pipecat/examples/foundational/17-detect-user-idle.py

#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#


import asyncio
import os

from dotenv import load_dotenv
from loguru import logger

from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
    EndTaskFrame,
    LLMMessagesAppendFrame,
    LLMRunFrame,
    TTSSpeakFrame,
)
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,
    LLMUserAggregatorParams,
)
from pipecat.processors.frame_processor import FrameDirection
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.llm_service import FunctionCallParams
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

load_dotenv(override=True)


class IdleHandler:
    """Helper class to manage user idle retry logic."""

    def __init__(self):
        self._retry_count = 0

    def reset(self):
        """Reset the retry count when user becomes active."""
        self._retry_count = 0

    async def handle_idle(self, aggregator):
        """Handle user idle event with escalating prompts."""
        self._retry_count += 1

        if self._retry_count == 1:
            # First attempt: Add a gentle prompt to the conversation
            message = {
                "role": "system",
                "content": "The user has been quiet. Politely and briefly ask if they're still there.",
            }
            await aggregator.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
        elif self._retry_count == 2:
            # Second attempt: More direct prompt
            message = {
                "role": "system",
                "content": "The user is still inactive. Ask if they'd like to continue our conversation.",
            }
            await aggregator.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
        else:
            # Third attempt: End the conversation
            await aggregator.push_frame(
                TTSSpeakFrame("It seems like you're busy right now. Have a nice day!")
            )
            await aggregator.push_frame(EndTaskFrame(), FrameDirection.UPSTREAM)


async def fetch_weather_from_api(params: FunctionCallParams):
    # Simulate a slow API call, waiting longer than the user idle timeout.
    await asyncio.sleep(3)
    await params.result_callback({"conditions": "nice", "temperature": "75"})


async def fetch_restaurant_recommendation(params: FunctionCallParams):
    await asyncio.sleep(6)
    await params.result_callback({"name": "The Golden Dragon"})


# We use lambdas to defer transport parameter creation until the transport
# type is selected at runtime.
transport_params = {
    "daily": lambda: DailyParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "twilio": lambda: FastAPIWebsocketParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
}


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"))

    llm.register_function("get_current_weather", fetch_weather_from_api)
    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)

    @llm.event_handler("on_function_calls_started")
    async def on_function_calls_started(service, function_calls):
        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))

    weather_function = FunctionSchema(
        name="get_current_weather",
        description="Get the current weather",
        properties={
            "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA",
            },
            "format": {
                "type": "string",
                "enum": ["celsius", "fahrenheit"],
                "description": "The temperature unit to use. Infer this from the user's location.",
            },
        },
        required=["location", "format"],
    )
    restaurant_function = FunctionSchema(
        name="get_restaurant_recommendation",
        description="Get a restaurant recommendation",
        properties={
            "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA",
            },
        },
        required=["location"],
    )
    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])

    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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
        },
    ]

    context = LLMContext(messages, tools)
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            user_idle_timeout=5.0,  # Detect user idle after 5 seconds
            vad_analyzer=SileroVADAnalyzer(),
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,
            user_aggregator,  # User aggregator with built-in idle detection
            llm,  # LLM
            tts,  # TTS
            transport.output(),  # Transport bot output
            assistant_aggregator,
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            enable_metrics=True,
            enable_usage_metrics=True,
        ),
        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
    )

    # Set up idle handling with retry logic
    idle_handler = IdleHandler()

    @user_aggregator.event_handler("on_user_turn_idle")
    async def on_user_turn_idle(aggregator):
        logger.info(f"User turn idle")
        await idle_handler.handle_idle(aggregator)

    @user_aggregator.event_handler("on_user_turn_started")
    async def on_user_turn_started(aggregator, strategy):
        idle_handler.reset()

    @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": "Please introduce yourself to the user."})
        await task.queue_frames([LLMRunFrame()])

    @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 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()