Dockerfile

# Dockerfile — ClauseXplain v5.0
# WHY this exists: HF Spaces Docker builder ignores runtime.txt entirely
# and defaults to python:3.13 where torch<2.5 has no wheels.
# This Dockerfile pins Python 3.10 so torch==2.1.2 installs cleanly.

FROM python:3.10-slim

# System deps: git-lfs (HF model download), libgomp (torch CPU threading),
# libgl1 / libglib2 (pymupdf), build-essential (sentencepiece compile)
RUN apt-get update && apt-get install -y --no-install-recommends \
        git \
        git-lfs \
        libgomp1 \
        libgl1 \
        libglib2.0-0 \
        build-essential \
    && git lfs install \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy requirements first (layer-cache friendly)
COPY requirements.txt .

# Install Python deps — torch 2.1.2 has clean 3.10 wheels on PyPI
RUN pip install --no-cache-dir --upgrade pip \
    && pip install --no-cache-dir -r requirements.txt

# Copy application source
COPY app.py pdf_utils.py inference.py explanation.py utils.py ./

# HF Spaces runs as user 1000 — avoid permission issues
RUN useradd -m -u 1000 appuser \
    && chown -R appuser:appuser /app
USER 1000

EXPOSE 7860

# HF_HOME inside /app so the model cache is writable by user 1000
ENV HF_HOME=/app/.cache/huggingface \
    PYTHONUNBUFFERED=1

CMD ["python", "app.py"]