FROM python:3.10-slim

WORKDIR /app

# Install system dependencies for PDF processing and ML
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-eng \
    poppler-utils \
    libgomp1 \
    git \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements and install Python packages
COPY backend/requirements.txt requirements.txt
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY backend/ .

# Set environment variables for HuggingFace and performance
ENV TRANSFORMERS_CACHE=/app/.cache/huggingface \
    HF_HOME=/app/.cache/huggingface \
    PYTHONUNBUFFERED=1 \
    TOKENIZERS_PARALLELISM=false

# Create cache directory with proper permissions
RUN mkdir -p /app/.cache/huggingface && chmod -R 777 /app/.cache

EXPOSE 7860

CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]