Dockerfile

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

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1
ENV POETRY_VERSION=1.8.2
ENV POETRY_HOME="/opt/poetry"
ENV POETRY_VENV_IN_PROJECT=1
ENV POETRY_NO_INTERACTION=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/*

# Install Poetry
RUN curl -sSL https://install.python-poetry.org | python3 - \
    && export PATH="/opt/poetry/bin:$PATH" \
    && poetry --version

# Add Poetry to PATH
ENV PATH="/opt/poetry/bin:$PATH"

# Copy only Poetry configuration files first (for better caching)
COPY pyproject.toml poetry.lock* /app/

# Configure Poetry and install dependencies
RUN poetry config virtualenvs.create false \
    && poetry lock --no-update \
    && poetry install --no-interaction --no-ansi --only main

# Install PyTorch with CPU support (adjust based on your needs)
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 (this layer will be rebuilt when code changes)
COPY src/ ./src/
# COPY src/app.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
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

ENTRYPOINT ["streamlit", "run", "src/app.py", "--server.port=8501", "--server.address=0.0.0.0"]