追踪 Pipecat 应用

import asyncio
import uuid
from dotenv import load_dotenv

# 加载环境变量
load_dotenv()

# 导入 Pipecat 组件
from pipecat.audio.vad.silero import SileroVADAnalyzer
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.services.whisper.stt import WhisperSTTService
from pipecat.services.openai import OpenAILLMService, OpenAITTSService
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams

# 导入 span 处理器以启用 LangSmith 追踪
from langsmith_processor import span_processor

async def main():
    # 为 LangSmith 生成唯一的对话 ID
    conversation_id = str(uuid.uuid4())
    print(f"Starting conversation: {conversation_id}")

    # 配置带有语音活动检测的音频输入/输出
    transport = LocalAudioTransport(
        LocalAudioTransportParams(
            audio_in_enabled=True,
            audio_out_enabled=True,
            vad_analyzer=SileroVADAnalyzer(),
        )
    )

    # 初始化 AI 服务
    stt = WhisperSTTService()
    llm = OpenAILLMService(model="gpt-5.4-mini")
    tts = OpenAITTSService(voice="alloy")

    # 设置带有系统提示的对话上下文
    context = OpenAILLMContext(
        messages=[
            {
                "role": "system",
                "content": "You are a helpful voice assistant. Keep responses concise and conversational."
            }
        ]
    )
    context_aggregator = llm.create_context_aggregator(context)

    # 构建处理管道
    pipeline = Pipeline([
        transport.input(),           # 捕获麦克风输入
        stt,                         # 将语音转换为文本
        context_aggregator.user(),   # 将用户消息添加到上下文
        llm,                         # 生成 AI 响应
        tts,                         # 将响应转换为语音
        transport.output(),          # 通过扬声器播放
        context_aggregator.assistant(),  # 将助手响应添加到上下文
    ])

    # 创建启用了追踪的任务
    task = PipelineTask(
        pipeline,
        params=PipelineParams(enable_metrics=True),
        enable_tracing=True,
        enable_turn_tracking=True,
        conversation_id=conversation_id,
    )

    # 运行代理
    runner = PipelineRunner()
    await runner.run(task)

if __name__ == "__main__":
    asyncio.run(main())

python agent.py

from opentelemetry import trace

tracer = trace.get_tracer(__name__)

async def run_voice_session():
    with tracer.start_as_current_span("voice_conversation") as span:
        # 添加自定义元数据
        span.set_attribute("langsmith.metadata.session_type", "voice_assistant")
        span.set_attribute("langsmith.metadata.user_id", "user_123")
        span.set_attribute("langsmith.span.tags", "pipecat,voice-ai,stt-llm-tts")

        # 您的 Pipecat 管道代码在此处
        task = PipelineTask(pipeline, enable_tracing=True)
        await task.queue_frames([TextFrame("Hello")])

from pathlib import Path
from datetime import datetime
from audio_recorder import AudioRecorder

# 设置录制目录
recordings_dir = Path(__file__).parent / "recordings"
recordings_dir.mkdir(exist_ok=True)
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
recording_path = recordings_dir / f"conversation_{timestamp}.wav"

# 创建音频录制器
audio_recorder = AudioRecorder(str(recording_path))

# 注册到 span 处理器以附加到对话 span
span_processor.register_recording(
    conversation_id,
    str(recording_path),
    audio_recorder=audio_recorder
)

# 添加到您的管道
pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm,
    tts,
    audio_recorder,              # 将音频录制器添加到管道
    transport.output(),
    context_aggregator.assistant(),
])

# 运行管道
runner = PipelineRunner()
try:
    await runner.run(task)
finally:
    # 重要：在对话 span 完成之前保存录制
    audio_recorder.save_recording()

from turn_audio_recorder import TurnAudioRecorder

# 创建轮次音频录制器
turn_audio_recorder = TurnAudioRecorder(
    span_processor=span_processor,
    conversation_id=conversation_id,
    recordings_dir=recordings_dir,
    turn_tracker=None,  # 将在任务创建后设置
)

# 注册到 span 处理器
span_processor.register_turn_audio_recorder(conversation_id, turn_audio_recorder)

# 添加到您的管道
pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm,
    tts,
    audio_recorder,              # 完整对话录制
    turn_audio_recorder,         # 按轮次音频片段
    transport.output(),
    context_aggregator.assistant(),
])

# 创建任务
task = PipelineTask(
    pipeline,
    params=PipelineParams(enable_metrics=True),
    enable_tracing=True,
    enable_turn_tracking=True,  # 按轮次音频录制所需
    conversation_id=conversation_id,
)

# 在任务创建后连接轮次跟踪器
if task.turn_tracking_observer:
    turn_audio_recorder.connect_to_turn_tracker(task.turn_tracking_observer)

# 运行管道
runner = PipelineRunner()
try:
    await runner.run(task)
finally:
    audio_recorder.save_recording()