diff --git a/CHANGES.md b/CHANGES.md
index 62e090a87324..e694e0c0d2f3 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -71,6 +71,8 @@
   * Prism is a portable runner that executes each transform independantly, ensuring coders.
   * At this point it supercedes the Go direct runner in functionality. The Go direct runner is now deprecated.
   * See https://github.com/apache/beam/blob/master/sdks/go/pkg/beam/runners/prism/README.md for the goals and features of Prism.
+* Hugging Face Model Handler for RunInference added to Python SDK. ([#26632](https://github.com/apache/beam/pull/26632))
+* Hugging Face Pipelines support for RunInference added to Python SDK. ([#27399](https://github.com/apache/beam/pull/27399))
 
 ## Breaking Changes
 
diff --git a/sdks/python/apache_beam/ml/inference/huggingface_inference.py b/sdks/python/apache_beam/ml/inference/huggingface_inference.py
index 09201d3b080b..57eb86d84820 100644
--- a/sdks/python/apache_beam/ml/inference/huggingface_inference.py
+++ b/sdks/python/apache_beam/ml/inference/huggingface_inference.py
@@ -74,7 +74,8 @@
 
 class PipelineTask(str, Enum):
   """
-  PipelineTask lists all the tasks supported by the Hugging Face Pipelines.
+  PipelineTask defines all the tasks supported by the Hugging Face Pipelines
+  listed at https://huggingface.co/docs/transformers/main_classes/pipelines.
   Only these tasks can be passed to HuggingFacePipelineModelHandler.
   """
   AudioClassification = 'audio-classification'
@@ -626,6 +627,7 @@ def __init__(
     _validate_constructor_args_hf_pipeline(self._task, self._model)
 
   def load_model(self):
+    """Loads and initializes the pipeline for processing."""
     return pipeline(
         task=self._task, model=self._model, **self._load_pipeline_args)
 
@@ -664,6 +666,10 @@ def update_model_path(self, model_path: Optional[str] = None):
     self._model = model_path if model_path else self._model
 
   def get_num_bytes(self, batch: Sequence[str]) -> int:
+    """
+    Returns:
+      The number of bytes of input batch elements.
+    """
     return sum(sys.getsizeof(element) for element in batch)
 
   def batch_elements_kwargs(self):
@@ -673,4 +679,8 @@ def share_model_across_processes(self) -> bool:
     return self._large_model
 
   def get_metrics_namespace(self) -> str:
+    """
+    Returns:
+       A namespace for metrics collected by the RunInference transform.
+    """
     return 'BeamML_HuggingFacePipelineModelHandler'