yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-12-26 14:38:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: build pdftotext from sources (#3746)

Browse Source 
* build pdftotext from sources

* trigger the build on my own PR - to be reverted

* trigger the build on my own PR - to be reverted

* Update docker_release.yml
This commit is contained in:
Massimiliano Pippi 2022-12-22 18:37:36 +01:00 committed by GitHub
parent 367c63ef1d
commit 450c3d4484
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
docker/Dockerfile.base
View File

@ -7,14 +7,18 @@ ARG haystack_version
ARG haystack_extras
RUN apt-get update && apt-get install -y --no-install-recommends \
build-essential gcc git curl \
build-essential gcc git curl cmake \
tesseract-ocr libtesseract-dev poppler-utils
# Install PDF converter
RUN curl -O https://dl.xpdfreader.com/xpdf-tools-linux-4.04.tar.gz && \
tar -xvf xpdf-tools-linux-4.04.tar.gz && \
cp xpdf-tools-linux-4.04/bin64/pdftotext /opt && \
rm -rf xpdf-tools-linux-4.04
RUN curl -O https://dl.xpdfreader.com/xpdf-4.04.tar.gz && \
tar -xvf xpdf-4.04.tar.gz && \
cd xpdf-4.04 && \
cmake . && \
make && \
cp xpdf/pdftotext /opt && \
cd .. && \
rm -rf xpdf-4.04
# Shallow clone Haystack repo, we'll install from the local sources
RUN git clone --depth=1 --branch=${haystack_version} https://github.com/deepset-ai/haystack.git /opt/haystack