Add PDF converter in Dockerfiles (deepset-ai#877)

jamescalam · Mar 8, 2021 · 6d00eff · 6d00eff
1 parent 81b8329
commit 6d00eff
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/Dockerfile b/Dockerfile
@@ -4,6 +4,10 @@ WORKDIR /home/user
 
 RUN apt-get update && apt-get install -y curl git pkg-config cmake
 
+# 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
+
 # copy code
 COPY haystack /home/user/haystack
 

diff --git a/Dockerfile-GPU b/Dockerfile-GPU
@@ -3,7 +3,7 @@ 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 git pkg-config cmake swig
+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
@@ -12,6 +12,10 @@ ENV LANG=C.UTF-8
 RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.7 1
 RUN update-alternatives --set python3 /usr/bin/python3.7
 
+# 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
+
 # copy code
 COPY haystack /home/user/haystack