Dockerfile.fallback

# Use official Python 3.12 slim image
FROM python:3.12-slim

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

# Set work directory
WORKDIR /app

# Install system dependencies in a single layer
RUN apt-get update && apt-get install -y \
    curl \
    build-essential \
    tesseract-ocr \
    libtesseract-dev \
    poppler-utils \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements file (if it exists)
COPY requirements.txt* /app/

# Install Python dependencies using pip
RUN pip install --no-cache-dir --upgrade pip

# Install dependencies from requirements.txt if it exists, otherwise install manually
RUN if [ -f "requirements.txt" ]; then \
        pip install --no-cache-dir -r requirements.txt; \
    else \
        pip install --no-cache-dir \
            streamlit>=1.28.0 \
            pandas>=2.0.0 \
            numpy>=1.24.0 \
            PyMuPDF>=1.23.0 \
            PyPDF2>=3.0.0 \
            doctr>=2.4.0 \
            pdf2image>=1.16.0 \
            spacy>=3.7.0 \
            torch>=2.0.0 \
            fuzzywuzzy>=0.18.0 \
            python-Levenshtein>=0.21.0 \
            openai>=1.0.0 \
            huggingface-hub>=0.19.0 \
            pydantic>=2.0.0 \
            pydantic-settings>=2.0.0 \
            python-dateutil>=2.8.0 \
            python-dotenv>=1.0.0; \
    fi

# Install PyTorch with CPU support
RUN pip3 install torch torchvision torchaudio

# Install spaCy models
RUN python -m spacy download en_core_web_sm

# Create temp directory for file processing
RUN mkdir -p /app/temp && chmod 777 /app/temp

# Copy the source code
COPY src/ /app/src/
COPY main.py /app/

# Expose the port Streamlit will run on
EXPOSE 8501

# Set environment variables for Streamlit
ENV STREAMLIT_SERVER_PORT=8501
ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0
ENV STREAMLIT_SERVER_HEADLESS=true
ENV STREAMLIT_SERVER_ENABLE_CORS=false
ENV STREAMLIT_SERVER_ENABLE_XSRF_PROTECTION=false

# Run the Streamlit application
CMD ["streamlit", "run", "main.py", "--server.port=8501", "--server.address=0.0.0.0"]