legal-doc-masker/mineru/Dockerfile

46 lines
1.1 KiB
Docker

FROM python:3.12-slim
WORKDIR /app
# Install system dependencies
RUN apt-get update && apt-get install -y \
build-essential \
libreoffice \
wget \
&& rm -rf /var/lib/apt/lists/*
RUN pip install --upgrade pip
RUN pip install uv
# Configure uv and install mineru
ENV UV_SYSTEM_PYTHON=1
RUN uv pip install --system -U "mineru[core]"
# Copy requirements first to leverage Docker cache
# COPY requirements.txt .
# RUN pip install huggingface_hub
# RUN wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
# RUN wget https://raw.githubusercontent.com/opendatalab/MinerU/refs/heads/release-1.3.1/scripts/download_models_hf.py -O download_models_hf.py
# RUN python download_models_hf.py
RUN mineru-models-download -s modelscope -m pipeline
# RUN pip install --no-cache-dir -r requirements.txt
# RUN pip install -U magic-pdf[full]
# Copy the rest of the application
# COPY . .
# Create storage directories
# RUN mkdir -p storage/uploads storage/processed
# Expose the port the app runs on
EXPOSE 8000
# Command to run the application
CMD ["mineru-api", "--host", "0.0.0.0", "--port", "8000"]