219 lines
7.6 KiB
Python
219 lines
7.6 KiB
Python
#
|
||
# Copyright (c) 2024–2025, 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.base_smart_turn import SmartTurnParams
|
||
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 (
|
||
Frame,
|
||
LLMRunFrame,
|
||
UserImageRawFrame,
|
||
UserImageRequestFrame,
|
||
VisionImageRawFrame,
|
||
)
|
||
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
|
||
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.llm_response_universal import LLMContextAggregatorPair
|
||
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.llm_service import FunctionCallParams
|
||
from pipecat.services.moondream.vision import MoondreamService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.daily.transport import DailyParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
async def fetch_user_image(params: FunctionCallParams):
|
||
"""Fetch the user image.
|
||
|
||
When called, this function pushes a UserImageRequestFrame upstream to the
|
||
transport. As a result, the transport will request the user image and push a
|
||
UserImageRawFrame downstream.
|
||
"""
|
||
user_id = params.arguments["user_id"]
|
||
question = params.arguments["question"]
|
||
logger.debug(f"Requesting image with user_id={user_id}, question={question}")
|
||
|
||
# Request the user image frame frame. In this case we don't use
|
||
# `llm.request_image_frame()` because we don't want the LLM to analyze it.
|
||
await params.llm.push_frame(
|
||
UserImageRequestFrame(user_id=user_id, context=question), FrameDirection.UPSTREAM
|
||
)
|
||
|
||
await params.result_callback(None)
|
||
|
||
|
||
class UserImageProcessor(FrameProcessor):
|
||
"""Converts incoming user images into vision frames.
|
||
|
||
This processor handles the UserImageRawFrame from the transport, converts it
|
||
to a VisionImageRawFrame and pushes it downstream so it can be handled by a
|
||
vision service.
|
||
|
||
"""
|
||
|
||
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:
|
||
frame = VisionImageRawFrame(
|
||
image=frame.image,
|
||
text=frame.request.context,
|
||
size=frame.size,
|
||
format=frame.format,
|
||
)
|
||
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(params=VADParams(stop_secs=0.2)),
|
||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
video_in_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||
logger.info(f"Starting bot")
|
||
|
||
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
|
||
)
|
||
|
||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
llm.register_function("fetch_user_image", fetch_user_image)
|
||
|
||
fetch_image_function = FunctionSchema(
|
||
name="fetch_user_image",
|
||
description="Called when the user requests a description of their camera feed",
|
||
properties={
|
||
"user_id": {
|
||
"type": "string",
|
||
"description": "The ID of the user to grab the image from",
|
||
},
|
||
"question": {
|
||
"type": "string",
|
||
"description": "The question that the user is asking about the image",
|
||
},
|
||
},
|
||
required=["user_id", "question"],
|
||
)
|
||
tools = ToolsSchema(standard_tools=[fetch_image_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 converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
|
||
},
|
||
]
|
||
|
||
context = LLMContext(messages, tools)
|
||
context_aggregator = LLMContextAggregatorPair(context)
|
||
|
||
# This will get the get the user image frame and push it to the LLM.
|
||
image_processor = UserImageProcessor()
|
||
|
||
# If you run into weird description, try with use_cpu=True
|
||
moondream = MoondreamService()
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt, # STT
|
||
context_aggregator.user(), # User responses
|
||
ParallelPipeline(
|
||
[llm], # LLM
|
||
[image_processor, moondream],
|
||
),
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(), # Assistant spoken responses
|
||
]
|
||
)
|
||
|
||
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)
|
||
|
||
# Kick off the conversation.
|
||
messages.append(
|
||
{
|
||
"role": "system",
|
||
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
|
||
}
|
||
)
|
||
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()
|