Dockerfile.cpu

# CPU-Only Dockerfile (No GPU required)

# --- Builder Stage ---
FROM python:3.11-slim AS builder

# Set DEBIAN_FRONTEND to noninteractive to avoid prompts during apt-get install
ENV DEBIAN_FRONTEND=noninteractive

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    aria2 \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy the uv binary for fast package installation
COPY --from=ghcr.io/astral-sh/uv:0.2.9 /uv /usr/local/bin/

# Create and activate a virtual environment
ENV VIRTUAL_ENV=/opt/venv
RUN python3 -m venv $VIRTUAL_ENV
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

# Copy your requirements file
COPY requirements.txt .

# Install Python dependencies using uv (CPU-only versions)
RUN --mount=type=cache,target=/root/.cache/uv \
    echo "Installing Python packages..." && \
    uv pip install -r requirements.txt && \
    echo "Python packages installed successfully"

# Download NLTK data with progress indication
RUN echo "Downloading NLTK data packages..." && \
    python3 -c "import nltk; \
    print('Downloading punkt...'); nltk.download('punkt', quiet=False); \
    print('Downloading stopwords...'); nltk.download('stopwords', quiet=False); \
    print('Downloading averaged_perceptron_tagger...'); nltk.download('averaged_perceptron_tagger', quiet=False); \
    print('Downloading maxent_ne_chunker...'); nltk.download('maxent_ne_chunker', quiet=False); \
    print('Downloading words...'); nltk.download('words', quiet=False); \
    print('All NLTK data downloaded successfully')"

# --- Final Stage ---
FROM python:3.11-slim AS final

ENV DEBIAN_FRONTEND=noninteractive

# Install only the runtime system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    aria2 \
    && rm -rf /var/lib/apt/lists/*

# Copy the virtual environment with installed packages from the builder stage
COPY --from=builder /opt/venv /opt/venv

# Copy the application code
COPY ./api /app/api

# Set the working directory
WORKDIR /app

# Make the virtual environment's binaries available
ENV PATH="/opt/venv/bin:$PATH"

# Set environment for CPU-only operation
ENV CUDA_VISIBLE_DEVICES=""
ENV OMP_NUM_THREADS=4

# Expose the port the app runs on
EXPOSE 8000

# Command to run the CPU-only FastAPI application
CMD ["python3", "-m", "uvicorn", "api.main_cpu:app", "--host", "0.0.0.0", "--port", "8000"]