fb27642190
- AWSNovaSonicLLMService: new `AWSNovaSonicLLMSettings` with `voice_id` and `endpointing_sensitivity`; remove `self._params` entirely, storing audio I/O config as plain instance variables - NeuphonicHttpTTSService: reuse `NeuphonicTTSSettings`; use inherited `language` field instead of bespoke `lang_code` - NvidiaTTSService: new `NvidiaTTSSettings` with `quality` - PiperTTSService / PiperHttpTTSService: new `PiperTTSSettings` / `PiperHttpTTSSettings` (no extra fields) - SpeechmaticsTTSService: new `SpeechmaticsTTSSettings` with `max_retries` Also remove redundant `lang_code` from `NeuphonicTTSSettings` (both WS and HTTP services now use the inherited `TTSSettings.language` field, with automatic enum conversion via the base class). HTTP services (Neuphonic HTTP, Piper HTTP, Speechmatics) don't override `_update_settings` since the base class applies changes to `self._settings` and subsequent requests read from it automatically.
125 lines
3.9 KiB
Python
125 lines
3.9 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
import asyncio
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
from loguru import logger
|
|
|
|
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
|
from pipecat.frames.frames import LLMRunFrame, LLMUpdateSettingsFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.processors.aggregators.llm_context import LLMContext
|
|
from pipecat.processors.aggregators.llm_response_universal import (
|
|
LLMContextAggregatorPair,
|
|
LLMUserAggregatorParams,
|
|
)
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import create_transport
|
|
from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService, AWSNovaSonicLLMSettings
|
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
from pipecat.transports.daily.transport import DailyParams
|
|
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
|
|
|
load_dotenv(override=True)
|
|
|
|
transport_params = {
|
|
"daily": lambda: DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
"twilio": lambda: FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
logger.info(f"Starting bot")
|
|
|
|
llm = AWSNovaSonicLLMService(
|
|
secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
|
|
access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
|
|
region=os.getenv("AWS_REGION"),
|
|
)
|
|
|
|
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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Tell me a fun fact!",
|
|
},
|
|
]
|
|
|
|
context = LLMContext(messages)
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
|
context,
|
|
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
|
)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
user_aggregator,
|
|
llm,
|
|
transport.output(),
|
|
assistant_aggregator,
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
|
)
|
|
|
|
@transport.event_handler("on_client_connected")
|
|
async def on_client_connected(transport, client):
|
|
logger.info(f"Client connected")
|
|
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
|
await task.queue_frames([LLMRunFrame()])
|
|
|
|
await asyncio.sleep(10)
|
|
logger.info("Updating AWS Nova Sonic LLM settings: temperature=0.1")
|
|
await task.queue_frame(
|
|
LLMUpdateSettingsFrame(update=AWSNovaSonicLLMSettings(temperature=0.1))
|
|
)
|
|
|
|
@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=runner_args.handle_sigint)
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
async def bot(runner_args: RunnerArguments):
|
|
"""Main bot entry point compatible with Pipecat Cloud."""
|
|
transport = await create_transport(runner_args, transport_params)
|
|
await run_bot(transport, runner_args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pipecat.runner.run import main
|
|
|
|
main()
|