Files
pipecat/examples/foundational/14-function-calling.py
Aleix Conchillo Flaqué bf8c73b25b examples: add 15-switch-voices
2024-06-07 13:12:21 -07:00

141 lines
4.4 KiB
Python

#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import aiohttp
import os
import sys
from pipecat.frames.frames import TextFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMAssistantContextAggregator,
LLMUserContextAggregator,
)
from pipecat.processors.logger import FrameLogger
from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVADAnalyzer
from openai.types.chat import ChatCompletionToolParam
from runner import configure
from loguru import logger
from dotenv import load_dotenv
load_dotenv(override=True)
logger.remove(0)
logger.add(sys.stderr, level="DEBUG")
async def start_fetch_weather(llm):
await llm.push_frame(TextFrame("Let me think."))
async def fetch_weather_from_api(llm, args):
return {"conditions": "nice", "temperature": "75"}
async def main(room_url: str, token):
async with aiohttp.ClientSession() as session:
transport = DailyTransport(
room_url,
token,
"Respond bot",
DailyParams(
audio_out_enabled=True,
transcription_enabled=True,
vad_enabled=True,
vad_analyzer=SileroVADAnalyzer()
)
)
tts = ElevenLabsTTSService(
aiohttp_session=session,
api_key=os.getenv("ELEVENLABS_API_KEY"),
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o")
llm.register_function(
"get_current_weather",
fetch_weather_from_api,
start_callback=start_fetch_weather)
fl_in = FrameLogger("Inner")
fl_out = FrameLogger("Outer")
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)
tma_in = LLMUserContextAggregator(context)
tma_out = LLMAssistantContextAggregator(context)
pipeline = Pipeline([
fl_in,
transport.input(),
tma_in,
llm,
fl_out,
tts,
transport.output(),
tma_out
])
task = PipelineTask(pipeline)
@ transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
transport.capture_participant_transcription(participant["id"])
# Kick off the conversation.
await tts.say("Hi! Ask me about the weather in San Francisco.")
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
(url, token) = configure()
asyncio.run(main(url, token))