Update kserve sdk examples with renamed classes (kubeflow#1966)

* Update kserve sdk examples

Signed-off-by: Mark Winter <mark.winter@navercorp.com>

* Better var names

Signed-off-by: Mark Winter <mark.winter@navercorp.com>

* Update READMEs

Signed-off-by: Mark Winter <mark.winter@navercorp.com>

docs/samples/explanation/aif/germancredit/server/model.py

@@ -6,7 +6,7 @@
 from aif360.algorithms.preprocessing.optim_preproc_helpers.data_preproc_functions import load_preproc_data_german
 
 
-class KServeSampleModel(kserve.KFModel):
+class KServeSampleModel(kserve.Model):
     def __init__(self, name: str):
         super().__init__(name)
         self.name = name
@@ -39,4 +39,4 @@ def predict(self, request: Dict) -> Dict:
 if __name__ == "__main__":
     model = KServeSampleModel("german-credit")
     model.load()
-    kserve.KFServer(workers=1).start([model])
+    kserve.ModelServer(workers=1).start([model])

docs/samples/explanation/aix/mnist/rfserver/rfserver/__main__.py

@@ -18,12 +18,12 @@
 
 DEFAULT_MODEL_NAME = "rfserver"
 
-parser = argparse.ArgumentParser(parents=[kserve.kfserver.parser])
+parser = argparse.ArgumentParser(parents=[kserve.model_server.parser])
 parser.add_argument('--model_name', default=DEFAULT_MODEL_NAME,
                     help='The name that the model is served under.')
 args, _ = parser.parse_known_args()
 
 if __name__ == "__main__":
     model = RFModel(args.model_name)
     model.load()
-    kserve.KFServer().start([model])
+    kserve.ModelServer().start([model])

docs/samples/explanation/aix/mnist/rfserver/rfserver/model.py

@@ -33,7 +33,7 @@ def transform(self, X):
         return self._step_func(X)
 
 
-class RFModel(kserve.KFModel):  # pylint:disable=c-extension-no-member
+class RFModel(kserve.Model):  # pylint:disable=c-extension-no-member
     def __init__(self, name: str):
         super().__init__(name)
         self.name = name

docs/samples/explanation/aix/mnist/rfserver/setup.py

@@ -25,7 +25,7 @@
     license='https://github.com/kserve/kserve/LICENSE',
     url='https://github.com/kserve/kserve/python/rfserver',
     description='Model Server implementation for AI eXplainability using LIME. \
-                 Not intended for use outside KFServing Frameworks Images',
+                 Not intended for use outside KServe Frameworks Images',
     long_description=open('README.md').read(),
     python_requires='>3.4',
     packages=find_packages("rfserver"),

docs/samples/explanation/art/mnist/sklearnserver/setup.py

@@ -26,7 +26,7 @@
     license='https://github.com/kserve/kserve/LICENSE',
     url='https://github.com/kserve/kserve/python/sklearnserver',
     description='Model Server implementation for scikit-learn. \
-                 Not intended for use outside KFServing Frameworks Images',
+                 Not intended for use outside KServe Frameworks Images',
     long_description=open('README.md').read(),
     python_requires='>3.4',
     packages=find_packages("sklearnserver"),

docs/samples/explanation/art/mnist/sklearnserver/sklearnserver/__main__.py

@@ -16,13 +16,13 @@
 import sys
 
 import kserve
-from .kfserver import KFServer
+from .kfserver import ModelServer
 from sklearnserver import SKLearnModel, SKLearnModelRepository
 
 DEFAULT_MODEL_NAME = "model"
 DEFAULT_LOCAL_MODEL_DIR = "/tmp/model"
 
-parser = argparse.ArgumentParser(parents=[kserve.kfserver.parser])
+parser = argparse.ArgumentParser(parents=[kserve.model_server.parser])
 parser.add_argument('--model_dir', required=True,
                     help='A URI pointer to the model binary')
 parser.add_argument('--model_name', default=DEFAULT_MODEL_NAME,
@@ -38,4 +38,4 @@
         logging.error(f"fail to load model {args.model_name} from dir {args.model_dir}. "
                       f"exception type {ex_type}, exception msg: {ex_value}")
         model.ready = False
-    KFServer(registered_models=SKLearnModelRepository(args.model_dir)).start([model] if model.ready else [])
+    ModelServer(registered_models=SKLearnModelRepository(args.model_dir)).start([model] if model.ready else [])

docs/samples/explanation/art/mnist/sklearnserver/sklearnserver/http.py

@@ -15,11 +15,11 @@
 import tornado.web
 import json
 from http import HTTPStatus
-from .kfmodel_repository import KFModelRepository
+from .model_repository import ModelRepository
 
 
 class HTTPHandler(tornado.web.RequestHandler):
-    def initialize(self, models: KFModelRepository):
+    def initialize(self, models: ModelRepository):
         self.models = models  # pylint:disable=attribute-defined-outside-init
 
     def get_model(self, name: str):

docs/samples/explanation/art/mnist/sklearnserver/sklearnserver/kfmodel_repository.py

@@ -12,12 +12,12 @@
 # limitations under the License.
 
 from typing import List, Optional
-from kserve import KFModel
+from kserve import Model
 
 MODEL_MOUNT_DIRS = "/mnt/models"
 
 
-class KFModelRepository:
+class ModelRepository:
     """
     Model repository interface, follows NVIDIA Triton's `model-repository`
     extension.
@@ -30,17 +30,17 @@ def __init__(self, models_dir: str = MODEL_MOUNT_DIRS):
     def set_models_dir(self, models_dir):  # used for unit tests
         self.models_dir = models_dir
 
-    def get_model(self, name: str) -> Optional[KFModel]:
+    def get_model(self, name: str) -> Optional[Model]:
         return self.models.get(name, None)
 
-    def get_models(self) -> List[KFModel]:
+    def get_models(self) -> List[Model]:
         return list(self.models.values())
 
     def is_model_ready(self, name: str):
         model = self.get_model(name)
         return False if model is None else model.ready
 
-    def update(self, model: KFModel):
+    def update(self, model: Model):
         self.models[model.name] = model
 
     def load(self, name: str) -> bool:

docs/samples/explanation/art/mnist/sklearnserver/sklearnserver/kfserver.py

@@ -23,8 +23,8 @@
 import tornado.log
 
 from .http import PredictHandler, ExplainHandler
-from kserve import KFModel
-from .kfmodel_repository import KFModelRepository
+from kserve import Model
+from .model_repository import ModelRepository
 
 DEFAULT_HTTP_PORT = 8080
 DEFAULT_GRPC_PORT = 8081
@@ -44,12 +44,12 @@
 tornado.log.enable_pretty_logging()
 
 
-class KFServer:
+class ModelServer:
     def __init__(self, http_port: int = args.http_port,
                  grpc_port: int = args.grpc_port,
                  max_buffer_size: int = args.max_buffer_size,
                  workers: int = args.workers,
-                 registered_models: KFModelRepository = KFModelRepository()):
+                 registered_models: ModelRepository = ModelRepository()):
         self.registered_models = registered_models
         self.http_port = http_port
         self.grpc_port = grpc_port
@@ -85,7 +85,7 @@ def create_application(self):
              UnloadHandler, dict(models=self.registered_models)),
         ])
 
-    def start(self, models: List[KFModel], nest_asyncio: bool = False):
+    def start(self, models: List[Model], nest_asyncio: bool = False):
         for model in models:
             self.register_model(model)
 
@@ -106,7 +106,7 @@ def start(self, models: List[KFModel], nest_asyncio: bool = False):
 
         tornado.ioloop.IOLoop.current().start()
 
-    def register_model(self, model: KFModel):
+    def register_model(self, model: Model):
         if not model.name:
             raise Exception(
                 "Failed to register model, model.name must be provided.")
@@ -120,7 +120,7 @@ def get(self):
 
 
 class HealthHandler(tornado.web.RequestHandler):
-    def initialize(self, models: KFModelRepository):
+    def initialize(self, models: ModelRepository):
         self.models = models  # pylint:disable=attribute-defined-outside-init
 
     def get(self, name: str):
@@ -144,15 +144,15 @@ def get(self, name: str):
 
 
 class ListHandler(tornado.web.RequestHandler):
-    def initialize(self, models: KFModelRepository):
+    def initialize(self, models: ModelRepository):
         self.models = models  # pylint:disable=attribute-defined-outside-init
 
     def get(self):
         self.write(json.dumps([ob.name for ob in self.models.get_models()]))
 
 
 class LoadHandler(tornado.web.RequestHandler):
-    def initialize(self, models: KFModelRepository):  # pylint:disable=attribute-defined-outside-init
+    def initialize(self, models: ModelRepository):  # pylint:disable=attribute-defined-outside-init
         self.models = models
 
     async def post(self, name: str):
@@ -178,7 +178,7 @@ async def post(self, name: str):
 
 
 class UnloadHandler(tornado.web.RequestHandler):
-    def initialize(self, models: KFModelRepository):  # pylint:disable=attribute-defined-outside-init
+    def initialize(self, models: ModelRepository):  # pylint:disable=attribute-defined-outside-init
         self.models = models
 
     def post(self, name: str):

docs/samples/explanation/art/mnist/sklearnserver/sklearnserver/model.py

@@ -21,7 +21,7 @@
 MODEL_EXTENSIONS = [".joblib", ".pkl", ".pickle"]
 
 
-class SKLearnModel(kserve.KFModel):  # pylint:disable=c-extension-no-member
+class SKLearnModel(kserve.Model):  # pylint:disable=c-extension-no-member
     def __init__(self, name: str, model_dir: str):
         super().__init__(name)
         self.name = name

docs/samples/explanation/art/mnist/sklearnserver/sklearnserver/sklearn_model_repository.py

@@ -12,11 +12,11 @@
 # limitations under the License.
 
 import os
-from .kfmodel_repository import KFModelRepository, MODEL_MOUNT_DIRS
+from .model_repository import ModelRepository, MODEL_MOUNT_DIRS
 from sklearnserver import SKLearnModel
 
 
-class SKLearnModelRepository(KFModelRepository):
+class SKLearnModelRepository(ModelRepository):
 
     def __init__(self, model_dir: str = MODEL_MOUNT_DIRS):
         super().__init__(model_dir)

docs/samples/kafka/image_transformer/__main__.py

@@ -17,7 +17,7 @@
 
 DEFAULT_MODEL_NAME = "model"
 
-parser = argparse.ArgumentParser(parents=[kserve.kfserver.parser])
+parser = argparse.ArgumentParser(parents=[kserve.model_server.parser])
 parser.add_argument('--model_name', default=DEFAULT_MODEL_NAME,
                     help='The name that the model is served under.')
 parser.add_argument('--predictor_host', help='The URL for the model predict function', required=True)
@@ -26,5 +26,5 @@
 
 if __name__ == "__main__":
     transformer = ImageTransformer(args.model_name, predictor_host=args.predictor_host)
-    kfserver = kserve.KFServer()
-    kfserver.start(models=[transformer])
+    server = kserve.ModelServer()
+    server.start(models=[transformer])

docs/samples/kafka/image_transformer/image_transformer.py

@@ -31,7 +31,7 @@ def image_transform(image):
     return g.tolist()
 
 
-class ImageTransformer(kserve.KFModel):
+class ImageTransformer(kserve.Model):
     def __init__(self, name: str, predictor_host: str):
         super().__init__(name)
         self.predictor_host = predictor_host

docs/samples/v1beta1/custom/custom_model/README.md

@@ -1,25 +1,25 @@
 # Deploy Custom Python Model with KFServer API
 When out of the box model server does not fit your need, you can build your own model server using KFServer API and use the
-following source to serving workflow to deploy your custom models to KFServing.
+following source to serving workflow to deploy your custom models to KServe.
 
 ## Setup
-1. Your ~/.kube/config should point to a cluster with [KFServing installed](https://github.com/kubeflow/kfserving/#install-kfserving).
+1. Your ~/.kube/config should point to a cluster with [KServe installed](https://github.com/kserve/kserve#installation).
 2. Your cluster's Istio Ingress gateway must be [network accessible](https://istio.io/latest/docs/tasks/traffic-management/ingress/ingress-control/).
 3. Install [pack CLI](https://buildpacks.io/docs/tools/pack/) to build your custom model server image.
 
-## Create your custom Model Server by extending KFModel
-`KFServing.KFModel` base class mainly defines three handlers `preprocess`, `predict` and `postprocess`, these handlers are executed
+## Create your custom Model Server by extending Model
+`KServe.Model` base class mainly defines three handlers `preprocess`, `predict` and `postprocess`, these handlers are executed
 in sequence, the output of the `preprocess` is passed to `predict` as the input, the `predictor` handler should execute the
 inference for your model, the `postprocess` handler then turns the raw prediction result into user-friendly inference response. There
 is an additional `load` handler which is used for writing custom code to load your model into the memory from local file system or
 remote model storage, a general good practice is to call the `load` handler in the model server class `__init__` function, so your model
 is loaded on startup and ready to serve when user is making the prediction calls.
 
 ```python
-import kfserving
+import kserve
 from typing import Dict
 
-class AlexNetModel(kfserving.KFModel):
+class AlexNetModel(kserve.Model):
     def __init__(self, name: str):
        super().__init__(name)
        self.name = name
@@ -33,11 +33,11 @@ class AlexNetModel(kfserving.KFModel):
 
 if __name__ == "__main__":
     model = AlexNetModel("custom-model")
-    kfserving.KFServer().start([model])
+    kserve.ModelServer().start([model])
 ```
 
 ## Build the custom image with Buildpacks
-[Buildpacks](https://buildpacks.io/) allows you to transform your inference code into images that can be deployed on KFServing without
+[Buildpacks](https://buildpacks.io/) allows you to transform your inference code into images that can be deployed on KServe without
 needing to define the `Dockerfile`. Buildpacks automatically determines the python application and then install the dependencies from the
 `requirements.txt` file, it looks at the `Procfile` to determine how to start the model server. Here we are showing how to build the serving
 image manually with `pack`, you can also choose to use [kpack](https://github.com/pivotal/kpack)
@@ -52,16 +52,16 @@ docker push ${DOCKER_USER}/custom-model:v1
 ## Parallel Inference
 By default the model is loaded and inference is ran in the same process as tornado http server, if you are hosting multiple models
 the inference can only be run for one model at a time which limits the concurrency when you share the container for the models.
-KFServing integrates [RayServe](https://docs.ray.io/en/master/serve/index.html) which provides a programmable API to deploy models
+KServe integrates [RayServe](https://docs.ray.io/en/master/serve/index.html) which provides a programmable API to deploy models
 as separate python workers so the inference can be ran in parallel.
 
 ```python
-import kfserving
+import kserve
 from typing import Dict
 from ray import serve
 
 @serve.deployment(name="custom-model", config={"num_replicas": 2})
-class AlexNetModel(kfserving.KFModel):
+class AlexNetModel(kserve.Model):
     def __init__(self):
        self.name = "custom-model"
        super().__init__(self.name)
@@ -74,7 +74,7 @@ class AlexNetModel(kfserving.KFModel):
         pass
 
 if __name__ == "__main__":
-    kfserving.KFServer().start({"custom-model": AlexNetModel})
+    kserve.ModelServer().start({"custom-model": AlexNetModel})
 ```
 
 Modify the `Procfile` to `web: python -m model_remote` and then run the above `pack` command, it builds the serving image which launches
@@ -96,7 +96,7 @@ curl localhost:8080/v1/models/custom-model:predict -d @./input.json
 {"predictions": [[14.861763000488281, 13.94291877746582, 13.924378395080566, 12.182709693908691, 12.00634765625]]}
 ```
 
-## Deploy to KFServing
+## Deploy to KServe
 ### Create the InferenceService
 
 In the `custom.yaml` file edit the container image and replace {username} with your Docker Hub username.

docs/samples/v1beta1/custom/torchserve/README.md

@@ -4,14 +4,14 @@ In this example we use torchserve as custom server to serve an mnist model. The
 
 ## Setup
 
-1. Your ~/.kube/config should point to a cluster with [KFServing installed](https://github.com/kubeflow/kfserving/#install-kfserving).
+1. Your ~/.kube/config should point to a cluster with [KServe installed](https://github.com/kserve/kserve#installation).
 2. Your cluster's Istio Ingress gateway must be [network accessible](https://istio.io/latest/docs/tasks/traffic-management/ingress/ingress-control/).
 
 ### This example requires v1beta1/KFS 0.5
 
 ## Build and push the sample Docker Image
 
-The custom torchserve image is wrapped with model inside the container and serves it with KFServing.
+The custom torchserve image is wrapped with model inside the container and serves it with KServe.
 
 In this example we build a torchserve image with marfile and config.properties into a container. To build and push with Docker Hub, run these commands replacing {username} with your Docker Hub username:
 

docs/samples/v1beta1/custom/torchserve/bert-sample/hugging-face-bert-sample.md

@@ -41,7 +41,7 @@ torch-model-archiver --model-name BERTSeqClassification --version 1.0 --serializ
 
 ## Build and push the sample Docker Image
 
-The custom torchserve image is wrapped with model inside the container and serves it with KFServing.
+The custom torchserve image is wrapped with model inside the container and serves it with KServe.
 
 In this example we use Docker to build the torchserve image with marfile and config.properties into a container.
 

docs/samples/v1beta1/custom/torchserve/docs/metrics.md

@@ -4,7 +4,7 @@ This adds prometheus and granfana to the cluster with some default metrics.
 
 ## Setup
 
-1. Your ~/.kube/config should point to a cluster with [KFServing installed](https://github.com/kubeflow/kfserving/#install-kfserving).
+1. Your ~/.kube/config should point to a cluster with [KServe installed](https://github.com/kserve/kserve#installation).
 2. Your cluster's Istio Ingress gateway must be [network accessible](https://istio.io/latest/docs/tasks/traffic-management/ingress/ingress-control/).
 
 ## Enable request metrics

docs/samples/v1beta1/lightgbm/README.md

@@ -48,7 +48,7 @@ print(res.text)
 ## Predict on a InferenceService using LightGBM Server
 
 ## Setup
-1. Your ~/.kube/config should point to a cluster with [KFServing installed](https://github.com/kubeflow/kfserving/#install-kfserving).
+1. Your ~/.kube/config should point to a cluster with [KServe installed](https://github.com/kserve/kserve#installation).
 2. Your cluster's Istio Ingress gateway must be [network accessible](https://istio.io/latest/docs/tasks/traffic-management/ingress/ingress-control/).
 
 ## Create the InferenceService
@@ -99,11 +99,11 @@ Expected Output
 ```
 
 ## Run LightGBM InferenceService with your own image
-Since the KFServing LightGBM image is built from a specific version of `lightgbm` pip package, sometimes it might not be compatible with the pickled model
+Since the KServe LightGBM image is built from a specific version of `lightgbm` pip package, sometimes it might not be compatible with the pickled model
 you saved from your training environment, however you can build your own lgbserver image following [this instruction](../../../python/lgbserver/README.md#building-your-own-ligthgbm-server-docker-image).
 
 To use your lgbserver image:
-- Add the image to the KFServing [configmap](../../../../config/configmap/inferenceservice.yaml)
+- Add the image to the KServe [configmap](../../../../config/configmap/inferenceservice.yaml)
 ```yaml
         "lightgbm": {
             "image": "<your-dockerhub-id>/kfserving/lgbserver",