ClearML/clearml-serving
1
0
Fork 0
mirror of https://github.com/clearml/clearml-serving synced 2025-01-31 02:46:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Improve preprocess template docstring

Browse Source
This commit is contained in:
allegroai 2024-01-06 17:58:20 +02:00
parent b42a0b0cfc
commit 4335ebd340
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
clearml_serving/preprocess/preprocess_template.py
View File

@ -26,9 +26,11 @@ class Preprocess(object):
def load(self, local_file_name: str) -> Any: # noqa
"""
Optional: provide loading method for the model
OPTIONAL: provide loading method for the model
useful if we need to load a model in a specific way for the prediction engine to work
REMOVE FUNCTION IF NOT USED
Notice! When used with specific engines (i.e. not Custom)
The returned object will be passed as is to the inference engine,
this means it must not be None, otherwise the endpoint will be ignored!
@ -108,9 +110,11 @@ class Preprocess(object):
collect_custom_statistics_fn: Optional[Callable[[dict], None]],
) -> Any: # noqa
"""
Optional: do something with the actual data, return any type of object.
OPTIONAL: do something with the actual data, return any type of object.
The returned object will be passed as is to the postprocess function engine
REMOVE FUNCTION IF NOT USED
:param data: object as recieved from the preprocessing function
:param state: Use state dict to store data passed to the post-processing function call.
This is a per-request state dict (meaning a dict instance per request)
@ -138,7 +142,7 @@ class Preprocess(object):
data: Optional[dict] = None
) -> Optional[dict]:
"""
NOTICE: This method will be replaced in runtime, by the inference service
NOTICE! This method will be replaced in runtime, by the inference service
Helper method to send model inference requests to the inference service itself.
This is designed to help with model ensemble, model pipelines, etc.