Pipeline: improve performance by using direct mode

CHANGELOG.md

@@ -38,6 +38,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an issue where `AsyncAITTSService` had very high latency in responding
   by adding `force=true` when sending the flush command.
 
+### Performance
+
+- `Pipeline` performance improvements by using direct mode.
+
 ### Other
 
 - Added `14w-function-calling-mistal.py` using `MistralLLMService`.

src/pipecat/pipeline/base_pipeline.py

@@ -19,9 +19,9 @@ class BasePipeline(FrameProcessor):
     metrics collection from their contained processors.
     """
 
-    def __init__(self):
+    def __init__(self, **kwargs):
         """Initialize the base pipeline."""
-        super().__init__()
+        super().__init__(**kwargs)
 
     @abstractmethod
     def processors_with_metrics(self) -> List[FrameProcessor]:

src/pipecat/pipeline/pipeline.py

@@ -98,7 +98,7 @@ class Pipeline(BasePipeline):
         Args:
             processors: List of frame processors to connect in sequence.
         """
-        super().__init__()
+        super().__init__(enable_direct_mode=True)
 
         # Add a source and a sink queue so we can forward frames upstream and
         # downstream outside of the pipeline.