cleaned up example logging (#46)

This commit is contained in:
chadbailey59
2024-03-08 15:25:17 -06:00
committed by GitHub
parent 95a1efbe75
commit 8241dc0bed
20 changed files with 410 additions and 274 deletions

View File

@@ -1,23 +1,29 @@
import argparse
import asyncio
import os
import logging
from typing import AsyncGenerator
import aiohttp
import requests
import time
import urllib.parse
from PIL import Image
from dailyai.pipeline.frames import ImageFrame, Frame
from dailyai.pipeline.frames import ImageFrame, Frame
from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
from dailyai.services.ai_services import AIService
from dailyai.pipeline.aggregators import LLMAssistantContextAggregator, LLMUserContextAggregator
from dailyai.pipeline.aggregators import (
LLMAssistantContextAggregator,
LLMUserContextAggregator,
)
from dailyai.services.fal_ai_services import FalImageGenService
from examples.support.runner import configure
logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
logger = logging.getLogger("dailyai")
logger.setLevel(logging.DEBUG)
class ImageSyncAggregator(AIService):
def __init__(self, speaking_path: str, waiting_path: str):
@@ -50,15 +56,18 @@ async def main(room_url: str, token):
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
model=os.getenv("AZURE_CHATGPT_MODEL"))
model=os.getenv("AZURE_CHATGPT_MODEL"),
)
tts = AzureTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"))
region=os.getenv("AZURE_SPEECH_REGION"),
)
img = FalImageGenService(
image_size="1024x1024",
aiohttp_session=session,
key_id=os.getenv("FAL_KEY_ID"),
key_secret=os.getenv("FAL_KEY_SECRET"))
key_secret=os.getenv("FAL_KEY_SECRET"),
)
async def get_images():
get_speaking_task = asyncio.create_task(
@@ -80,12 +89,13 @@ async def main(room_url: str, token):
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."},
{
"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_in = LLMUserContextAggregator(messages, transport._my_participant_id)
tma_out = LLMAssistantContextAggregator(
messages, transport._my_participant_id
)
@@ -96,14 +106,8 @@ async def main(room_url: str, token):
await tts.run_to_queue(
transport.send_queue,
image_sync_aggregator.run(
tma_out.run(
llm.run(
tma_in.run(
transport.get_receive_frames()
)
)
)
)
tma_out.run(llm.run(tma_in.run(transport.get_receive_frames())))
),
)
transport.transcription_settings["extra"]["punctuate"] = True