140 lines
4.8 KiB
Python
140 lines
4.8 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import asyncio
|
||
import os
|
||
import sys
|
||
|
||
import aiohttp
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
from openai.types.chat import ChatCompletionToolParam
|
||
from runner import configure
|
||
|
||
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.services.azure import AzureLLMService
|
||
from pipecat.services.cartesia import CartesiaTTSService
|
||
from pipecat.services.openai import OpenAILLMContext
|
||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||
|
||
load_dotenv(override=True)
|
||
|
||
logger.remove(0)
|
||
logger.add(sys.stderr, level="DEBUG")
|
||
|
||
|
||
async def start_fetch_weather(function_name, llm, context):
|
||
"""Push a frame to the LLM; this is handy when the LLM response might take a while."""
|
||
await llm.push_frame(TTSSpeakFrame("Let me check on that."))
|
||
logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
|
||
|
||
|
||
async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
|
||
await result_callback({"conditions": "nice", "temperature": "75"})
|
||
|
||
|
||
async def main():
|
||
async with aiohttp.ClientSession() as session:
|
||
(room_url, token) = await configure(session)
|
||
|
||
transport = DailyTransport(
|
||
room_url,
|
||
token,
|
||
"Respond bot",
|
||
DailyParams(
|
||
audio_out_enabled=True,
|
||
transcription_enabled=True,
|
||
vad_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
)
|
||
|
||
tts = CartesiaTTSService(
|
||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
|
||
)
|
||
|
||
llm = AzureLLMService(
|
||
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
|
||
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
|
||
model=os.getenv("AZURE_CHATGPT_MODEL"),
|
||
)
|
||
# Register a function_name of None to get all functions
|
||
# sent to the same callback with an additional function_name parameter.
|
||
llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
|
||
|
||
tools = [
|
||
ChatCompletionToolParam(
|
||
type="function",
|
||
function={
|
||
"name": "get_current_weather",
|
||
"description": "Get the current weather",
|
||
"parameters": {
|
||
"type": "object",
|
||
"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 users location.",
|
||
},
|
||
},
|
||
"required": ["location", "format"],
|
||
},
|
||
},
|
||
)
|
||
]
|
||
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 converted to audio so don't include special characters in your answers. 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(),
|
||
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,
|
||
),
|
||
)
|
||
|
||
@transport.event_handler("on_first_participant_joined")
|
||
async def on_first_participant_joined(transport, participant):
|
||
await transport.capture_participant_transcription(participant["id"])
|
||
# Kick off the conversation.
|
||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||
|
||
runner = PipelineRunner()
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|