WIP: environment cleanup (#19)
* removed env var usage from SDK services * started consolidating configure.py * 1–3 work * cleaned up the rest * more cleanup * cleanup and 05 tinkering * made fal keys optional
This commit is contained in:
chadbailey59
@@ -1,19 +1,19 @@
|
||||
import argparse
|
||||
import aiohttp
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
import wave
|
||||
import requests
|
||||
import time
|
||||
import urllib.parse
|
||||
|
||||
from dailyai.services.daily_transport_service import DailyTransportService
|
||||
from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
|
||||
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
|
||||
from dailyai.queue_aggregators import LLMContextAggregator, LLMUserContextAggregator, LLMAssistantContextAggregator
|
||||
from dailyai.services.ai_services import AIService, FrameLogger
|
||||
from dailyai.queue_frame import QueueFrame, AudioQueueFrame, LLMResponseEndQueueFrame, LLMMessagesQueueFrame
|
||||
from typing import AsyncGenerator
|
||||
|
||||
from samples.foundational.support.runner import configure
|
||||
|
||||
logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s") # or whatever
|
||||
logger = logging.getLogger("dailyai")
|
||||
logger.setLevel(logging.DEBUG)
|
||||
@@ -64,52 +64,56 @@ class InboundSoundEffectWrapper(AIService):
|
||||
|
||||
|
||||
async def main(room_url: str, token):
|
||||
global transport
|
||||
global llm
|
||||
global tts
|
||||
async with aiohttp.ClientSession() as session:
|
||||
|
||||
transport = DailyTransportService(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
5,
|
||||
)
|
||||
transport.mic_enabled = True
|
||||
transport.mic_sample_rate = 16000
|
||||
transport.camera_enabled = False
|
||||
global transport
|
||||
global llm
|
||||
global tts
|
||||
|
||||
llm = AzureLLMService()
|
||||
tts = AzureTTSService()
|
||||
|
||||
@transport.event_handler("on_first_other_participant_joined")
|
||||
async def on_first_other_participant_joined(transport):
|
||||
await tts.say("Hi, I'm listening!", transport.send_queue)
|
||||
await transport.send_queue.put(AudioQueueFrame(sounds["ding1.wav"]))
|
||||
async def handle_transcriptions():
|
||||
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. Respond to what the user said in a creative and helpful way."},
|
||||
]
|
||||
|
||||
tma_in = LLMUserContextAggregator(
|
||||
messages, transport.my_participant_id
|
||||
transport = DailyTransportService(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
5,
|
||||
)
|
||||
tma_out = LLMAssistantContextAggregator(
|
||||
messages, transport.my_participant_id
|
||||
)
|
||||
out_sound = OutboundSoundEffectWrapper()
|
||||
in_sound = InboundSoundEffectWrapper()
|
||||
fl = FrameLogger("LLM Out")
|
||||
fl2 = FrameLogger("Transcription In")
|
||||
await out_sound.run_to_queue(
|
||||
transport.send_queue,
|
||||
tts.run(
|
||||
fl.run(
|
||||
tma_out.run(
|
||||
llm.run(
|
||||
fl2.run(
|
||||
in_sound.run(
|
||||
tma_in.run(
|
||||
transport.get_receive_frames()
|
||||
transport.mic_enabled = True
|
||||
transport.mic_sample_rate = 16000
|
||||
transport.camera_enabled = False
|
||||
|
||||
llm = AzureLLMService(api_key=os.getenv("AZURE_CHATGPT_API_KEY"), endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"), model=os.getenv("AZURE_CHATGPT_MODEL"))
|
||||
tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id="ErXwobaYiN019PkySvjV")
|
||||
|
||||
|
||||
@transport.event_handler("on_first_other_participant_joined")
|
||||
async def on_first_other_participant_joined(transport):
|
||||
await tts.say("Hi, I'm listening!", transport.send_queue)
|
||||
await transport.send_queue.put(AudioQueueFrame(sounds["ding1.wav"]))
|
||||
async def handle_transcriptions():
|
||||
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. Respond to what the user said in a creative and helpful way."},
|
||||
]
|
||||
|
||||
tma_in = LLMUserContextAggregator(
|
||||
messages, transport.my_participant_id
|
||||
)
|
||||
tma_out = LLMAssistantContextAggregator(
|
||||
messages, transport.my_participant_id
|
||||
)
|
||||
out_sound = OutboundSoundEffectWrapper()
|
||||
in_sound = InboundSoundEffectWrapper()
|
||||
fl = FrameLogger("LLM Out")
|
||||
fl2 = FrameLogger("Transcription In")
|
||||
await out_sound.run_to_queue(
|
||||
transport.send_queue,
|
||||
tts.run(
|
||||
fl.run(
|
||||
tma_out.run(
|
||||
llm.run(
|
||||
fl2.run(
|
||||
in_sound.run(
|
||||
tma_in.run(
|
||||
transport.get_receive_frames()
|
||||
)
|
||||
)
|
||||
)
|
||||
)
|
||||
@@ -117,43 +121,12 @@ async def main(room_url: str, token):
|
||||
)
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
|
||||
transport.transcription_settings["extra"]["punctuate"] = True
|
||||
await asyncio.gather(transport.run(), handle_transcriptions())
|
||||
transport.transcription_settings["extra"]["punctuate"] = True
|
||||
await asyncio.gather(transport.run(), handle_transcriptions())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
|
||||
parser.add_argument(
|
||||
"-u", "--url", type=str, required=True, help="URL of the Daily room to join"
|
||||
)
|
||||
parser.add_argument(
|
||||
"-k",
|
||||
"--apikey",
|
||||
type=str,
|
||||
required=True,
|
||||
help="Daily API Key (needed to create token)",
|
||||
)
|
||||
|
||||
args, unknown = parser.parse_known_args()
|
||||
|
||||
# Create a meeting token for the given room with an expiration 1 hour in the future.
|
||||
room_name: str = urllib.parse.urlparse(args.url).path[1:]
|
||||
expiration: float = time.time() + 60 * 60
|
||||
|
||||
res: requests.Response = requests.post(
|
||||
f"https://api.daily.co/v1/meeting-tokens",
|
||||
headers={"Authorization": f"Bearer {args.apikey}"},
|
||||
json={
|
||||
"properties": {"room_name": room_name, "is_owner": True, "exp": expiration}
|
||||
},
|
||||
)
|
||||
|
||||
if res.status_code != 200:
|
||||
raise Exception(f"Failed to create meeting token: {res.status_code} {res.text}")
|
||||
|
||||
token: str = res.json()["token"]
|
||||
|
||||
asyncio.run(main(args.url, token))
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
Reference in New Issue
Block a user