pipecat/examples/foundational/49d-thinking-functions-google.py

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

import os

from dotenv import load_dotenv
from loguru import logger

from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame
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 (
    AssistantThoughtMessage,
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
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.google.llm import GoogleLLMService, GoogleThinkingConfig
from pipecat.services.llm_service import FunctionCallParams
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)


async def check_flight_status(params: FunctionCallParams, flight_number: str):
    """Check the status of a flight. Returns status (e.g., "on time", "delayed") and departure time.

    Args:
        flight_number (str): The flight number, e.g. "AA100".
    """
    await params.result_callback({"status": "delayed", "departure_time": "14:30"})


async def book_taxi(params: FunctionCallParams, time: str):
    """Book a taxi for a given time. Returns status (e.g., "done").

    Args:
        time (str): The time to book the taxi for, e.g. "15:00".
    """
    await params.result_callback({"status": "done"})


# 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"),
        settings=CartesiaTTSService.Settings(
            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
        ),
    )

    llm = GoogleLLMService(
        api_key=os.getenv("GOOGLE_API_KEY"),
        # model="gemini-3-pro-preview", # A more powerful reasoning model, but slower
        settings=GoogleLLMService.Settings(
            thinking=GoogleThinkingConfig(
                thinking_budget=-1,  # Dynamic thinking
                include_thoughts=True,
            ),
            system_instruction="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.",
        ),
    )

    llm.register_direct_function(check_flight_status)
    llm.register_direct_function(book_taxi)

    tools = ToolsSchema(standard_tools=[check_flight_status, book_taxi])

    context = LLMContext(tools=tools)
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
    )

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,
            user_aggregator,  # User responses
            llm,  # LLM
            tts,  # TTS
            transport.output(),  # Transport bot output
            assistant_aggregator,  # Assistant spoken responses
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            enable_metrics=True,
            enable_usage_metrics=True,
        ),
        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")
        # Kick off the conversation.
        context.add_message({"role": "user", "content": "Say hello briefly."})
        # Replace the above with one of these example prompts to demonstrate
        # thinking and function calling.
        # This example comes from Gemini docs.
        # context.add_message(
        #     {
        #         "role": "user",
        #         "content": "Check the status of flight AA100 and, if it's delayed, book me a taxi 2 hours before its departure time.",
        #     }
        # )
        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()

    @assistant_aggregator.event_handler("on_assistant_thought")
    async def on_assistant_thought(aggregator, message: AssistantThoughtMessage):
        logger.info(f"Thought (timestamp: {message.timestamp}): {message.content}")

    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()