wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

examples: update with LLMUserAggregatorParams vad_analyzer and VADProcessor

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2026-01-28 11:58:08 -08:00
parent 305ab44132
commit 307aeaeda0
184 changed files with 628 additions and 1028 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
examples/foundational/26d-gemini-live-text.py
View File

@@ -17,7 +17,10 @@ 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.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -44,36 +47,20 @@ Respond to what the user said in a creative and helpful way. Keep your responses
"""
# 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,
# 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)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
# 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)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
# 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)),
),
}
@@ -111,7 +98,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Set up conversation context and management
# The context_aggregator will automatically collect conversation context
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(
[