155 lines
5.2 KiB
Python
155 lines
5.2 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
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.services.anthropic.llm import AnthropicLLMService
|
||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.llm_service import FunctionCallParams
|
||
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 get_weather(params: FunctionCallParams):
|
||
location = params.arguments["location"]
|
||
await params.result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
|
||
|
||
|
||
async def fetch_restaurant_recommendation(params: FunctionCallParams):
|
||
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(),
|
||
),
|
||
"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"))
|
||
|
||
tts = CartesiaTTSService(
|
||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||
)
|
||
|
||
llm = AnthropicLLMService(
|
||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||
model="claude-3-7-sonnet-latest",
|
||
)
|
||
llm.register_function("get_weather", get_weather)
|
||
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
|
||
|
||
weather_function = FunctionSchema(
|
||
name="get_weather",
|
||
description="Get the current weather",
|
||
properties={
|
||
"location": {
|
||
"type": "string",
|
||
"description": "The city and state, e.g. San Francisco, CA",
|
||
},
|
||
},
|
||
required=["location"],
|
||
)
|
||
restaurant_function = FunctionSchema(
|
||
name="get_restaurant_recommendation",
|
||
description="Get a restaurant recommendation",
|
||
properties={
|
||
"location": {
|
||
"type": "string",
|
||
"description": "The city and state, e.g. San Francisco, CA",
|
||
},
|
||
},
|
||
required=["location"],
|
||
)
|
||
tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
|
||
|
||
# todo: test with very short initial user message
|
||
|
||
# messages = [{"role": "system",
|
||
# "content": "You are a helpful assistant who can report the weather in any location in the universe. Respond concisely. Your response will be turned into speech so use only simple words and punctuation."},
|
||
# {"role": "user",
|
||
# "content": " Start the conversation by introducing yourself."}]
|
||
|
||
messages = [{"role": "user", "content": "Say 'hello' to start the conversation."}]
|
||
|
||
context = OpenAILLMContext(messages, tools)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
stt,
|
||
context_aggregator.user(), # User spoken responses
|
||
llm, # LLM
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(), # Assistant spoken responses and tool context
|
||
]
|
||
)
|
||
|
||
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.
|
||
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)
|