initial commit for new pipecat architecture

examples/foundational/04-utterance-and-speech.py

@@ -1,37 +1,40 @@
-import asyncio
-import logging
-import os
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
 
 import aiohttp
-from dailyai.pipeline.merge_pipeline import SequentialMergePipeline
-from dailyai.pipeline.pipeline import Pipeline
+import asyncio
+import os
+import sys
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.services.deepgram_ai_services import DeepgramTTSService
-from dailyai.pipeline.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
+from pipecat.pipeline.pipeline import Pipeline
+
+from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.azure import AzureLLMService, AzureTTSService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.transport_services import TransportServiceOutput
+from pipecat.services.transports.daily_transport import DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 async def main(room_url: str):
     async with aiohttp.ClientSession() as session:
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Static And Dynamic Speech",
-            duration_minutes=1,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-        )
+        transport = DailyTransport(room_url, None, "Static And Dynamic Speech")
+
+        meeting = TransportServiceOutput(transport, mic_enabled=True)
 
         llm = AzureLLMService(
             api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
@@ -43,10 +46,6 @@ async def main(room_url: str):
             region=os.getenv("AZURE_SPEECH_REGION"),
         )
 
-        deepgram_tts = DeepgramTTSService(
-            aiohttp_session=session,
-            api_key=os.getenv("DEEPGRAM_API_KEY"),
-        )
         elevenlabs_tts = ElevenLabsTTSService(
             aiohttp_session=session,
             api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -56,11 +55,13 @@ async def main(room_url: str):
         messages = [{"role": "system",
                      "content": "tell the user a joke about llamas"}]
 
-        # Start a task to run the LLM to create a joke, and convert the LLM output to audio frames. This task
-        # will run in parallel with generating and speaking the audio for static text, so there's no delay to
-        # speak the LLM response.
+        # Start a task to run the LLM to create a joke, and convert the LLM
+        # output to audio frames. This task will run in parallel with generating
+        # and speaking the audio for static text, so there's no delay to speak
+        # the LLM response.
         llm_pipeline = Pipeline([llm, elevenlabs_tts])
-        await llm_pipeline.queue_frames([LLMMessagesFrame(messages), EndPipeFrame()])
+        llm_task = PipelineTask(llm_pipeline)
+        await llm_task.queue_frames([LLMMessagesFrame(messages), EndPipeFrame()])
 
         simple_tts_pipeline = Pipeline([azure_tts])
         await simple_tts_pipeline.queue_frames(