119 lines
3.7 KiB
Python
119 lines
3.7 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
import argparse
|
||
import os
|
||
|
||
from dotenv import load_dotenv
|
||
from loguru import logger
|
||
from simli import SimliConfig
|
||
|
||
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.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.services.simli.video import SimliVideoService
|
||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||
from pipecat.transports.services.daily import DailyParams
|
||
|
||
load_dotenv(override=True)
|
||
|
||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||
# instantiated. The function will be called when the desired transport gets
|
||
# selected.
|
||
transport_params = {
|
||
"daily": lambda: DailyParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
video_out_enabled=True,
|
||
video_out_is_live=True,
|
||
video_out_width=512,
|
||
video_out_height=512,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
"webrtc": lambda: TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
video_out_enabled=True,
|
||
video_out_is_live=True,
|
||
video_out_width=512,
|
||
video_out_height=512,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
),
|
||
}
|
||
|
||
|
||
async def run_example(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="a167e0f3-df7e-4d52-a9c3-f949145efdab",
|
||
)
|
||
|
||
simli_ai = SimliVideoService(
|
||
SimliConfig(os.getenv("SIMLI_API_KEY"), os.getenv("SIMLI_FACE_ID"))
|
||
)
|
||
|
||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
|
||
|
||
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)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(),
|
||
stt,
|
||
context_aggregator.user(),
|
||
llm,
|
||
tts,
|
||
simli_ai,
|
||
transport.output(),
|
||
context_aggregator.assistant(),
|
||
]
|
||
)
|
||
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
allow_interruptions=True,
|
||
enable_metrics=True,
|
||
),
|
||
)
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def on_client_connected(transport, client):
|
||
logger.info(f"Client connected")
|
||
# Start conversation - empty prompt to let LLM follow system instructions
|
||
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.examples.run import main
|
||
|
||
main(run_example, transport_params=transport_params)
|