pipecat/examples/foundational/14v-function-calling-openai.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.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
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, 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.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.stt import OpenAISTTService
from pipecat.services.openai.tts import OpenAITTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
from pipecat.turns.user_turn_strategies import UserTurnStrategies

load_dotenv(override=True)


async def fetch_weather_from_api(params: FunctionCallParams):
    await params.result_callback({"conditions": "nice", "temperature": "75"})


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


# 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)),
    ),
    "twilio": lambda: FastAPIWebsocketParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
}


async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    logger.info(f"Starting bot")

    stt = OpenAISTTService(
        api_key=os.getenv("OPENAI_API_KEY"),
        model="gpt-4o-transcribe",
        prompt="Expect words related weather, such as temperature and conditions. And restaurant names.",
    )

    # voice choices: ash, ballad, or any other voice available in the OpenAI TTS API
    # see https://www.openai.fm/
    tts = OpenAITTSService(
        api_key=os.getenv("OPENAI_API_KEY"),
        voice="ballad",
        instructions="Please speak clearly and at a moderate pace.",
    )

    # model choices: gpt-4o, gpt-4.1, etc.
    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))

    # You can also register a function_name of None to get all functions
    # sent to the same callback with an additional function_name parameter.
    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)
    context_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            user_turn_strategies=UserTurnStrategies(
                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
            ),
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            context_aggregator.user(),
            llm,
            tts,
            transport.output(),
            context_aggregator.assistant(),
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            enable_metrics=True,
            enable_usage_metrics=True,
        ),
    )

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
        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()