Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt (#1534)

Co-authored-by: Filipi Fuchter <filipi@daily.co>

examples/foundational/10-wake-phrase.py

@@ -4,89 +4,99 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Robot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
+        },
+    ]
+
+    hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            hey_robot_filter,  # Filter out speech not directed at the robot
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
+    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frame(TTSSpeakFrame("Hi! If you want to talk to me, just say 'Hey Robot'"))
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                hey_robot_filter,  # Filter out speech not directed at the robot
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            await tts.say("Hi! If you want to talk to me, just say 'Hey Robot'.")
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()