246 lines
7.8 KiB
Python
246 lines
7.8 KiB
Python
#
|
||
# Copyright (c) 2024–2025, Daily
|
||
#
|
||
# SPDX-License-Identifier: BSD 2-Clause License
|
||
#
|
||
|
||
"""simple_dialout.py.
|
||
|
||
Simple Dial-out Bot.
|
||
"""
|
||
|
||
import argparse
|
||
import asyncio
|
||
import json
|
||
import os
|
||
import sys
|
||
from typing import Any
|
||
|
||
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.services.cartesia.tts import CartesiaTTSService
|
||
from pipecat.services.openai.llm import OpenAILLMService
|
||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||
|
||
load_dotenv(override=True)
|
||
|
||
logger.remove(0)
|
||
logger.add(sys.stderr, level="DEBUG")
|
||
|
||
daily_api_key = os.getenv("DAILY_API_KEY", "")
|
||
daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
|
||
|
||
|
||
async def run_bot(
|
||
room_url: str,
|
||
token: str,
|
||
body: dict,
|
||
) -> None:
|
||
"""Run the voice bot with the given parameters.
|
||
|
||
Args:
|
||
room_url: The Daily room URL
|
||
token: The Daily room token
|
||
body: Body passed to the bot from the webhook
|
||
|
||
"""
|
||
# ------------ CONFIGURATION AND SETUP ------------
|
||
logger.info(f"Starting bot with room: {room_url}")
|
||
logger.info(f"Token: {token}")
|
||
logger.info(f"Body: {body}")
|
||
# Parse the body to get the dial-in settings
|
||
body_data = json.loads(body)
|
||
|
||
# Check if the body contains dial-in settings
|
||
logger.debug(f"Body data: {body_data}")
|
||
|
||
if not body_data.get("dialout_settings"):
|
||
logger.error("Dial-out settings not found in the body data")
|
||
return
|
||
|
||
dialout_settings = body_data["dialout_settings"]
|
||
|
||
if not dialout_settings.get("phone_number"):
|
||
logger.error("Dial-out phone number not found in the dial-out settings")
|
||
return
|
||
|
||
# Extract dial-out phone number
|
||
phone_number = dialout_settings["phone_number"]
|
||
caller_id = dialout_settings.get("caller_id") # Use .get() to handle optional field
|
||
|
||
if caller_id:
|
||
logger.info(f"Dial-out caller ID specified: {caller_id}")
|
||
else:
|
||
logger.info("Dial-out caller ID not specified; proceeding without it")
|
||
|
||
# ------------ TRANSPORT SETUP ------------
|
||
|
||
transport_params = DailyParams(
|
||
api_url=daily_api_url,
|
||
api_key=daily_api_key,
|
||
audio_in_enabled=True,
|
||
audio_out_enabled=True,
|
||
video_out_enabled=False,
|
||
vad_analyzer=SileroVADAnalyzer(),
|
||
transcription_enabled=True,
|
||
)
|
||
|
||
# Initialize transport with Daily
|
||
transport = DailyTransport(
|
||
room_url,
|
||
token,
|
||
"Simple Dial-out Bot",
|
||
transport_params,
|
||
)
|
||
|
||
# Initialize TTS
|
||
tts = CartesiaTTSService(
|
||
api_key=os.getenv("CARTESIA_API_KEY", ""),
|
||
voice_id="b7d50908-b17c-442d-ad8d-810c63997ed9", # Use Helpful Woman voice by default
|
||
)
|
||
|
||
# ------------ LLM AND CONTEXT SETUP ------------
|
||
|
||
# Initialize LLM
|
||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||
|
||
# Create system message and initialize messages list
|
||
messages = [
|
||
{
|
||
"role": "system",
|
||
"content": (
|
||
"You are a friendly phone assistant. Your responses will be read aloud, "
|
||
"so keep them concise and conversational. Avoid special characters or "
|
||
"formatting. Begin by greeting the caller and asking how you can help them today."
|
||
),
|
||
},
|
||
]
|
||
# Initialize LLM context and aggregator
|
||
context = OpenAILLMContext(messages)
|
||
context_aggregator = llm.create_context_aggregator(context)
|
||
|
||
# ------------ PIPELINE SETUP ------------
|
||
|
||
# Build pipeline
|
||
pipeline = Pipeline(
|
||
[
|
||
transport.input(), # Transport user input
|
||
context_aggregator.user(), # User responses
|
||
llm, # LLM
|
||
tts, # TTS
|
||
transport.output(), # Transport bot output
|
||
context_aggregator.assistant(), # Assistant spoken responses
|
||
]
|
||
)
|
||
|
||
# Create pipeline task
|
||
task = PipelineTask(
|
||
pipeline,
|
||
params=PipelineParams(
|
||
enable_metrics=True,
|
||
enable_usage_metrics=True,
|
||
),
|
||
)
|
||
|
||
# ------------ RETRY LOGIC VARIABLES ------------
|
||
max_retries = 5
|
||
retry_count = 0
|
||
dialout_successful = False
|
||
|
||
# Build dialout parameters conditionally
|
||
dialout_params = {"phoneNumber": phone_number}
|
||
if caller_id:
|
||
dialout_params["callerId"] = caller_id
|
||
logger.debug(f"Including caller ID in dialout: {caller_id}")
|
||
|
||
logger.debug(f"Dialout parameters: {dialout_params}")
|
||
|
||
async def attempt_dialout():
|
||
"""Attempt to start dialout with retry logic."""
|
||
nonlocal retry_count, dialout_successful
|
||
|
||
if retry_count < max_retries and not dialout_successful:
|
||
retry_count += 1
|
||
logger.info(
|
||
f"Attempting dialout (attempt {retry_count}/{max_retries}) to: {phone_number}"
|
||
)
|
||
await transport.start_dialout(dialout_params)
|
||
else:
|
||
logger.error(f"Maximum retry attempts ({max_retries}) reached. Giving up on dialout.")
|
||
|
||
# ------------ EVENT HANDLERS ------------
|
||
|
||
@transport.event_handler("on_joined")
|
||
async def on_joined(transport, data):
|
||
# Start initial dialout attempt
|
||
logger.debug(f"Dialout settings detected; starting dialout to number: {phone_number}")
|
||
await attempt_dialout()
|
||
|
||
@transport.event_handler("on_dialout_connected")
|
||
async def on_dialout_connected(transport, data):
|
||
logger.debug(f"Dial-out connected: {data}")
|
||
|
||
@transport.event_handler("on_dialout_answered")
|
||
async def on_dialout_answered(transport, data):
|
||
nonlocal dialout_successful
|
||
logger.debug(f"Dial-out answered: {data}")
|
||
dialout_successful = True # Mark as successful to stop retries
|
||
# Automatically start capturing transcription for the participant
|
||
await transport.capture_participant_transcription(data["sessionId"])
|
||
# The bot will wait to hear the user before the bot speaks
|
||
|
||
@transport.event_handler("on_dialout_error")
|
||
async def on_dialout_error(transport, data: Any):
|
||
logger.error(f"Dial-out error (attempt {retry_count}/{max_retries}): {data}")
|
||
|
||
if retry_count < max_retries:
|
||
logger.info(f"Retrying dialout")
|
||
await attempt_dialout()
|
||
else:
|
||
logger.error(f"All {max_retries} dialout attempts failed. Stopping bot.")
|
||
await task.cancel()
|
||
|
||
@transport.event_handler("on_first_participant_joined")
|
||
async def on_first_participant_joined(transport, participant):
|
||
logger.debug(f"First participant joined: {participant['id']}")
|
||
|
||
@transport.event_handler("on_participant_left")
|
||
async def on_participant_left(transport, participant, reason):
|
||
logger.debug(f"Participant left: {participant}, reason: {reason}")
|
||
await task.cancel()
|
||
|
||
# ------------ RUN PIPELINE ------------
|
||
|
||
runner = PipelineRunner()
|
||
await runner.run(task)
|
||
|
||
|
||
async def main():
|
||
"""Parse command line arguments and run the bot."""
|
||
parser = argparse.ArgumentParser(description="Simple Dial-out Bot")
|
||
parser.add_argument("-u", "--url", type=str, help="Room URL")
|
||
parser.add_argument("-t", "--token", type=str, help="Room Token")
|
||
parser.add_argument("-b", "--body", type=str, help="JSON configuration string")
|
||
|
||
args = parser.parse_args()
|
||
|
||
logger.debug(f"url: {args.url}")
|
||
logger.debug(f"token: {args.token}")
|
||
logger.debug(f"body: {args.body}")
|
||
if not all([args.url, args.token, args.body]):
|
||
logger.error("All arguments (-u, -t, -b) are required")
|
||
parser.print_help()
|
||
sys.exit(1)
|
||
|
||
await run_bot(args.url, args.token, args.body)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|