haystack/docker/Dockerfile.base

ARG build_image
ARG base_image

FROM $build_image AS build-image

ARG DEBIAN_FRONTEND=noninteractive
ARG haystack_version
ARG haystack_extras

RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential gcc git curl cmake \
    tesseract-ocr libtesseract-dev poppler-utils

# Install PDF converter
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
WORKDIR /opt/haystack

# Use a virtualenv we can copy over the next build stage
RUN python3 -m venv --system-site-packages /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

RUN pip install --upgrade pip && \
    pip install --no-cache-dir -U torchaudio && \
    pip install --no-cache-dir .${haystack_extras} && \
    pip install --no-cache-dir ./rest_api


FROM $base_image AS final

COPY --from=build-image /opt/venv /opt/venv
COPY --from=build-image /opt/pdftotext /usr/local/bin
# pdftotext requires fontconfig runtime
RUN apt-get update && apt-get install -y libfontconfig && rm -rf /var/lib/apt/lists/*

ENV PATH="/opt/venv/bin:$PATH"

# The JSON schema is lazily generated at first usage, but we do it explicitly here for two reasons:
# - the schema will be already there when the container runs, saving the generation overhead when a container starts
# - derived images don't need to write the schema and can run with lower user privileges
RUN python3 -c "from haystack.utils.docker import cache_schema; cache_schema()"