112 lines
3.3 KiB
Python
112 lines
3.3 KiB
Python
#
|
|
# Copyright (c) 2025, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
import os
|
|
import sys
|
|
|
|
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.serializers.protobuf import ProtobufFrameSerializer
|
|
from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
|
|
from pipecat.transports.network.fastapi_websocket import (
|
|
FastAPIWebsocketParams,
|
|
FastAPIWebsocketTransport,
|
|
)
|
|
|
|
load_dotenv(override=True)
|
|
|
|
logger.remove(0)
|
|
logger.add(sys.stderr, level="DEBUG")
|
|
|
|
|
|
SYSTEM_INSTRUCTION = f"""
|
|
"You are Gemini Chatbot, a friendly, helpful robot.
|
|
|
|
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. Keep your responses brief. One or two sentences at most.
|
|
"""
|
|
|
|
|
|
async def run_bot(websocket_client):
|
|
ws_transport = FastAPIWebsocketTransport(
|
|
websocket=websocket_client,
|
|
params=FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
add_wav_header=False,
|
|
vad_analyzer=SileroVADAnalyzer(),
|
|
serializer=ProtobufFrameSerializer(),
|
|
),
|
|
)
|
|
|
|
llm = GeminiMultimodalLiveLLMService(
|
|
api_key=os.getenv("GOOGLE_API_KEY"),
|
|
voice_id="Puck", # Aoede, Charon, Fenrir, Kore, Puck
|
|
transcribe_model_audio=True,
|
|
system_instruction=SYSTEM_INSTRUCTION,
|
|
)
|
|
|
|
context = OpenAILLMContext(
|
|
[
|
|
{
|
|
"role": "user",
|
|
"content": "Start by greeting the user warmly and introducing yourself.",
|
|
}
|
|
],
|
|
)
|
|
context_aggregator = llm.create_context_aggregator(context)
|
|
|
|
# RTVI events for Pipecat client UI
|
|
rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
ws_transport.input(),
|
|
context_aggregator.user(),
|
|
rtvi,
|
|
llm, # LLM
|
|
ws_transport.output(),
|
|
context_aggregator.assistant(),
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
allow_interruptions=True,
|
|
),
|
|
observers=[RTVIObserver(rtvi)],
|
|
)
|
|
|
|
@rtvi.event_handler("on_client_ready")
|
|
async def on_client_ready(rtvi):
|
|
logger.info("Pipecat client ready.")
|
|
await rtvi.set_bot_ready()
|
|
# Kick off the conversation.
|
|
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
|
|
|
@ws_transport.event_handler("on_client_connected")
|
|
async def on_client_connected(transport, client):
|
|
logger.info("Pipecat Client connected")
|
|
|
|
@ws_transport.event_handler("on_client_disconnected")
|
|
async def on_client_disconnected(transport, client):
|
|
logger.info("Pipecat Client disconnected")
|
|
await task.cancel()
|
|
|
|
runner = PipelineRunner(handle_sigint=False)
|
|
|
|
await runner.run(task)
|