Dockerfile

# Build stage
FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS builder

WORKDIR /app

# Copy dependency files
COPY pyproject.toml uv.lock ./

# Install dependencies into .venv
RUN uv sync --frozen --no-dev

# Download spaCy models into .venv
RUN .venv/bin/python -m spacy download en_core_web_sm && \
    .venv/bin/python -m spacy download pt_core_news_sm

# Runtime stage
FROM python:3.12-slim-bookworm

WORKDIR /app

# Install runtime dependencies (tesseract, languages, and poppler)
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-por \
    tesseract-ocr-eng \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# Copy virtual environment from builder
COPY --from=builder /app/.venv /app/.venv

# Copy application code
COPY . .

# Expose port
EXPOSE 8080

# Set environment variables
ENV PATH="/app/.venv/bin:$PATH"

# Run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8080"]