ARG build_image
ARG base_immage

FROM $build_image AS build-image

ARG haystack_version
ARG haystack_extras
ARG torch_scatter

RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential gcc git curl \
    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

# 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 python -m venv --system-site-packages /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

RUN pip install --upgrade pip && \
    pip install --no-cache-dir .${haystack_extras} && \
    pip install --no-cache-dir ./rest_api && \
    pip install --no-cache-dir torch-scatter -f $torch_scatter

FROM $base_immage 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"