pipecat/examples/voice/voice-langchain.py

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


import os

from dotenv import load_dotenv
from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.chat_history import BaseChatMessageHistory
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_openai import ChatOpenAI
from loguru import logger

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 (
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
from pipecat.processors.frameworks.langchain import LangchainProcessor
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.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

load_dotenv(override=True)


message_store = {}


def get_session_history(session_id: str) -> BaseChatMessageHistory:
    if session_id not in message_store:
        message_store[session_id] = ChatMessageHistory()
    return message_store[session_id]


# 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.environ["DEEPGRAM_API_KEY"])

    tts = CartesiaTTSService(
        api_key=os.environ["CARTESIA_API_KEY"],
        settings=CartesiaTTSService.Settings(
            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
        ),
    )

    prompt = ChatPromptTemplate.from_messages(
        [
            (
                "system",
                "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
            ),
            MessagesPlaceholder("chat_history"),
            ("human", "{input}"),
        ]
    )
    chain = prompt | ChatOpenAI(model="gpt-4.1", temperature=0.7)
    history_chain = RunnableWithMessageHistory(
        chain,
        get_session_history,
        history_messages_key="chat_history",
        input_messages_key="input",
    )
    lc = LangchainProcessor(history_chain)

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

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,
            user_aggregator,  # User responses
            lc,  # Langchain
            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.
        # An `LLMContextFrame` will be picked up by the LangchainProcessor using
        # only the content of the last message to inject it in the prompt defined
        # above. So no role is required here.
        context.add_message(
            {"role": "developer", "content": "Please briefly 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()