143 lines
4.7 KiB
Python
143 lines
4.7 KiB
Python
#
|
|
# Copyright (c) 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.frames.frames import TTSSpeakFrame
|
|
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.cartesia.tts import CartesiaTTSService
|
|
from pipecat.services.deepgram.stt import DeepgramSTTService
|
|
from pipecat.services.deepseek.llm import DeepSeekLLMService
|
|
from pipecat.transports.base_transport import TransportParams
|
|
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
|
|
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
|
|
|
|
load_dotenv(override=True)
|
|
|
|
|
|
async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
|
|
await llm.push_frame(TTSSpeakFrame("Let me check on that."))
|
|
await result_callback({"conditions": "nice", "temperature": "75"})
|
|
|
|
|
|
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
|
|
logger.info(f"Starting bot")
|
|
|
|
transport = SmallWebRTCTransport(
|
|
webrtc_connection=webrtc_connection,
|
|
params=TransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
vad_analyzer=SileroVADAnalyzer(),
|
|
),
|
|
)
|
|
|
|
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 = DeepSeekLLMService(api_key=os.getenv("DEEPSEEK_API_KEY"), model="deepseek-chat")
|
|
# You can also register a function_name of None to get all functions
|
|
# sent to the same callback with an additional function_name parameter.
|
|
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 LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
|
|
|
|
You have one functions available:
|
|
|
|
1. get_current_weather is used to get current weather information.
|
|
|
|
Infer whether to use Fahrenheit or Celsius automatically based on the location, unless the user specifies a preference.
|
|
|
|
Start by asking me for my location. Then, use 'get_weather_current' to give me a forecast.
|
|
|
|
Respond to what the user said in a creative and helpful way.""",
|
|
},
|
|
]
|
|
|
|
context = OpenAILLMContext(messages, tools)
|
|
context_aggregator = llm.create_context_aggregator(context)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
stt,
|
|
context_aggregator.user(),
|
|
llm,
|
|
tts,
|
|
transport.output(),
|
|
context_aggregator.assistant(),
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
allow_interruptions=True,
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
report_only_initial_ttfb=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")
|
|
|
|
@transport.event_handler("on_client_closed")
|
|
async def on_client_closed(transport, client):
|
|
logger.info(f"Client closed connection")
|
|
await task.cancel()
|
|
|
|
runner = PipelineRunner(handle_sigint=False)
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from run import main
|
|
|
|
main()
|