From 00c823cdff067c329d687875a32f368db74dde6a Mon Sep 17 00:00:00 2001
From: oryx1729 <78848855+oryx1729@users.noreply.github.com>
Date: Tue, 4 Jan 2022 14:33:13 +0100
Subject: [PATCH] Add GitHub Action for Docker Build for GPU (#1916)

---
 .github/workflows/docker_build.yml | 55 +++++++++++++++++++++++++
 Dockerfile-GPU                     | 65 ++++++++++++++++++------------
 2 files changed, 95 insertions(+), 25 deletions(-)
 create mode 100644 .github/workflows/docker_build.yml

diff --git a/.github/workflows/docker_build.yml b/.github/workflows/docker_build.yml
new file mode 100644
index 000000000..8f337e7d1
--- /dev/null
+++ b/.github/workflows/docker_build.yml
@@ -0,0 +1,55 @@
+name: docker-build
+
+on:
+  push:
+    branches:
+      - master
+      - docker-build
+
+jobs:
+  build:
+    runs-on: ubuntu-20.04
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - dockerfile: Dockerfile
+            repository: deepset/haystack-cpu
+
+          - dockerfile: Dockerfile-GPU
+            repository: deepset/haystack-gpu
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v3
+        with:
+          images: |
+            ${{ matrix.repository }}
+          flavor: |
+            latest=true
+          tags: |
+            type=ref,event=tag
+            type=sha
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Login to DockerHub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKER_HUB_USER }}
+          password: ${{ secrets.DOCKER_HUB_TOKEN }}
+
+      - name: Build and push docker image
+        uses: docker/build-push-action@v2
+        with:
+          file: ${{ matrix.dockerfile }}
+          tags: ${{ steps.meta.outputs.tags }}
+          push: true
+          cache-from: type=registry,ref=${{ matrix.repository }}:latest
+          cache-to: type=inline
diff --git a/Dockerfile-GPU b/Dockerfile-GPU
index fa3c78323..6f4bafbc4 100644
--- a/Dockerfile-GPU
+++ b/Dockerfile-GPU
@@ -2,51 +2,66 @@ FROM  nvidia/cuda:11.0-runtime-ubuntu20.04
 
 WORKDIR /home/user
 
-RUN apt-get update && apt-get install -y software-properties-common && add-apt-repository ppa:deadsnakes/ppa
-RUN apt-get update && apt-get install -y python3.7 python3.7-dev python3.7-distutils python3-pip curl wget git pkg-config cmake swig
-
 ENV LC_ALL=C.UTF-8
 ENV LANG=C.UTF-8
 
-# Set default Python version
-RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.7 1
-RUN update-alternatives --set python3 /usr/bin/python3.7
+# create folder for /file-upload API endpoint with write permissions, this might be adjusted depending on FILE_UPLOAD_PATH
+RUN mkdir -p /home/user/file-upload && chmod 777 /home/user/file-upload
 
 # Install PDF converter
-RUN wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.03.tar.gz && \
-tar -xvf xpdf-tools-linux-4.03.tar.gz && cp xpdf-tools-linux-4.03/bin64/pdftotext /usr/local/bin
+RUN curl -s https://dl.xpdfreader.com/xpdf-tools-linux-4.03.tar.gz | tar -xvzf - -C /usr/local/bin --strip-components=2 xpdf-tools-linux-4.03/bin64/pdftotext
 
-RUN apt-get install libpoppler-cpp-dev pkg-config -y --fix-missing
-RUN apt-get install tesseract-ocr libtesseract-dev poppler-utils -y
+# Install software dependencies
+RUN apt-get update && apt-get install -y software-properties-common && \
+    add-apt-repository ppa:deadsnakes/ppa && \
+    apt-get update && apt-get install -y \
+        cmake \
+        curl \
+        git \
+        libpoppler-cpp-dev \
+        libtesseract-dev \
+        pkg-config \
+        poppler-utils \
+        python3-pip \
+        python3.7 \
+        python3.7-dev \
+        python3.7-distutils \
+        swig \
+        tesseract-ocr \
+        wget
 
-# copy code
-COPY haystack /home/user/haystack
+# Set default Python version
+RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.7 1 && \
+    update-alternatives --set python3 /usr/bin/python3.7
 
-# install as a package
+# Copy package setup files
 COPY setup.py requirements.txt README.md /home/user/
-RUN pip3 install numpy scipy Cython
 
-# Install PyTorch for CUDA 11
-RUN pip3 install torch==1.7.1+cu110 -f https://download.pytorch.org/whl/torch_stable.html
-# Install faiss separately as building latest versions can cause trouble with swig
-RUN pip3 install faiss-cpu==1.6.3
-
-RUN pip3 install -r requirements.txt
-RUN pip3 install -e .
+RUN echo "Install required packages" && \
+    # Install PyTorch for CUDA 11
+    pip3 install torch==1.7.1+cu110 -f https://download.pytorch.org/whl/torch_stable.html && \
+    # Install faiss separately as building latest versions can cause trouble with swig
+    pip3 install faiss-cpu==1.6.3 && \
+    # Install extra packages
+    pip3 install Cython && \
+    # Install from requirements.txt
+    pip3 install -r requirements.txt
 
 # download punkt tokenizer to be included in image
 RUN python3 -c "import nltk;nltk.download('punkt', download_dir='/usr/nltk_data')"
 
-# create folder for /file-upload API endpoint with write permissions, this might be adjusted depending on FILE_UPLOAD_PATH
-RUN mkdir -p /home/user/file-upload
-RUN chmod 777 /home/user/file-upload
-
 # copy saved models
 COPY README.md models* /home/user/models/
 
 # Copy REST API code
 COPY rest_api /home/user/rest_api
 
+# copy code
+COPY haystack /home/user/haystack
+
+# Install package
+RUN pip3 install -e .
+
 # optional : copy sqlite db if needed for testing
 #COPY qa.db /home/user/