oval
33997778f6
- Add .gitignore excluding .env, __pycache__, test_files (copyrighted PDFs), session logs, marker/ submodule, and other generated/private files - Add .env with local config (gitignored); expand .env.example with all supported environment variables - docker-compose.yml: all hardcoded values now use default pattern - Containerfile: install marker-pdf from GitHub instead of local submodule; fix AMD_COMPUTE default to false; sanitize default OLLAMA_HOST - Remove marker/ submodule from git tracking (keep local checkout via .gitignore) - Remove session transcript and copyrighted ENISA PDFs from git tracking - Sanitize local IPs in README, kubernetes deployment, deploy-podman.sh - Fix hardcoded paths in convert_both.py and compare_conversions.py - Update requirements.txt to reference GitHub instead of local --editable
81 lines
2.8 KiB
Docker
81 lines
2.8 KiB
Docker
# ===== Containerfile for marker-api =====
|
|
#
|
|
# Uses ROCm PyTorch base for broad GPU support (AMD + NVIDIA via CUDA).
|
|
# Ollama defaults to localhost:11434; override with env vars at runtime.
|
|
|
|
FROM rocm/pytorch:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.9.1
|
|
|
|
# install system deps & remove system-installed python3-blinker to avoid pip upgrade conflicts
|
|
RUN apt-get update && \
|
|
apt-get install -y --no-install-recommends \
|
|
curl ca-certificates tini procps git gcc g++ zlib1g-dev libjpeg-dev \
|
|
libpango-1.0-0 libharfbuzz0b libpangoft2-1.0-0 \
|
|
poppler-utils pandoc && \
|
|
apt-get remove -y python3-blinker || true && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
# ---- runtime ----
|
|
RUN groupadd -r marker && (groupadd -r render || true) && (groupadd -r video || true) && useradd -r -g marker -G render,video marker && \
|
|
mkdir -p /app/conversion_results /app/uploads /app/.cache && \
|
|
chown -R marker:marker /app
|
|
|
|
WORKDIR /app
|
|
|
|
# ---- deps ----
|
|
# Install marker-pdf from GitHub. For local builds with a cloned marker/
|
|
# directory, replace the line below with: -e /app/marker[full]
|
|
RUN pip install --no-cache-dir --break-system-packages \
|
|
--extra-index-url https://download.pytorch.org/whl/rocm7.2 \
|
|
"marker-pdf[full] @ git+https://github.com/VikParuchuri/marker.git" && \
|
|
pip install --no-cache-dir --break-system-packages flask gunicorn
|
|
|
|
# ---- font: download GoNotoCurrent-Regular.ttf at build time ----
|
|
# Find the marker package dir inside the installed package
|
|
RUN MARKER_DIR=$(python3 -c "import marker; print(marker.__path__[0])") && \
|
|
mkdir -p "$MARKER_DIR/static/fonts" && \
|
|
curl -sL -o "$MARKER_DIR/static/fonts/GoNotoCurrent-Regular.ttf" \
|
|
"https://models.datalab.to/artifacts/GoNotoCurrent-Regular.ttf" && \
|
|
chown marker:marker "$MARKER_DIR/static/fonts/GoNotoCurrent-Regular.ttf"
|
|
|
|
# ---- final image ----
|
|
COPY app.py /app/
|
|
COPY request_store.py /app/
|
|
COPY deepseek_ocr.py /app/
|
|
COPY gunicorn.conf.py /app/
|
|
COPY entrypoint.sh /app/entrypoint.sh
|
|
|
|
RUN chmod +x /app/entrypoint.sh
|
|
|
|
ENV HOME=/app
|
|
ENV PYTHONUNBUFFERED=1
|
|
ENV PYTHONDONTWRITEBYTECODE=1
|
|
ENV MARKER_OUTPUT_DIR=/app/conversion_results
|
|
ENV UPLOAD_DIR=/app/uploads
|
|
ENV RESULTS_DIR=/app/conversion_results
|
|
ENV SELF_URL=http://localhost:8001
|
|
ENV OLLAMA_HOST=http://localhost:11434
|
|
ENV DEESEEK_OCR_MODEL=deepseek-ocr
|
|
ENV AMD_COMPUTE=false
|
|
ENV TORCH_DEVICE=
|
|
ENV MODEL_DTYPE=float32
|
|
ENV PORT=8001
|
|
ENV HOST=0.0.0.0
|
|
ENV LLM_SERVICE=marker.services.ollama.OllamaService
|
|
ENV USE_LLM=false
|
|
ENV OPENAI_BASE_URL=
|
|
ENV OPENAI_API_KEY=
|
|
ENV OPENAI_MODEL=
|
|
ENV OCR_BACKEND=marker
|
|
ENV DEEPSEEK_OLLAMA_HOST=http://localhost:11434
|
|
ENV DEEPSEEK_OCR_MODEL=deepseek-ocr:latest
|
|
ENV DEEPSEEK_OCR_PROMPT="<|grounding|>Free OCR."
|
|
ENV API_KEY=
|
|
ENV GUNICORN_WORKERS=3
|
|
|
|
USER marker
|
|
|
|
EXPOSE 8001
|
|
|
|
ENTRYPOINT ["/app/entrypoint.sh"]
|
|
CMD ["gunicorn", "-c", "gunicorn.conf.py", "app:app_instance"]
|