examples: update with LLMUserAggregatorParams vad_analyzer and VADProcessor

examples/foundational/26g-gemini-live-groundingMetadata.py

@@ -11,7 +11,10 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -24,27 +27,23 @@ 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.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         video_in_enabled=False,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         video_in_enabled=False,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         video_in_enabled=False,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
     ),
 }
 
@@ -126,7 +125,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Set up conversation context and management
     context = LLMContext(messages)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            # Set stop_secs to something roughly similar to the internal setting
+            # of the Multimodal Live api, just to align events. This doesn't
+            # really matter because we can only use the Multimodal Live API's
+            # phrase endpointing, for now.
+            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5))
+        ),
+    )
 
     pipeline = Pipeline(
         [