Pipecat

pip install traceAI-pipecat pipecat-ai[tracing]

import os

os.environ["FI_API_KEY"] = FI_API_KEY
os.environ["FI_SECRET_KEY"] = FI_SECRET_KEY

from fi_instrumentation.otel import register, Transport, ProjectType

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="Pipecat Voice App",
    set_global_tracer_provider=True,
)

import os

from loguru import logger
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.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
from pipecat.runner.types import RunnerArguments
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.network.small_webrtc import SmallWebRTCTransport


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 friendly AI assistant. Respond naturally and keep your answers conversational.",
        },
    ]

    context = OpenAILLMContext(messages)
    context_aggregator = llm.create_context_aggregator(context)

    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            rtvi,  # RTVI processor
            stt,
            context_aggregator.user(),  # User responses
            llm,  # LLM
            tts,  # TTS
            transport.output(),  # Transport bot output
            context_aggregator.assistant(),  # Assistant spoken responses
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            enable_metrics=True,
            enable_usage_metrics=True,
        ),
        enable_tracing=True,
        enable_turn_tracking=True,
        conversation_id="customer-123",
        additional_span_attributes={"session.id": "abc-123"},
        observers=[RTVIObserver(rtvi)],
    )

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
        messages.append(
            {"role": "system", "content": "Say hello and briefly introduce yourself."}
        )
        await task.queue_frames([context_aggregator.user().get_context_frame()])

    @transport.event_handler("on_client_disconnected")
    async def on_client_disconnected(transport, client):
        logger.info(f"Client disconnected")
        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 for the bot starter."""

    transport = SmallWebRTCTransport(
        params=TransportParams(
            audio_in_enabled=True,
            audio_out_enabled=True,
            vad_analyzer=SileroVADAnalyzer(),
        ),
        webrtc_connection=runner_args.webrtc_connection,
    )

    await run_bot(transport, runner_args)


if __name__ == "__main__":
    from pipecat.runner.run import main

    main()