197 lines
7.5 KiB
Python
197 lines
7.5 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import asyncio
|
||
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 LLMRunFrame, ManuallySwitchServiceFrame
|
||
from pipecat.pipeline.llm_switcher import LLMSwitcher
|
||
from pipecat.pipeline.pipeline import Pipeline
|
||
from pipecat.pipeline.runner import PipelineRunner
|
||
from pipecat.pipeline.service_switcher import ServiceSwitcher, ServiceSwitcherStrategyManual
|
||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||
from pipecat.runner.types import RunnerArguments
|
||
from pipecat.runner.utils import create_transport
|
||
from pipecat.services.cartesia.stt import CartesiaSTTService
|
||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||
from pipecat.services.google.llm import GoogleLLMService
|
||
from pipecat.services.llm_service import FunctionCallParams
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.daily.transport import DailyParams
|
||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
# "Classic" function
|
||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||
await params.result_callback({"conditions": "nice", "temperature": "75"})
|
||
|
||
|
||
# "Direct" function
|
||
async def get_restaurant_recommendation(params: FunctionCallParams, location: str):
|
||
"""
|
||
Get a restaurant recommendation.
|
||
|
||
Args:
|
||
location (str): The city and state, e.g. "San Francisco, CA".
|
||
"""
|
||
await params.result_callback({"name": "The Golden Dragon"})
|
||
|
||
|
||
# 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,
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_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,
|
||
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")
|
||
|
||
weather_function = FunctionSchema(
|
||
name="get_current_weather",
|
||
description="Get the current weather",
|
||
properties={
|
||
"location": {
|
||
"type": "string",
|
||
"description": "The city and state, e.g. San Francisco, CA",
|
||
},
|
||
"format": {
|
||
"type": "string",
|
||
"enum": ["celsius", "fahrenheit"],
|
||
"description": "The temperature unit to use. Infer this from the user's location.",
|
||
},
|
||
},
|
||
required=["location", "format"],
|
||
)
|
||
|
||
stt_cartesia = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
|
||
stt_deepgram = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
stt_switcher = ServiceSwitcher(
|
||
services=[stt_cartesia, stt_deepgram], strategy_type=ServiceSwitcherStrategyManual
|
||
)
|
||
|
||
tts_cartesia = CartesiaTTSService(
|
||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",
|
||
)
|
||
tts_deepgram = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
tts_switcher = ServiceSwitcher(
|
||
services=[tts_cartesia, tts_deepgram], strategy_type=ServiceSwitcherStrategyManual
|
||
)
|
||
|
||
llm_openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
llm_google = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
|
||
llm_switcher = LLMSwitcher(
|
||
llms=[llm_openai, llm_google], strategy_type=ServiceSwitcherStrategyManual
|
||
)
|
||
# Register a "classic" function
|
||
llm_switcher.register_function("get_current_weather", fetch_weather_from_api)
|
||
# Register a "direct" function
|
||
llm_switcher.register_direct_function(get_restaurant_recommendation)
|
||
|
||
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
||
},
|
||
]
|
||
tools = ToolsSchema(standard_tools=[weather_function, get_restaurant_recommendation])
|
||
|
||
context = LLMContext(messages, tools)
|
||
context_aggregator = LLMContextAggregatorPair(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt_switcher,
|
||
context_aggregator.user(), # User responses
|
||
llm_switcher, # LLM
|
||
tts_switcher, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(), # Assistant spoken responses
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
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")
|
||
# Kick off the conversation.
|
||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||
await task.queue_frames([LLMRunFrame()])
|
||
await asyncio.sleep(15)
|
||
print(f"Switching to {stt_deepgram}")
|
||
await task.queue_frames([ManuallySwitchServiceFrame(service=stt_deepgram)])
|
||
await asyncio.sleep(15)
|
||
print(f"Switching to {llm_google}")
|
||
await task.queue_frames([ManuallySwitchServiceFrame(service=llm_google)])
|
||
await asyncio.sleep(15)
|
||
print(f"Switching to {tts_deepgram}")
|
||
await task.queue_frames([ManuallySwitchServiceFrame(service=tts_deepgram)])
|
||
|
||
@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()
|