Dockerfile

FROM python:3.9-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    software-properties-common \
    git \
    poppler-utils \
    libpoppler-cpp-dev \
    tesseract-ocr \
    tesseract-ocr-eng \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for better caching
COPY requirements.txt ./
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Create necessary directories with proper permissions
RUN mkdir -p /tmp/uploads /tmp/processed /app/.cache/huggingface
RUN chmod -R 777 /tmp /app/.cache

# Set environment variables for caching and permissions
ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
ENV HF_HOME=/app/.cache/huggingface
ENV TORCH_HOME=/app/.cache/torch
ENV HF_DATASETS_CACHE=/app/.cache/huggingface/datasets

# Expose FastAPI port
EXPOSE 7860

# Health check for FastAPI
HEALTHCHECK CMD curl --fail http://localhost:7860/health || exit 1

# Run FastAPI application
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]