Refactor API round #2

Author: vishalbollu

build/lint.sh

@@ -75,7 +75,7 @@ output=$(cd "$ROOT" && find . -type f \
 ! -path "./.circleci/*" \
 ! -path "./.git/*" \
 ! -name LICENSE \
-! -name requirements.txt \
+! -name "*requirements.txt" \
 ! -name "go.*" \
 ! -name "*.md" \
 ! -name ".*" \

docs/deployments/onnx.md

@@ -57,7 +57,7 @@ You can log information about each request by adding a `?debug=true` parameter t
 An ONNX Predictor is a Python class that describes how to serve your ONNX model to make predictions.
 
 <!-- CORTEX_VERSION_MINOR -->
-Cortex provides an `onnx_client` and a config object to initialize your implementation of the ONNX Predictor class. The `onnx_client` is an instance of [ONNXClient](https://github.com/cortexlabs/cortex/tree/master/pkg/workloads/cortex/onnx_serve/client.py) that manages an ONNX Runtime session and helps make predictions using your model. Once your implementation of the ONNX Predictor class has been initialized, the replica is available to serve requests. Upon receiving a request, your implementation's `predict()` function is called with the JSON payload and is responsible for returning a prediction or batch of predictions. Your `predict()` function should call `onnx_client.predict()` to make an inference against your exported ONNX model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
+Cortex provides an `onnx_client` and a config object to initialize your implementation of the ONNX Predictor class. The `onnx_client` is an instance of [ONNXClient](https://github.com/cortexlabs/cortex/tree/master/pkg/workloads/cortex/lib/client/onnx.py) that manages an ONNX Runtime session and helps make predictions using your model. Once your implementation of the ONNX Predictor class has been initialized, the replica is available to serve requests. Upon receiving a request, your implementation's `predict()` function is called with the JSON payload and is responsible for returning a prediction or batch of predictions. Your `predict()` function should call `onnx_client.predict()` to make an inference against your exported ONNX model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
 
 ## Implementation
 

docs/deployments/tensorflow.md

@@ -58,7 +58,7 @@ You can log information about each request by adding a `?debug=true` parameter t
 A TensorFlow Predictor is a Python class that describes how to serve your TensorFlow model to make predictions.
 
 <!-- CORTEX_VERSION_MINOR -->
-Cortex provides a `tensorflow_client` and a config object to initialize your implementation of the TensorFlow Predictor class. The `tensorflow_client` is an instance of [TensorFlowClient](https://github.com/cortexlabs/cortex/tree/master/pkg/workloads/cortex/tf_api/client.py) that manages a connection to a TensorFlow Serving container via gRPC to make predictions using your model. Once your implementation of the TensorFlow Predictor class has been initialized, the replica is available to serve requests. Upon receiving a request, your implementation's `predict()` function is called with the JSON payload and is responsible for returning a prediction or batch of predictions. Your `predict()` function should call `tensorflow_client.predict()` to make an inference against your exported TensorFlow model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
+Cortex provides a `tensorflow_client` and a config object to initialize your implementation of the TensorFlow Predictor class. The `tensorflow_client` is an instance of [TensorFlowClient](https://github.com/cortexlabs/cortex/tree/master/pkg/workloads/cortex/lib/client/tensorflow.py) that manages a connection to a TensorFlow Serving container via gRPC to make predictions using your model. Once your implementation of the TensorFlow Predictor class has been initialized, the replica is available to serve requests. Upon receiving a request, your implementation's `predict()` function is called with the JSON payload and is responsible for returning a prediction or batch of predictions. Your `predict()` function should call `tensorflow_client.predict()` to make an inference against your exported TensorFlow model. Preprocessing of the JSON payload and postprocessing of predictions can be implemented in your `predict()` function as well.
 
 ## Implementation
 

images/onnx-serve-gpu/Dockerfile

@@ -23,17 +23,18 @@ RUN apt-get update -qq && apt-get install -y -q \
 ENV PYTHONPATH "${PYTHONPATH}:/src:/mnt/project"
 
 COPY pkg/workloads/cortex/lib/requirements.txt /src/cortex/lib/requirements.txt
-COPY pkg/workloads/cortex/onnx_serve/requirements.txt /src/cortex/onnx_serve/requirements.txt
+COPY pkg/workloads/cortex/serve/onnx.requirements.txt /src/cortex/serve/requirements.txt
 
 ARG ONNXRUNTIME_VERSION="1.1.0"
 
-RUN pip install -r /src/cortex/lib/requirements.txt && \
-    pip install -r /src/cortex/onnx_serve/requirements.txt && \
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
+    pip install --no-cache-dir -r /src/cortex/serve/requirements.txt && \
     pip install onnxruntime-gpu==${ONNXRUNTIME_VERSION} && \
     rm -rf /root/.cache/pip*
 
 COPY pkg/workloads/cortex/consts.py /src/cortex
 COPY pkg/workloads/cortex/lib /src/cortex/lib
-COPY pkg/workloads/cortex/onnx_serve /src/cortex/onnx_serve
+COPY pkg/workloads/cortex/serve /src/cortex/serve
 
-ENTRYPOINT ["/src/cortex/onnx_serve/run.sh"]
+ENTRYPOINT ["/src/cortex/serve/run.sh"]

images/onnx-serve/Dockerfile

@@ -23,17 +23,18 @@ RUN apt-get update -qq && apt-get install -y -q \
 ENV PYTHONPATH "${PYTHONPATH}:/src:/mnt/project"
 
 COPY pkg/workloads/cortex/lib/requirements.txt /src/cortex/lib/requirements.txt
-COPY pkg/workloads/cortex/onnx_serve/requirements.txt /src/cortex/onnx_serve/requirements.txt
+COPY pkg/workloads/cortex/serve/onnx.requirements.txt /src/cortex/serve/requirements.txt
 
 ARG ONNXRUNTIME_VERSION="1.1.0"
 
-RUN pip install -r /src/cortex/lib/requirements.txt && \
-    pip install -r /src/cortex/onnx_serve/requirements.txt && \
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
+    pip install --no-cache-dir -r /src/cortex/serve/requirements.txt && \
     pip install onnxruntime==${ONNXRUNTIME_VERSION} && \
     rm -rf /root/.cache/pip*
 
 COPY pkg/workloads/cortex/consts.py /src/cortex
 COPY pkg/workloads/cortex/lib /src/cortex/lib
-COPY pkg/workloads/cortex/onnx_serve /src/cortex/onnx_serve
+COPY pkg/workloads/cortex/serve /src/cortex/serve
 
-ENTRYPOINT ["/src/cortex/onnx_serve/run.sh"]
+ENTRYPOINT ["/src/cortex/serve/run.sh"]

images/python-serve-gpu/Dockerfile

@@ -23,13 +23,14 @@ RUN apt-get update -qq && apt-get install -y -q \
 ENV PYTHONPATH "${PYTHONPATH}:/src:/mnt/project"
 
 COPY pkg/workloads/cortex/lib/requirements.txt /src/cortex/lib/requirements.txt
-COPY pkg/workloads/cortex/python_serve/requirements.txt /src/cortex/python_serve/requirements.txt
-RUN pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
-    pip install --no-cache-dir -r /src/cortex/python_serve/requirements.txt && \
+COPY pkg/workloads/cortex/serve/python.requirements.txt /src/cortex/serve/requirements.txt
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
+    pip install --no-cache-dir -r /src/cortex/serve/requirements.txt && \
     rm -rf /root/.cache/pip*
 
 COPY pkg/workloads/cortex/consts.py /src/cortex
 COPY pkg/workloads/cortex/lib /src/cortex/lib
-COPY pkg/workloads/cortex/python_serve /src/cortex/python_serve
+COPY pkg/workloads/cortex/serve /src/cortex/serve
 
-ENTRYPOINT ["/src/cortex/python_serve/run.sh"]
+ENTRYPOINT ["/src/cortex/serve/run.sh"]

images/python-serve/Dockerfile

@@ -23,13 +23,14 @@ RUN apt-get update -qq && apt-get install -y -q \
 ENV PYTHONPATH "${PYTHONPATH}:/src:/mnt/project"
 
 COPY pkg/workloads/cortex/lib/requirements.txt /src/cortex/lib/requirements.txt
-COPY pkg/workloads/cortex/python_serve/requirements.txt /src/cortex/python_serve/requirements.txt
-RUN pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
-    pip install --no-cache-dir -r /src/cortex/python_serve/requirements.txt && \
+COPY pkg/workloads/cortex/serve/python.requirements.txt /src/cortex/serve/requirements.txt
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
+    pip install --no-cache-dir -r /src/cortex/serve/requirements.txt && \
     rm -rf /root/.cache/pip*
 
 COPY pkg/workloads/cortex/consts.py /src/cortex
 COPY pkg/workloads/cortex/lib /src/cortex/lib
-COPY pkg/workloads/cortex/python_serve /src/cortex/python_serve
+COPY pkg/workloads/cortex/serve /src/cortex/serve
 
-ENTRYPOINT ["/src/cortex/python_serve/run.sh"]
+ENTRYPOINT ["/src/cortex/serve/run.sh"]

images/tf-api/Dockerfile

@@ -17,14 +17,14 @@ RUN apt-get update -qq && apt-get install -y -q \
     && apt-get clean -qq && rm -rf /var/lib/apt/lists/*
 
 COPY pkg/workloads/cortex/lib/requirements.txt /src/cortex/lib/requirements.txt
-COPY pkg/workloads/cortex/tf_api/requirements.txt /src/cortex/tf_api/requirements.txt
+COPY pkg/workloads/cortex/serve/tf.requirements.txt /src/cortex/serve/requirements.txt
 RUN pip install --upgrade pip && \
-    pip install -r /src/cortex/lib/requirements.txt && \
-    pip install -r /src/cortex/tf_api/requirements.txt && \
+    pip install --no-cache-dir -r /src/cortex/lib/requirements.txt && \
+    pip install --no-cache-dir -r /src/cortex/serve/requirements.txt && \
     rm -rf /root/.cache/pip*
 
 COPY pkg/workloads/cortex/consts.py /src/cortex/
 COPY pkg/workloads/cortex/lib /src/cortex/lib
-COPY pkg/workloads/cortex/tf_api /src/cortex/tf_api
+COPY pkg/workloads/cortex/serve /src/cortex/serve
 
-ENTRYPOINT ["/src/cortex/tf_api/run.sh"]
+ENTRYPOINT ["/src/cortex/serve/run.sh"]