Files
pipecat/examples/foundational/12-describe-video.py
2025-04-24 17:14:18 -07:00

126 lines
3.9 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
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, TextFrame, UserImageRequestFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.user_response import UserResponseAggregator
from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
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 TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
load_dotenv(override=True)
class UserImageRequester(FrameProcessor):
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), FrameDirection.UPSTREAM
)
await self.push_frame(frame, direction)
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
# Get WebRTC peer connection ID
webrtc_peer_id = webrtc_connection.pc_id
logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
transport = SmallWebRTCTransport(
webrtc_connection=webrtc_connection,
params=TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
user_response = UserResponseAggregator()
# Initialize the image requester without setting the participant ID yet
image_requester = UserImageRequester()
vision_aggregator = VisionImageFrameAggregator()
# 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,
vision_aggregator,
moondream,
tts,
transport.output(),
]
)
task = PipelineTask(pipeline)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected: {client}")
# Welcome message
await tts.say("Hi there! Feel free to ask me what I see.")
# Set the participant ID in the image requester
image_requester.set_participant_id(webrtc_peer_id)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
if __name__ == "__main__":
from run import main
main()