145 lines
4.6 KiB
Python
145 lines
4.6 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
import os
|
||
from datetime import datetime
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.adapters.schemas.function_schema import FunctionSchema
|
||
from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||
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.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
|
||
from pipecat.services.llm_service import FunctionCallParams
|
||
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(params: FunctionCallParams):
|
||
temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
|
||
await params.result_callback(
|
||
{
|
||
"conditions": "nice",
|
||
"temperature": temperature,
|
||
"format": params.arguments["format"],
|
||
"timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
|
||
}
|
||
)
|
||
|
||
|
||
system_instruction = """
|
||
You are a helpful assistant who can answer questions and use tools.
|
||
|
||
You have a tool called "get_current_weather" that can be used to get the current weather. If the user asks
|
||
for the weather, call this function.
|
||
"""
|
||
|
||
|
||
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
|
||
logger.info(f"Starting bot")
|
||
|
||
# Initialize the SmallWebRTCTransport with the connection
|
||
transport = SmallWebRTCTransport(
|
||
webrtc_connection=webrtc_connection,
|
||
params=TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
# set stop_secs to something roughly similar to the internal setting
|
||
# of the Multimodal Live api, just to align events. This doesn't really
|
||
# matter because we can only use the Multimodal Live API's phrase
|
||
# endpointing, for now.
|
||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
|
||
),
|
||
)
|
||
|
||
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"],
|
||
)
|
||
search_tool = {"google_search": {}}
|
||
tools = ToolsSchema(
|
||
standard_tools=[weather_function], custom_tools={AdapterType.GEMINI: [search_tool]}
|
||
)
|
||
|
||
llm = GeminiMultimodalLiveLLMService(
|
||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||
system_instruction=system_instruction,
|
||
tools=tools,
|
||
)
|
||
|
||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||
|
||
context = OpenAILLMContext(
|
||
[{"role": "user", "content": "Say hello."}],
|
||
)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(),
|
||
context_aggregator.user(),
|
||
llm,
|
||
transport.output(),
|
||
context_aggregator.assistant(),
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
allow_interruptions=True,
|
||
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")
|
||
|
||
@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()
|