save

examples/foundational/17-detect-user-idle.py

@@ -25,7 +25,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.openrouter.llm import OpenRouterLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -67,7 +67,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenRouterLLMService(
+        api_key=os.getenv("OPENROUTER_API_KEY"),
+        model="google/gemini-2.5-flash",
+    )
 
     messages = [
         {

examples/foundational/karumi-17-detect-user-idle.py

@@ -0,0 +1,180 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+from collections import deque
+from math import log
+
+from dotenv import load_dotenv
+from loguru import logger
+from pipecat_whisker import WhiskerObserver
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import EndFrame, LLMMessagesAppendFrame, LLMRunFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.processors.transcript_processor import TranscriptProcessor
+from pipecat.processors.user_idle_processor import UserIdleProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openrouter.llm import OpenRouterLLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    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
+    )
+
+    llm = OpenRouterLLMService(
+        api_key=os.getenv("OPENROUTER_API_KEY"), model="google/gemini-2.5-flash"
+    )
+
+    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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    async def handle_user_idle(user_idle: UserIdleProcessor, retry_count: int) -> bool:
+        if retry_count == 1:
+            # First attempt: Add a gentle prompt to the conversation
+            message = {
+                "role": "user",
+                "content": "The user has been quiet. Politely and briefly ask if they're still there.",
+            }
+            await user_idle.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
+            return True
+        elif retry_count == 2:
+            # Second attempt: More direct prompt
+            message = {
+                "role": "user",
+                "content": "The user is still inactive. Ask if they'd like to continue our conversation.",
+            }
+            await user_idle.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
+            return True
+        else:
+            # Third attempt: End the conversation
+            await user_idle.push_frame(
+                TTSSpeakFrame("It seems like you're busy right now. Have a nice day!")
+            )
+            await task.queue_frame(EndFrame())
+            return False
+
+    user_idle = UserIdleProcessor(callback=handle_user_idle, timeout=5.0)
+    transcript = TranscriptProcessor()
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            user_idle,  # Idle user check-in
+            transcript.user(),
+            context_aggregator.user(),
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),
+            transcript.assistant(),
+        ]
+    )
+
+    whisker = WhiskerObserver(pipeline, file_name="whisker.bin")
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        observers=[whisker],
+    )
+
+    @transport.event_handler("on_app_message")
+    async def on_app_message(transport, message, sender):
+        logger.debug(f"Received app message: {message}")
+        if "message" not in message:
+            return
+
+        message = {
+            "role": "user",
+            "content": f"The user wrote in the chat: {message['message']}",
+        }
+        await user_idle.push_frame(LLMMessagesAppendFrame([message], run_llm=True))
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "user", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()