Disable pip cache for Dockerfiles (deepset-ai#2015)

.github/workflows/docker_build.yml

@@ -4,7 +4,6 @@ on:
  push:
  branches:
  - master
- - docker-build
 
 jobs:
  build:

Dockerfile

@@ -2,24 +2,28 @@ FROM python:3.7.4-stretch
 
 WORKDIR /home/user
 
-RUN apt-get update && apt-get install -y curl git pkg-config cmake
+RUN apt-get update && apt-get install -y \
+ curl \
+ git \
+ pkg-config \
+ cmake \
+ libpoppler-cpp-dev \
+ tesseract-ocr \
+ libtesseract-dev \
+ poppler-utils && \
+ rm -rf /var/lib/apt/lists/*
 
 # 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 apt-get install libpoppler-cpp-dev pkg-config -y --fix-missing
-
-# Install Tesseract
-RUN apt-get install tesseract-ocr libtesseract-dev poppler-utils -y
-
 # copy code
 COPY haystack /home/user/haystack
 
 # install as a package
 COPY setup.py requirements.txt README.md /home/user/
 RUN pip install --upgrade pip
-RUN pip install -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
 RUN pip install -e .
 RUN python3 -c "from haystack.utils.docker import cache_models;cache_models()"
 

Dockerfile-GPU

@@ -1,4 +1,4 @@
-FROM  nvidia/cuda:11.1-runtime-ubuntu20.04
+FROM nvidia/cuda:11.1-runtime-ubuntu20.04
 
 WORKDIR /home/user
 
@@ -11,7 +11,7 @@ RUN mkdir -p /home/user/file-upload && chmod 777 /home/user/file-upload
 # 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 \
+ apt-get install -y \
  cmake \
  curl \
  git \
@@ -25,7 +25,8 @@ RUN apt-get update && apt-get install -y software-properties-common && \
  python3.7-distutils \
  swig \
  tesseract-ocr \
- wget
+ wget && \
+ rm -rf /var/lib/apt/lists/*
 
 # Install PDF converter
 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
@@ -40,9 +41,9 @@ COPY setup.py requirements.txt README.md /home/user/
 RUN pip install --upgrade pip
 RUN echo "Install required packages" && \
  # Install PyTorch for CUDA 11
- pip3 install torch==1.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html && \
- # Install from requirements.txt 
- pip3 install -r requirements.txt
+ pip3 install --no-cache-dir torch==1.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html && \
+ # Install from requirements.txt
+ pip3 install --no-cache-dir -r requirements.txt
 
 # copy saved models
 COPY README.md models* /home/user/models/