examples: websocket-server updates

examples/foundational/websocket-server/server.py

@@ -9,32 +9,37 @@ import asyncio
 import os
 import sys
 
-from loguru import logger
-from pipecat.frames.frames import Frame, TextFrame, TranscriptionFrame
+from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.processors.aggregators.llm_response import LLMAssistantResponseAggregator, LLMUserResponseAggregator
 from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.services.whisper import WhisperSTTService
-from pipecat.transports.network.websocket_server import WebsocketServerTransport
+from pipecat.transports.network.websocket_server import WebsocketServerParams, WebsocketServerTransport
+from pipecat.vad.silero import SileroVAD
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
 
 logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-class WhisperTranscriber(FrameProcessor):
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        if isinstance(frame, TranscriptionFrame):
-            print(f"Transcribed: {frame.text}")
-        else:
-            await self.push_frame(frame, direction)
+logger.add(sys.stderr, level="TRACE")
 
 
 async def main():
     async with aiohttp.ClientSession() as session:
-        transport = WebsocketServerTransport()
+        transport = WebsocketServerTransport(params=WebsocketServerParams(add_wav_header=True))
+
+        vad = SileroVAD(audio_passthrough=True)
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4-turbo-preview")
+
+        stt = WhisperSTTService()
 
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
@@ -42,19 +47,35 @@ async def main():
             voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
         )
 
+        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 so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
         pipeline = Pipeline([
-            transport.input(),
-            WhisperSTTService(),
-            WhisperTranscriber(),
-            tts,
-            transport.output(),
+            transport.input(),   # Websocket input from client
+            vad,                 # VAD to detect user speech
+            stt,                 # Speech-To-Text
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # Text-To-Speech
+            transport.output(),  # Websocket output to client
+            tma_out              # LLM responses
         ])
 
         task = PipelineTask(pipeline)
 
         @transport.event_handler("on_client_connected")
         async def on_client_connected(transport, client):
-            await task.queue_frame(TextFrame("Hello there!"))
+            # Kick off the conversation.
+            messages.append(
+                {"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
 
         runner = PipelineRunner()