278a2fed56
Is this a service or processor? How to deal with conversation history? LC has sophisticated means of this, but might get in the way of `LLMResponseAggregator`
112 lines
3.6 KiB
Python
112 lines
3.6 KiB
Python
#
|
|
# Copyright (c) 2024, 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 runner import configure
|
|
|
|
from pipecat.frames.frames import LLMMessagesFrame
|
|
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 (
|
|
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
|
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
|
from pipecat.services.langchain import LangchainProcessor
|
|
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
|
from pipecat.vad.silero import SileroVADAnalyzer
|
|
|
|
load_dotenv(override=True)
|
|
|
|
try:
|
|
from langchain.prompts import ChatPromptTemplate
|
|
from langchain_openai import ChatOpenAI
|
|
except ModuleNotFoundError as e:
|
|
logger.exception(
|
|
"You need to `pip install langchain_openai` for this example. Also, be sure to set `OPENAI_API_KEY` in the environment variable."
|
|
)
|
|
raise Exception(f"Missing module: {e}")
|
|
|
|
logger.remove(0)
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
|
|
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 = ChatOpenAI(model="gpt-4o", temperature=0.7)
|
|
prompt = ChatPromptTemplate.from_messages(
|
|
[
|
|
("system",
|
|
"Be nice and helpful. Answer very briefly and without special characters like `#` or `*`. Your response will be synthesized to voice and those characters will create unnatural sounds.",
|
|
),
|
|
("human",
|
|
"{input}"),
|
|
])
|
|
chain = prompt | llm
|
|
lc = LangchainProcessor(chain)
|
|
|
|
tma_in = LLMUserResponseAggregator()
|
|
tma_out = LLMAssistantResponseAggregator()
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(), # Transport user input
|
|
tma_in, # User responses
|
|
lc, # Langchain
|
|
tts, # TTS
|
|
transport.output(), # Transport bot output
|
|
tma_out, # Assistant spoken responses
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(pipeline, allow_interruptions=True)
|
|
|
|
@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.
|
|
# the `LLMMessagesFrame` will be picked up by the LangchainProcessor using
|
|
# only the content of the last message to inject it in the prompt defined
|
|
# above. So no role is required here.
|
|
messages = [(
|
|
{
|
|
"content": "Please briefly introduce yourself to the user."
|
|
}
|
|
)]
|
|
await task.queue_frames([LLMMessagesFrame(messages)])
|
|
|
|
runner = PipelineRunner()
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
(url, token) = configure()
|
|
asyncio.run(main(url, token))
|