pipecat/examples/foundational/12-describe-video.py

#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import os
from typing import Optional

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
    Frame,
    LLMContextFrame,
    TextFrame,
    TTSSpeakFrame,
    UserImageRawFrame,
    UserImageRequestFrame,
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.user_response import UserResponseAggregator
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import (
    create_transport,
    get_transport_client_id,
    maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.moondream.vision import MoondreamService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams

load_dotenv(override=True)


class UserImageRequester(FrameProcessor):
    """Converts incoming text into requests for user images."""

    def __init__(self, participant_id: Optional[str] = None):
        super().__init__()
        self._participant_id = participant_id

    def set_participant_id(self, participant_id: str):
        self._participant_id = participant_id

    async def process_frame(self, frame: Frame, direction: FrameDirection):
        await super().process_frame(frame, direction)

        if self._participant_id and isinstance(frame, TextFrame):
            await self.push_frame(
                UserImageRequestFrame(self._participant_id, context=frame.text),
                FrameDirection.UPSTREAM,
            )
        else:
            await self.push_frame(frame, direction)


class UserImageProcessor(FrameProcessor):
    """Converts incoming user images into context frames."""

    async def process_frame(self, frame: Frame, direction: FrameDirection):
        await super().process_frame(frame, direction)

        if isinstance(frame, UserImageRawFrame):
            if frame.request and frame.request.context:
                context = LLMContext()
                context.add_image_frame_message(
                    image=frame.image,
                    text=frame.request.context,
                    size=frame.size,
                    format=frame.format,
                )
                frame = LLMContextFrame(context)
                await self.push_frame(frame)
        else:
            await self.push_frame(frame, direction)


# 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,
        video_in_enabled=True,
        vad_analyzer=SileroVADAnalyzer(),
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_in_enabled=True,
        vad_analyzer=SileroVADAnalyzer(),
    ),
}


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

    user_response = UserResponseAggregator()

    # Initialize the image requester without setting the participant ID yet
    image_requester = UserImageRequester()

    image_processor = UserImageProcessor()

    # If you run into weird description, try with use_cpu=True
    moondream = MoondreamService()

    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
    )

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            user_response,
            image_requester,
            image_processor,
            moondream,
            tts,
            transport.output(),
        ]
    )

    task = PipelineTask(
        pipeline,
        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: {client}")

        await maybe_capture_participant_camera(transport, client)

        # Set the participant ID in the image requester
        client_id = get_transport_client_id(transport, client)
        image_requester.set_participant_id(client_id)

        # Welcome message
        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))

    @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()