158 lines
5.3 KiB
Python
158 lines
5.3 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
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.vad.silero import SileroVADAnalyzer
|
||
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.filters.stt_mute_filter import STTMuteConfig, STTMuteFilter, STTMuteStrategy
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||
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.network.fastapi_websocket import FastAPIWebsocketParams
|
||
from pipecat.transports.services.daily import DailyParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||
# Add a delay to test interruption during function calls
|
||
logger.info("Weather API call starting...")
|
||
await asyncio.sleep(5) # 5-second delay
|
||
logger.info("Weather API call completed")
|
||
await params.result_callback({"conditions": "nice", "temperature": "75"})
|
||
|
||
|
||
# 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(),
|
||
),
|
||
"twilio": lambda: FastAPIWebsocketParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
|
||
logger.info(f"Starting bot")
|
||
|
||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||
|
||
# Configure the mute processor with both strategies
|
||
stt_mute_processor = STTMuteFilter(
|
||
config=STTMuteConfig(
|
||
strategies={
|
||
STTMuteStrategy.MUTE_UNTIL_FIRST_BOT_COMPLETE,
|
||
STTMuteStrategy.FUNCTION_CALL,
|
||
}
|
||
),
|
||
)
|
||
|
||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
|
||
|
||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||
|
||
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"],
|
||
)
|
||
tools = ToolsSchema(standard_tools=[weather_function])
|
||
|
||
messages = [
|
||
{
|
||
"role": "system",
|
||
"content": "You are a helpful assistant who can check the weather. Always check the weather when a location is mentioned. Respond concisely and naturally. Your output will be converted to audio so use only simple words and punctuation.",
|
||
},
|
||
]
|
||
|
||
context = OpenAILLMContext(messages, tools)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt_mute_processor, # Add the mute processor before STT
|
||
stt, # STT
|
||
context_aggregator.user(), # User responses
|
||
llm, # LLM
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(), # Assistant spoken responses
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# Kick off the conversation with a weather-related prompt
|
||
messages.append(
|
||
{
|
||
"role": "system",
|
||
"content": "Ask the user what city they'd like to know the weather for.",
|
||
}
|
||
)
|
||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||
|
||
@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=handle_sigint)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from pipecat.examples.run import main
|
||
|
||
main(run_example, transport_params=transport_params)
|