional[str] = None):
|
||
"""Initialize handler with optional file output.
|
||
|
||
Args:
|
||
output_file: Path to output file. If None, outputs to log only.
|
||
"""
|
||
self.messages: List[TranscriptionMessage] = []
|
||
self.output_file: Optional[str] = output_file
|
||
self._current_user_sentence = ""
|
||
self._current_assistant_sentence = ""
|
||
logger.debug(
|
||
f"TranscriptHandler initialized {'with output_file=' + output_file if output_file else 'with log output only'}"
|
||
)
|
||
|
||
async def save_message(self, message: TranscriptionMessage):
|
||
"""Save a single transcript message.
|
||
|
||
Outputs the message to the log and optionally to a file.
|
||
|
||
Args:
|
||
message: The message to save
|
||
"""
|
||
timestamp = f"[{message.timestamp}] " if message.timestamp else ""
|
||
line = f"{timestamp}{message.role}: {message.content}"
|
||
|
||
# Always log the message
|
||
logger.info(f"Transcript: {line}")
|
||
|
||
# Optionally write to file
|
||
if self.output_file:
|
||
try:
|
||
with open(self.output_file, "a", encoding="utf-8") as f:
|
||
f.write(line + "\n")
|
||
except Exception as e:
|
||
logger.error(f"Error saving transcript message to file: {e}")
|
||
|
||
async def _save_sentence(self, role: str, content: str, timestamp: Optional[str] = None):
|
||
"""Save a complete sentence as a transcript message.
|
||
|
||
Args:
|
||
role: The role (user/assistant)
|
||
content: The complete sentence content
|
||
timestamp: Optional timestamp
|
||
"""
|
||
# Cast role to the appropriate literal type
|
||
message_role = "user" if role == "user" else "assistant"
|
||
sentence_message = TranscriptionMessage(
|
||
role=message_role, content=content.strip(), timestamp=timestamp
|
||
)
|
||
self.messages.append(sentence_message)
|
||
await self.save_message(sentence_message)
|
||
|
||
async def on_transcript_update(
|
||
self, processor: TranscriptProcessor, frame: TranscriptionUpdateFrame
|
||
):
|
||
"""Handle new transcript messages.
|
||
|
||
Aggregates messages into complete sentences before saving them using match_endofsentence.
|
||
|
||
Args:
|
||
processor: The TranscriptProcessor that emitted the update
|
||
frame: TranscriptionUpdateFrame containing new messages
|
||
"""
|
||
logger.debug(f"Received transcript update with {len(frame.messages)} new messages")
|
||
|
||
for msg in frame.messages:
|
||
# Accumulate text for the appropriate role
|
||
if msg.role == "user":
|
||
self._current_user_sentence += msg.content + " "
|
||
# Check if we have a complete sentence
|
||
if match_endofsentence(self._current_user_sentence):
|
||
await self._save_sentence("user", self._current_user_sentence, msg.timestamp)
|
||
self._current_user_sentence = ""
|
||
elif msg.role == "assistant":
|
||
self._current_assistant_sentence += msg.content + " "
|
||
# Check if we have a complete sentence
|
||
if match_endofsentence(self._current_assistant_sentence):
|
||
await self._save_sentence(
|
||
"assistant", self._current_assistant_sentence, msg.timestamp
|
||
)
|
||
self._current_assistant_sentence = ""
|
||
|
||
async def finalize_partial_sentences(self):
|
||
"""Save any remaining partial sentences when the conversation ends."""
|
||
if self._current_user_sentence.strip():
|
||
await self._save_sentence("user", self._current_user_sentence)
|
||
self._current_user_sentence = ""
|
||
|
||
if self._current_assistant_sentence.strip():
|
||
await self._save_sentence("assistant", self._current_assistant_sentence)
|
||
self._current_assistant_sentence = ""
|
||
|
||
|
||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||
# instantiated. The function will be called when the desired transport gets
|
||
# selected.
|
||
transport_params = {
|
||
"daily": lambda: DailyParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||
logger.info(f"Starting bot")
|
||
|
||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
|
||
tts = CartesiaTTSService(
|
||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||
)
|
||
|
||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
|
||
messages = [
|
||
{
|
||
"role": "system",
|
||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative, helpful, and brief way. Say hello.",
|
||
},
|
||
]
|
||
|
||
context = LLMContext(messages)
|
||
context_aggregator = LLMContextAggregatorPair(context)
|
||
|
||
# Create transcript processor and handler
|
||
transcript = TranscriptProcessor()
|
||
transcript_handler = TranscriptHandler() # Output to log only
|
||
# transcript_handler = TranscriptHandler(output_file="transcript.txt") # Output to file and log
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt, # STT
|
||
transcript.user(), # User transcripts
|
||
context_aggregator.user(), # User responses
|
||
llm, # LLM
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
transcript.assistant(), # Assistant transcripts
|
||
context_aggregator.assistant(), # Assistant spoken responses
|
||
]
|
||
)
|
||
|
||
# Create Whisker debugger observer
|
||
whisker = WhiskerObserver(pipeline)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
observers=[whisker],
|
||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# Start conversation - empty prompt to let LLM follow system instructions
|
||
await task.queue_frames([LLMRunFrame()])
|
||
|
||
# Register event handler for transcript updates
|
||
@transcript.event_handler("on_transcript_update")
|
||
async def on_transcript_update(processor, frame):
|
||
await transcript_handler.on_transcript_update(processor, frame)
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def on_client_disconnected(transport, client):
|
||
logger.info(f"Client disconnected")
|
||
# Finalize any partial sentences before canceling
|
||
await transcript_handler.finalize_partial_sentences()
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||
await runner.run(task)
|
||
|
||
|
||
async def bot(runner_args: RunnerArguments):
|
||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||
transport = await create_transport(runner_args, transport_params)
|
||
await run_bot(transport, runner_args)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from pipecat.runner.run import main
|
||
|
||
main()
|