120 lines
3.5 KiB
Python
120 lines
3.5 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
"""Pipecat Quickstart Example.
|
||
|
||
The example runs a simple voice AI bot that you can connect to using your
|
||
browser and speak with it.
|
||
|
||
Required AI services:
|
||
- Deepgram (Speech-to-Text)
|
||
- OpenAI (LLM)
|
||
- Cartesia (Text-to-Speech)
|
||
|
||
The example connects between client and server using a P2P WebRTC connection.
|
||
|
||
Run the bot using::
|
||
|
||
python bot.py
|
||
"""
|
||
|
||
import argparse
|
||
import os
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
|
||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||
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.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
|
||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
|
||
async def run_bot(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
|
||
logger.info(f"Starting bot")
|
||
|
||
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 = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
|
||
messages = [
|
||
{
|
||
"role": "system",
|
||
"content": "You are a friendly AI assistant. Respond naturally and keep your answers conversational.",
|
||
},
|
||
]
|
||
|
||
context = OpenAILLMContext(messages)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
rtvi, # RTVI processor
|
||
stt,
|
||
context_aggregator.user(), # User responses
|
||
llm, # LLM
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(), # Assistant spoken responses
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
observers=[RTVIObserver(rtvi)],
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# Kick off the conversation.
|
||
messages.append({"role": "system", "content": "Say hello and briefly introduce yourself."})
|
||
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")
|
||
await task.cancel()
|
||
|
||
runner = PipelineRunner(handle_sigint=handle_sigint)
|
||
|
||
await runner.run(task)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
from pipecat.runner.local import main
|
||
|
||
# SmallWebRTCTransport for a P2P WebRTC connection
|
||
transport_params = {
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
}
|
||
|
||
main(run_bot, transport_params=transport_params)
|