300 lines
10 KiB
Python
300 lines
10 KiB
Python
#
|
|
# Copyright (c) 2025, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
import asyncio
|
|
import os
|
|
import sys
|
|
|
|
import aiohttp
|
|
from dotenv import load_dotenv
|
|
from loguru import logger
|
|
from PIL import Image
|
|
from pipecatcloud.agent import DailySessionArguments
|
|
|
|
from pipecat.audio.turn.smart_turn.fal_smart_turn import FalSmartTurnAnalyzer
|
|
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
from pipecat.audio.vad.vad_analyzer import VADParams
|
|
from pipecat.frames.frames import (
|
|
BotStartedSpeakingFrame,
|
|
BotStoppedSpeakingFrame,
|
|
Frame,
|
|
MetricsFrame,
|
|
OutputImageRawFrame,
|
|
SpriteFrame,
|
|
)
|
|
from pipecat.metrics.metrics import SmartTurnMetricsData
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
|
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
|
from pipecat.processors.frameworks.rtvi import (
|
|
RTVIConfig,
|
|
RTVIObserver,
|
|
RTVIProcessor,
|
|
RTVIServerMessageFrame,
|
|
)
|
|
from pipecat.services.cartesia.tts import CartesiaTTSService
|
|
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
from pipecat.services.google.llm import GoogleLLMService
|
|
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
|
|
|
load_dotenv(override=True)
|
|
|
|
# Check if we're in local development mode
|
|
LOCAL = os.getenv("LOCAL")
|
|
|
|
logger.remove()
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
sprites = []
|
|
script_dir = os.path.dirname(__file__)
|
|
|
|
# Load sequential animation frames
|
|
for i in range(1, 26):
|
|
# Build the full path to the image file
|
|
full_path = os.path.join(script_dir, f"assets/robot0{i}.png")
|
|
# Get the filename without the extension to use as the dictionary key
|
|
# Open the image and convert it to bytes
|
|
with Image.open(full_path) as img:
|
|
sprites.append(OutputImageRawFrame(image=img.tobytes(), size=img.size, format=img.format))
|
|
|
|
# Create a smooth animation by adding reversed frames
|
|
flipped = sprites[::-1]
|
|
sprites.extend(flipped)
|
|
|
|
# Define static and animated states
|
|
quiet_frame = sprites[0] # Static frame for when bot is listening
|
|
talking_frame = SpriteFrame(images=sprites) # Animation sequence for when bot is talking
|
|
|
|
|
|
class TalkingAnimation(FrameProcessor):
|
|
"""Manages the bot's visual animation states.
|
|
|
|
Switches between static (listening) and animated (talking) states based on
|
|
the bot's current speaking status.
|
|
"""
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
self._is_talking = False
|
|
|
|
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
|
"""Process incoming frames and update animation state.
|
|
|
|
Args:
|
|
frame: The incoming frame to process
|
|
direction: The direction of frame flow in the pipeline
|
|
"""
|
|
await super().process_frame(frame, direction)
|
|
|
|
# Switch to talking animation when bot starts speaking
|
|
if isinstance(frame, BotStartedSpeakingFrame):
|
|
if not self._is_talking:
|
|
await self.push_frame(talking_frame)
|
|
self._is_talking = True
|
|
# Return to static frame when bot stops speaking
|
|
elif isinstance(frame, BotStoppedSpeakingFrame):
|
|
await self.push_frame(quiet_frame)
|
|
self._is_talking = False
|
|
|
|
await self.push_frame(frame, direction)
|
|
|
|
|
|
class SmartTurnMetricsProcessor(FrameProcessor):
|
|
"""Processes the metrics data from Smart Turn Analyzer.
|
|
|
|
This processor is responsible for handling smart turn metrics data
|
|
and forwarding it to the client UI via RTVI.
|
|
"""
|
|
|
|
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
|
"""Process incoming frames and handle Smart Turn metrics.
|
|
|
|
Args:
|
|
frame: The incoming frame to process
|
|
direction: The direction of frame flow in the pipeline
|
|
"""
|
|
await super().process_frame(frame, direction)
|
|
|
|
# Handle Smart Turn metrics
|
|
if isinstance(frame, MetricsFrame):
|
|
for metrics in frame.data:
|
|
if isinstance(metrics, SmartTurnMetricsData):
|
|
logger.info(f"Smart Turn metrics: {metrics}")
|
|
|
|
# Create a payload with the smart turn prediction data
|
|
smart_turn_data = {
|
|
"type": "smart_turn_result",
|
|
"is_complete": metrics.is_complete,
|
|
"probability": metrics.probability,
|
|
"inference_time_ms": metrics.inference_time_ms,
|
|
"server_total_time_ms": metrics.server_total_time_ms,
|
|
"e2e_processing_time_ms": metrics.e2e_processing_time_ms,
|
|
}
|
|
|
|
# Send the data to the client via RTVI
|
|
rtvi_frame = RTVIServerMessageFrame(data=smart_turn_data)
|
|
await self.push_frame(rtvi_frame)
|
|
|
|
await self.push_frame(frame, direction)
|
|
|
|
|
|
async def main(transport: DailyTransport):
|
|
# Configure your STT, LLM, and TTS services here
|
|
# Swap out different processors or properties to customize your bot
|
|
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
|
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
|
|
tts = CartesiaTTSService(
|
|
api_key=os.getenv("CARTESIA_API_KEY"),
|
|
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
|
)
|
|
|
|
# Set up the initial context for the conversation
|
|
# You can specified initial system and assistant messages here
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
"content": "You are Chatbot, a friendly, helpful robot. 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, but keep your responses brief. Start by introducing yourself.",
|
|
},
|
|
]
|
|
|
|
# This sets up the LLM context by providing messages and tools
|
|
context = OpenAILLMContext(messages)
|
|
context_aggregator = llm.create_context_aggregator(context)
|
|
|
|
ta = TalkingAnimation()
|
|
smart_turn_metrics_processor = SmartTurnMetricsProcessor()
|
|
|
|
# RTVI events for Pipecat client UI
|
|
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
|
|
|
|
# A core voice AI pipeline
|
|
# Add additional processors to customize the bot's behavior
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
rtvi,
|
|
smart_turn_metrics_processor,
|
|
stt,
|
|
context_aggregator.user(),
|
|
llm,
|
|
tts,
|
|
ta,
|
|
transport.output(),
|
|
context_aggregator.assistant(),
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
allow_interruptions=True,
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
observers=[RTVIObserver(rtvi)],
|
|
)
|
|
|
|
@rtvi.event_handler("on_client_ready")
|
|
async def on_client_ready(rtvi):
|
|
logger.debug("Client ready event received")
|
|
await rtvi.set_bot_ready()
|
|
# Kick off the conversation
|
|
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
|
|
|
@transport.event_handler("on_first_participant_joined")
|
|
async def on_first_participant_joined(transport, participant):
|
|
logger.info("First participant joined: {}", participant["id"])
|
|
# Push a static frame to show the bot is listening
|
|
await task.queue_frame(quiet_frame)
|
|
|
|
@transport.event_handler("on_participant_left")
|
|
async def on_participant_left(transport, participant, reason):
|
|
logger.info("Participant left: {}", participant)
|
|
await task.cancel()
|
|
|
|
runner = PipelineRunner(handle_sigint=False, force_gc=True)
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
async def bot(args: DailySessionArguments):
|
|
"""Main bot entry point compatible with the FastAPI route handler.
|
|
|
|
Args:
|
|
room_url: The Daily room URL
|
|
token: The Daily room token
|
|
body: The configuration object from the request body
|
|
session_id: The session ID for logging
|
|
"""
|
|
from pipecat.audio.filters.krisp_filter import KrispFilter
|
|
|
|
logger.info(f"Bot process initialized {args.room_url} {args.token}")
|
|
async with aiohttp.ClientSession() as session:
|
|
transport = DailyTransport(
|
|
args.room_url,
|
|
args.token,
|
|
"Smart Turn Bot",
|
|
params=DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_in_filter=KrispFilter(),
|
|
audio_out_enabled=True,
|
|
video_out_enabled=True,
|
|
video_out_width=1024,
|
|
video_out_height=576,
|
|
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
|
turn_analyzer=FalSmartTurnAnalyzer(
|
|
api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=session
|
|
),
|
|
),
|
|
)
|
|
|
|
try:
|
|
await main(transport)
|
|
logger.info("Bot process completed")
|
|
except Exception as e:
|
|
logger.exception(f"Error in bot process: {str(e)}")
|
|
raise
|
|
|
|
|
|
# Local development
|
|
async def local_daily():
|
|
"""Daily transport for local development."""
|
|
from runner import configure
|
|
|
|
try:
|
|
async with aiohttp.ClientSession() as session:
|
|
(room_url, token) = await configure(session)
|
|
transport = DailyTransport(
|
|
room_url,
|
|
token,
|
|
"Smart Turn Bot",
|
|
params=DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
video_out_enabled=True,
|
|
video_out_width=1024,
|
|
video_out_height=576,
|
|
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
|
turn_analyzer=FalSmartTurnAnalyzer(
|
|
api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=session
|
|
),
|
|
),
|
|
)
|
|
|
|
await main(transport)
|
|
except Exception as e:
|
|
logger.exception(f"Error in local development mode: {e}")
|
|
|
|
|
|
# Local development entry point
|
|
if LOCAL and __name__ == "__main__":
|
|
try:
|
|
asyncio.run(local_daily())
|
|
except Exception as e:
|
|
logger.exception(f"Failed to run in local mode: {e}")
|