Fix docstring for sphinx autodoc

src/python/library/tritonclient/_plugin.py

@@ -30,7 +30,8 @@
 
 class InferenceServerClientPlugin(ABC):
     """Every Triton Client Plugin should extend this class.
-    Each plugin needs to implement the `__call__` method.
+    Each plugin needs to implement the :py:meth:`__call__` method.
+
     """
 
     @abstractmethod
@@ -42,5 +43,6 @@ def __call__(self, request):
         ----------
         request : Request
             The request object.
+
         """
         pass

src/python/library/tritonclient/_request.py

@@ -29,7 +29,7 @@
 class Request:
     """A request object.
 
-    Attributes
+    Parameters
     ----------
     headers : dict
         A dictionary containing the request headers.

src/python/library/tritonclient/grpc/__init__.py

@@ -32,6 +32,7 @@
     from tritonclient.utils import *
 
     from .._plugin import InferenceServerClientPlugin
+    from .._request import Request
     from ._client import MAX_GRPC_MESSAGE_SIZE, InferenceServerClient, KeepAliveOptions
     from ._infer_input import InferInput
     from ._infer_result import InferResult
@@ -59,3 +60,14 @@
         "use versions <1.43.0 or >=1.51.1 to avoid leaks "
         "(see https://github.com/grpc/grpc/issues/28513)."
     )
+
+__all__ = [
+    "InferenceServerClientPlugin",
+    "Request",
+    "InferenceServerClient",
+    "InferInput",
+    "InferRequestedOutput",
+    "InferResult",
+    "KeepAliveOptions",
+    "InferenceServerException"
+]

src/python/library/tritonclient/grpc/_client.py

@@ -982,6 +982,7 @@ def update_log_settings(
     ):
         """Update the global log settings.
         Returns the log settings after the update.
+
         Parameters
         ----------
         settings: dict
@@ -1005,11 +1006,13 @@ def update_log_settings(
             InferenceServerExeption with message "Deadline Exceeded" when the
             specified time elapses. The default value is None which means
             client will wait for the response from the server.
+
         Returns
         -------
         dict or protobuf message
             The JSON dict or LogSettingsResponse message holding
             the updated log settings.
+
         Raises
         ------
         InferenceServerException
@@ -1047,6 +1050,7 @@ def update_log_settings(
 
     def get_log_settings(self, headers=None, as_json=False, client_timeout=None):
         """Get the global log settings.
+
         Parameters
         ----------
         headers: dict
@@ -1067,15 +1071,18 @@ def get_log_settings(self, headers=None, as_json=False, client_timeout=None):
             InferenceServerExeption with message "Deadline Exceeded" when the
             specified time elapses. The default value is None which means
             client will wait for the response from the server.
+
         Returns
         -------
         dict or protobuf message
             The JSON dict or LogSettingsResponse message holding
             the log settings.
+
         Raises
         ------
         InferenceServerException
             If unable to get the log settings or has timed out.
+
         """
         metadata = self._get_metadata(headers)
         try:
@@ -1460,14 +1467,14 @@ def infer(
         model_name: str
             The name of the model to run inference.
         inputs : list
-            A list of InferInput objects, each describing data for a input
+            A list of :py:class:`InferInput` objects, each describing data for a input
             tensor required by the model.
         model_version : str
             The version of the model to run inference. The default value
             is an empty string which means then the server will choose
             a version based on the model and internal policy.
         outputs : list
-            A list of InferRequestedOutput objects, each describing how the output
+            A list of :py:class:`InferRequestedOutput` objects, each describing how the output
             data must be returned. If not specified all outputs produced
             by the model will be returned using default settings.
         request_id : str
@@ -1590,12 +1597,12 @@ def async_infer(
         model_name: str
             The name of the model to run inference.
         inputs : list
-            A list of InferInput objects, each describing data for a input
+            A list of :py:class:`InferInput` objects, each describing data for a input
             tensor required by the model.
         callback : function
             Python function that is invoked once the request is completed.
             The function must reserve the last two arguments (result, error)
-            to hold InferResult and InferenceServerException
+            to hold :py:class:`InferResult` and :py:class:`InferenceServerException`
             objects respectively which will be provided to the function when
             executing the callback. The ownership of these objects will be given
             to the user. The 'error' would be None for a successful inference.
@@ -1604,7 +1611,7 @@ def async_infer(
             is an empty string which means then the server will choose
             a version based on the model and internal policy.
         outputs : list
-            A list of InferRequestedOutput objects, each describing how the output
+            A list of :py:class:`InferRequestedOutput` objects, each describing how the output
             data must be returned. If not specified all outputs produced
             by the model will be returned using default settings.
         request_id : str
@@ -1668,13 +1675,13 @@ def async_infer(
             Computations represented by a Future may be yet to be begun,
             ongoing, or have already completed.
 
+            Note
+            ----
             This object can be used to cancel the inference request like
             below:
-            ----------
-            future = async_infer(...)
-            ret = future.cancel()
-            ----------
 
+            >>> future = async_infer(...)
+            >>> ret = future.cancel()
 
         Raises
         ------
@@ -1745,8 +1752,8 @@ def start_stream(
         callback : function
             Python function that is invoked upon receiving response from
             the underlying stream. The function must reserve the last two
-            arguments (result, error) to hold InferResult and
-            InferenceServerException objects respectively
+            arguments (result, error) to hold :py:class:`InferResult` and
+            :py:class:`InferenceServerException` objects respectively
             which will be provided to the function when executing the callback.
             The ownership of these objects will be given to the user. The 'error'
             would be None for a successful inference.
@@ -1830,14 +1837,14 @@ def async_stream_infer(
         model_name: str
             The name of the model to run inference.
         inputs : list
-            A list of InferInput objects, each describing data for a input
+            A list of :py:class:`InferInput` objects, each describing data for a input
             tensor required by the model.
         model_version: str
             The version of the model to run inference. The default value
             is an empty string which means then the server will choose
             a version based on the model and internal policy.
         outputs : list
-            A list of InferRequestedOutput objects, each describing how the output
+            A list of :py:class:`InferRequestedOutput` objects, each describing how the output
             data must be returned. If not specified all outputs produced
             by the model will be returned using default settings.
         request_id : str

src/python/library/tritonclient/grpc/_infer_result.py

@@ -32,7 +32,7 @@
 
 
 class InferResult:
-    """An object of InferResult class holds the response of
+    """An object of :py:class:`InferResult` class holds the response of
     an inference request and provide methods to retrieve
     inference results.
 

src/python/library/tritonclient/grpc/_infer_stream.py

@@ -45,11 +45,13 @@ class _InferStream:
     callback : function
         Python function that is invoked upon receiving response from
         the underlying stream. The function must reserve the last two
-        arguments (result, error) to hold InferResult and
-        InferenceServerException objects respectively which will be
+        arguments (result, error) to hold :py:class:`InferResult` and
+        :py:class:`InferenceServerException` objects respectively which will be
         provided to the function when executing the callback. The
         ownership of these objects will be given to the user. The
         'error' would be None for a successful inference.
+    verbose : bool
+        Enables verbose mode if set True.
     """
 
     def __init__(self, callback, verbose):

src/python/library/tritonclient/grpc/_requested_output.py

@@ -31,7 +31,7 @@
 
 
 class InferRequestedOutput:
-    """An object of InferRequestedOutput class is used to describe a
+    """An object of :py:class:`InferRequestedOutput` class is used to describe a
     requested output tensor for an inference request.
 
     Parameters
@@ -89,7 +89,7 @@ def set_shared_memory(self, region_name, byte_size, offset=0):
 
     def unset_shared_memory(self):
         """Clears the shared memory option set by the last call to
-        InferRequestedOutput.set_shared_memory(). After call to this
+        :py:meth:`InferRequestedOutput.set_shared_memory()`. After call to this
         function requested output will no longer be returned in a
         shared memory region.
         """

src/python/library/tritonclient/grpc/_utils.py

@@ -32,7 +32,7 @@
 
 
 def get_error_grpc(rpc_error):
-    """Convert a gRPC error to an InferenceServerException.
+    """Convert a gRPC error to an :py:class:`InferenceServerException`.
 
     Parameters
     ----------
@@ -51,7 +51,7 @@ def get_error_grpc(rpc_error):
 
 
 def get_cancelled_error(msg=None):
-    """Get InferenceServerException object for a cancelled RPC.
+    """Get :py:class:`InferenceServerException` object for a cancelled RPC.
 
     Returns
     -------
@@ -63,7 +63,7 @@ def get_cancelled_error(msg=None):
 
 
 def raise_error_grpc(rpc_error):
-    """Raise an InferenceServerException from a gRPC error.
+    """Raise an :py:class:`InferenceServerException` from a gRPC error.
 
     Parameters
     ----------