Files
pipecat/examples/foundational/12-describe-video.py
Mark Backman 3522bbb533 tmp
2025-03-11 21:55:18 -04:00

111 lines
3.4 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 asyncio
import os
import sys
from typing import Optional
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
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 import CartesiaTTSService
from pipecat.services.moondream import MoondreamService
from pipecat.transports.services.daily import DailyParams, DailyTransport
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
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 main():
async with aiohttp.ClientSession() as session:
(room_url, token) = await configure(session)
transport = DailyTransport(
room_url,
token,
"Describe participant video",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
)
user_response = UserResponseAggregator()
image_requester = UserImageRequester()
vision_aggregator = VisionImageFrameAggregator()
# If you run into weird description, try with use_cpu=True
moondream = MoondreamService()
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await tts.say("Hi there! Feel free to ask me what I see.")
await transport.capture_participant_video(participant["id"], framerate=0)
await transport.capture_participant_transcription(participant["id"])
image_requester.set_participant_id(participant["id"])
pipeline = Pipeline(
[
transport.input(),
user_response,
image_requester,
vision_aggregator,
moondream,
tts,
transport.output(),
]
)
task = PipelineTask(pipeline)
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())