starting on interruptions

This commit is contained in:
Moishe Lettvin
2024-03-04 13:41:28 -05:00
parent 18e7626b9f
commit d3f86dab2e
3 changed files with 70 additions and 33 deletions

View File

@@ -5,8 +5,8 @@ from dailyai.pipeline.pipeline import Pipeline
from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
from dailyai.services.ai_services import FrameLogger
from dailyai.pipeline.aggregators import LLMAssistantContextAggregator, LLMContextAggregator, LLMUserContextAggregator
from support.runner import configure
from dailyai.pipeline.aggregators import LLMAssistantContextAggregator, LLMUserContextAggregator
from examples.foundational.support.runner import configure
async def main(room_url: str, token):
@@ -46,8 +46,6 @@ async def main(room_url: str, token):
tma_in = LLMUserContextAggregator(messages, transport._my_participant_id)
tma_out = LLMAssistantContextAggregator(messages, transport._my_participant_id)
pipeline = Pipeline(
source=transport.receive_queue,
sink=transport.send_queue,
processors=[
fl,
tma_in,
@@ -57,7 +55,7 @@ async def main(room_url: str, token):
tts
],
)
await pipeline.run_pipeline()
await transport.run_pipeline(pipeline)
transport.transcription_settings["extra"]["endpointing"] = True
transport.transcription_settings["extra"]["punctuate"] = True

View File

@@ -2,8 +2,11 @@ import asyncio
import aiohttp
import os
from dailyai.conversation_wrappers import InterruptibleConversationWrapper
from dailyai.pipeline.aggregators import LLMAssistantContextAggregator, LLMUserContextAggregator
from dailyai.pipeline.frames import StartStreamQueueFrame, TextQueueFrame
from dailyai.pipeline.pipeline import Pipeline
from dailyai.services.ai_services import FrameLogger
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
@@ -32,17 +35,7 @@ async def main(room_url: str, token):
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"))
async def run_response(user_speech, tma_in, tma_out):
await tts.run_to_queue(
transport.send_queue,
tma_out.run(
llm.run(
tma_in.run(
[StartStreamQueueFrame(), TextQueueFrame(user_speech)]
)
)
),
)
pipeline = Pipeline([FrameLogger(), llm, FrameLogger(), tts])
@transport.event_handler("on_first_other_participant_joined")
async def on_first_other_participant_joined(transport):
@@ -53,14 +46,15 @@ async def main(room_url: str, token):
{"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."},
]
conversation_wrapper = InterruptibleConversationWrapper(
frame_generator=transport.get_receive_frames,
runner=run_response,
interrupt=transport.interrupt,
my_participant_id=transport._my_participant_id,
llm_messages=messages,
await transport.run_interruptible_pipeline(
pipeline,
post_processor=LLMAssistantContextAggregator(
messages, transport._my_participant_id
),
pre_processor=LLMUserContextAggregator(
messages, transport._my_participant_id, complete_sentences=False
),
)
await conversation_wrapper.run_conversation()
transport.transcription_settings["extra"]["punctuate"] = False
await asyncio.gather(transport.run(), run_conversation())