diff --git a/examples/models/openvino_R4/Makefile b/examples/models/openvino_R4/Makefile
deleted file mode 100644
index 22c5045cb1..0000000000
--- a/examples/models/openvino_R4/Makefile
+++ /dev/null
@@ -1,12 +0,0 @@
-
-
-build_image:
-	s2i build -E environment_grpc . seldon_python_openvino seldon-openvino-prediction
-
-
-clean:
-	rm -rf model
-	rm -rf proto/__pycache__
-	rm -f proto/*.py
-	rm -r proto/*.proto
-	rm -rf tensorflow
diff --git a/examples/models/openvino_R4/Prediction.py b/examples/models/openvino_R4/Prediction.py
deleted file mode 100644
index 6997961a29..0000000000
--- a/examples/models/openvino_R4/Prediction.py
+++ /dev/null
@@ -1,100 +0,0 @@
-import numpy as np
-import logging
-import datetime
-import os
-import sys
-from urllib.parse import urlparse
-from google.cloud import storage
-from openvino.inference_engine import IENetwork, IEPlugin
-
-
-def get_logger(name):
-    logger = logging.getLogger(name)
-    log_formatter = logging.Formatter("%(asctime)s - %(name)s - "
-                                      "%(levelname)s - %(message)s")
-    logger.setLevel('DEBUG')
-
-    console_handler = logging.StreamHandler()
-    console_handler.setFormatter(log_formatter)
-    logger.addHandler(console_handler)
-
-    return logger
-
-logger = get_logger(__name__)
-
-
-def gs_download_file(path):
-    if path is None:
-        return None
-    parsed_path = urlparse(path)
-    bucket_name = parsed_path.netloc
-    file_path = parsed_path.path[1:]
-    gs_client = storage.Client()
-    bucket = gs_client.get_bucket(bucket_name)
-    blob = bucket.blob(file_path)
-    tmp_path = os.path.join('/tmp', file_path.split(os.sep)[-1])
-    blob.download_to_filename(tmp_path)
-    return tmp_path
-
-
-def s3_download_file(path):
-    if path is None:
-        return None
-    s3_endpoint = os.getenv('S3_ENDPOINT')
-    s3_client = boto3.client('s3', endpoint_url=s3_endpoint)
-    parsed_path = urlparse(path)
-    bucket_name = parsed_path.netloc
-    file_path = parsed_path.path[1:]
-    tmp_path = os.path.join('/tmp', file_path.split(os.sep)[-1])
-    s3_transfer = boto3.s3.transfer.S3Transfer(s3_client)
-    s3_transfer.download_file(bucket_name, file_path, tmp_path)
-    return tmp_path
-
-
-def GetLocalPath(requested_path):
-    parsed_path = urlparse(requested_path)
-    if parsed_path.scheme == '':
-        return requested_path
-    elif parsed_path.scheme == 'gs':
-        return gs_download_file(path=requested_path)
-    elif parsed_path.scheme == 's3':
-        return s3_download_file(path=requested_path)
-
-
-class Prediction(object):
-    def __init__(self):
-        try:
-            xml_path = os.environ["XML_PATH"]
-            bin_path = os.environ["BIN_PATH"]
-
-        except KeyError:
-            print("Please set the environment variables XML_PATH, BIN, PATH, INPUT and OUTPUT")
-            sys.exit(1)
-
-        xml_local_path = GetLocalPath(xml_path)
-        bin_local_path = GetLocalPath(bin_path)
-        print('path object', xml_local_path)
-
-        CPU_EXTENSION = os.getenv('CPU_EXTENSION', '/usr/local/lib/libcpu_extension.so')
-
-        plugin = IEPlugin(device='CPU', plugin_dirs=None)
-        if CPU_EXTENSION:
-            plugin.add_cpu_extension(CPU_EXTENSION)
-        net = IENetwork.from_ir(model=xml_local_path, weights=bin_local_path)
-        self.input_blob = next(iter(net.inputs))
-        self.out_blob = next(iter(net.outputs))
-        self.batch_size = net.inputs[self.input_blob].shape[0]
-        self.inputs = net.inputs
-        self.outputs = net.outputs
-        self.exec_net = plugin.load(network=net, num_requests=self.batch_size)
-
-
-    def predict(self,X,feature_names):
-        start_time = datetime.datetime.now()
-        results = self.exec_net.infer(inputs={self.input_blob: X})
-        predictions = results[self.out_blob]
-        end_time = datetime.datetime.now()
-        duration = (end_time - start_time).total_seconds() * 1000
-        logger.debug("Processing time: {:.2f} ms".format(duration))
-        return predictions.astype(np.float64)
-
diff --git a/examples/models/openvino_R4/README.md b/examples/models/openvino_R4/README.md
deleted file mode 100644
index b1f5d759dc..0000000000
--- a/examples/models/openvino_R4/README.md
+++ /dev/null
@@ -1,8 +0,0 @@
-# OpenVINO prediction component
-
-Model configuration is implemented using environment variables:
-
-XML_PATH  - s3, gs or local path to xml file in OpenVINO model server
-
-BIN_PATH - s3, gs or local path to bin file in OpenVINO model server
-
diff --git a/examples/models/openvino_R4/client.py b/examples/models/openvino_R4/client.py
deleted file mode 100644
index fabc04a8d7..0000000000
--- a/examples/models/openvino_R4/client.py
+++ /dev/null
@@ -1,103 +0,0 @@
-import json
-import requests
-import base64
-from proto import prediction_pb2
-from proto import prediction_pb2_grpc
-import grpc
-import numpy as np
-import pickle
-import tensorflow as tf
-import cv2
-import datetime
-import tensorflow as tf
-
-def image_2_vector(input_file):
-    nparr = np.fromfile(input_file, dtype=np.float32)
-    print("nparr",nparr.dtype,nparr.shape)
-    img = cv2.imdecode(nparr, cv2.IMREAD_ANYCOLOR)
-    print("img",img.dtype,img.shape)
-    print("Initial size",img.shape)
-    image = cv2.resize(img, (w, h))
-    print("image",image.dtype)
-    print("Converted size",image.shape)
-
-    vector = image.reshape((w * h * 3))
-    print("vector shape",vector.shape, "vector type", vector.dtype )
-    return vector
-
-def image_2_bytes(input_file):
-    with open(input_file, "rb") as binary_file:
-        # Read the whole file at once
-        data = binary_file.read()
-
-        #data = data.tobytes()
-        #print(data)
-        print("binary data size:", len(data), type(data))
-    return data
-
-def run(function,image_path,iterations=1):
-    w = 224
-    h = 224
-
-    # NOTE(gRPC Python Team): .close() is possible on a channel and should be
-    # used in circumstances in which the with statement does not fit the needs
-    # of the code.
-    with grpc.insecure_channel('localhost:5000') as channel:
-        stub = prediction_pb2_grpc.ModelStub(channel)
-        print("seldon stub", stub)
-        start_time = datetime.datetime.now()
-        processing_times = np.zeros((0),int)
-
-        img = cv2.imread(image_path)
-        print("img type", type(img))
-        print("img",img.shape)
-        print("Initial size",img.shape)
-        image = cv2.resize(img, (w, h))
-        image = image.reshape(1, w, h, 3)
-        image = image.transpose((0,3,1,2))
-        print("image",image.dtype)
-        print("Converted size",image.shape)
-        
-        if function == "tensor":
-            datadef = prediction_pb2.DefaultData(
-                names = 'x',
-                tensor = prediction_pb2.Tensor(
-                    shape = image.shape,
-                    values = image.ravel().tolist()
-                )
-            )
-        elif function == "tftensor":
-            print("Create tftensor")
-            datadef = prediction_pb2.DefaultData(
-                names = 'x',
-                tftensor = tf.make_tensor_proto(image)
-            )
-            
-        GRPC_request = prediction_pb2.SeldonMessage(
-            data = datadef
-        )
-            
-        for I in range(iterations):
-            start_time = datetime.datetime.now()
-            response = stub.Predict(request=GRPC_request)
-            end_time = datetime.datetime.now()
-            duration = (end_time - start_time).total_seconds() * 1000
-            processing_times = np.append(processing_times,np.array([int(duration)]))
-            
-        print('processing time for all iterations')
-        for x in processing_times:
-            print(x,"ms")
-        print('processing_statistics')
-        print('average time:',round(np.average(processing_times),1), 'ms; average speed:', round(1000/np.average(processing_times),1),'fps')
-        print('median time:',round(np.median(processing_times),1), 'ms; median speed:',round(1000/np.median(processing_times),1),'fps')
-        print('max time:',round(np.max(processing_times),1), 'ms; max speed:',round(1000/np.max(processing_times),1),'fps')
-        print('min time:',round(np.min(processing_times),1),'ms; min speed:',round(1000/np.min(processing_times),1),'fps')
-        print('time percentile 90:',round(np.percentile(processing_times,90),1),'ms; speed percentile 90:',round(1000/np.percentile(processing_times,90),1),'fps')
-        print('time percentile 50:',round(np.percentile(processing_times,50),1),'ms; speed percentile 50:',round(1000/np.percentile(processing_times,50),1),'fps')
-        print('time standard deviation:',round(np.std(processing_times)))
-        print('time variance:',round(np.var(processing_times)))
-
-
-#run("tensor","./dog.jpeg",iterations=100)
-
-run("tftensor","./dog.jpeg",iterations=100)
diff --git a/examples/models/openvino_R4/dog.jpeg b/examples/models/openvino_R4/dog.jpeg
deleted file mode 100644
index 8d83ed006c..0000000000
Binary files a/examples/models/openvino_R4/dog.jpeg and /dev/null differ
diff --git a/examples/models/openvino_R4/environment_grpc b/examples/models/openvino_R4/environment_grpc
deleted file mode 100644
index 7399188ba7..0000000000
--- a/examples/models/openvino_R4/environment_grpc
+++ /dev/null
@@ -1,8 +0,0 @@
-MODEL_NAME=Prediction
-API_TYPE=GRPC
-SERVICE_TYPE=MODEL
-XML_PATH=gs://inference-eu/models_zoo/resnet_V1_50/frozen_resnet_V1_50.xml
-BIN_PATH=gs://inference-eu/models_zoo/resnet_V1_50/frozen_resnet_V1_50.bin
-GOOGLE_APPLICATION_CREDENTIALS=/etc/gcp.json
-PERSISTENCE=0
-
diff --git a/examples/models/openvino_R4/requirements.txt b/examples/models/openvino_R4/requirements.txt
deleted file mode 100644
index e931a7a540..0000000000
--- a/examples/models/openvino_R4/requirements.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-google-cloud-storage==1.13.0
-boto3==1.9.34
\ No newline at end of file
diff --git a/wrappers/s2i/python/Dockerfile_model_openvino b/wrappers/s2i/python/Dockerfile_model_openvino
deleted file mode 100644
index c43f6ab23b..0000000000
--- a/wrappers/s2i/python/Dockerfile_model_openvino
+++ /dev/null
@@ -1,25 +0,0 @@
-FROM openvino_base:latest
-LABEL io.openshift.s2i.scripts-url="image:///s2i/bin"
-
-#RUN apt-get update -y
-RUN apt-get install -y build-essential
-
-RUN mkdir microservice
-WORKDIR /microservice
-
-ENV LD_LIBRARY_PATH=/usr/local/lib
-ENV PYTHONPATH=/usr/local/lib
-
-RUN conda create --name myenv -y
-ENV PATH /opt/conda/envs/myenv/bin:$PATH
-
-COPY _python /microservice
-
-RUN cd /microservice/python && \
-    pip install .
-
-#RUN pip install seldon-core
-
-COPY ./s2i/bin/ /s2i/bin
-
-EXPOSE 5000
diff --git a/wrappers/s2i/python/Dockerfile_openvino_base b/wrappers/s2i/python/Dockerfile_openvino_base
deleted file mode 100644
index 312f98129f..0000000000
--- a/wrappers/s2i/python/Dockerfile_openvino_base
+++ /dev/null
@@ -1,63 +0,0 @@
-FROM intelpython/intelpython3_core as DEV
-RUN apt-get update && apt-get install -y \
-            curl \
-            ca-certificates \
-            libgfortran3 \
-            vim \
-            build-essential \
-            cmake \
-            curl \
-            wget \
-            libssl-dev \
-            ca-certificates \
-            git \
-            libboost-regex-dev \
-            gcc-multilib \
-            g++-multilib \
-            libgtk2.0-dev \
-            pkg-config \
-            unzip \
-            automake \
-            libtool \
-            autoconf \
-            libpng-dev \
-            libcairo2-dev \
-            libpango1.0-dev \
-            libglib2.0-dev \
-            libgtk2.0-dev \
-            libswscale-dev \
-            libavcodec-dev \
-            libavformat-dev \
-            libgstreamer1.0-0 \
-            gstreamer1.0-plugins-base \
-            libusb-1.0-0-dev \
-            libopenblas-dev
-
-ARG DLDT_DIR=/dldt-2018_R4
-RUN git clone --depth=1 -b 2018_R4 https://github.com/opencv/dldt.git ${DLDT_DIR} && \
-    cd ${DLDT_DIR} && git submodule init && git submodule update --recursive && \
-    rm -Rf .git && rm -Rf model-optimizer
-
-WORKDIR ${DLDT_DIR}
-RUN curl -L -o ${DLDT_DIR}/mklml_lnx_2019.0.1.20180928.tgz https://github.com/intel/mkl-dnn/releases/download/v0.17/mklml_lnx_2019.0.1.20180928.tgz && \
-    tar -xzf ${DLDT_DIR}/mklml_lnx_2019.0.1.20180928.tgz && rm ${DLDT_DIR}/mklml_lnx_2019.0.1.20180928.tgz
-WORKDIR ${DLDT_DIR}/inference-engine
-RUN mkdir build && cd build && cmake -DGEMM=MKL  -DMKLROOT=${DLDT_DIR}/mklml_lnx_2019.0.1.20180928 -DENABLE_MKL_DNN=ON  -DCMAKE_BUILD_TYPE=Release ..
-RUN cd build && make -j4
-RUN pip install cython numpy && mkdir ie_bridges/python/build && cd ie_bridges/python/build && \
-    cmake -DInferenceEngine_DIR=${DLDT_DIR}/inference-engine/build -DPYTHON_EXECUTABLE=`which python` -DPYTHON_LIBRARY=/opt/conda/lib/libpython3.6m.so -DPYTHON_INCLUDE_DIR=/opt/conda/include/python3.6m .. && \
-    make -j4
-
-FROM intelpython/intelpython3_core as PROD
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-            curl \
-            ca-certificates \
-            vim
-
-COPY --from=DEV /dldt-2018_R4/inference-engine/bin/intel64/Release/lib/*.so /usr/local/lib/
-COPY --from=DEV /dldt-2018_R4/inference-engine/ie_bridges/python/build/ /usr/local/lib/openvino/
-COPY --from=DEV /dldt-2018_R4/mklml_lnx_2019.0.1.20180928/lib/lib*.so /usr/local/lib/
-ENV LD_LIBRARY_PATH=/usr/local/lib
-ENV PYTHONPATH=/usr/local/lib
-
diff --git a/wrappers/s2i/python/Makefile b/wrappers/s2i/python/Makefile
index 9ae3c5e95b..6c9f417c17 100644
--- a/wrappers/s2i/python/Makefile
+++ b/wrappers/s2i/python/Makefile
@@ -44,10 +44,6 @@ test_local:
 	cat Dockerfile.local.tmpl | sed  -e "s|%PYTHON_VERSION%|$(PYTHON_VERSION)|" > Dockerfile
 	docker build -t $(IMAGE_NAME)-candidate .
 	IMAGE_NAME=$(IMAGE_NAME)-candidate test/run
-.PHONY: build_python_openvino
-build_python_openvino:
-	docker build -f Dockerfile_openvino_base --build-arg http_proxy=$http_proxy --build-arg https_proxy=$https_proxy -t openvino_base:latest .
-	docker build -f Dockerfile_model_openvino --build-arg http_proxy=$http_proxy --build-arg https_proxy=$https_proxy -t seldon_model_openvino .	
 
 .PHONY: clean
 clean:
diff --git a/wrappers/s2i/python/README.md b/wrappers/s2i/python/README.md
index dbb8a44aaa..4464081131 100644
--- a/wrappers/s2i/python/README.md
+++ b/wrappers/s2i/python/README.md
@@ -13,8 +13,4 @@ e.g. from 0.3-SNAPSHOT to release 0.3 and create 0.4-SNAPSHOT
     ``` ./update_python_version.sh X X+1```, e.g ```./update_python_version.sh 0.2 0.3```
 
 
- * building openvino python base image
-```docker build -f Dockerfile_openvino_base --build-arg http_proxy=$http_proxy --build-arg https_proxy=$https_proxy -t openvino_base:latest . ```
-
-