Dockerfile

# Dockerfile for Marine Species Identification API on HuggingFace Spaces
# Multi-stage build to handle model downloading with proper permissions

# Stage 1: Download models as root
FROM python:3.10-slim AS model-builder

# Install system dependencies for model downloading
RUN apt-get update && apt-get install -y \
    wget \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/*

# Install huggingface_hub for downloading models
RUN pip install huggingface_hub

# Create models directory
RUN mkdir -p /models

# Create download script
RUN echo 'from huggingface_hub import hf_hub_download\n\
import os\n\
\n\
# Download model files\n\
print("Downloading model files...")\n\
hf_hub_download("seamo-ai/marina-species-v1", "marina-benthic-33k.pt", local_dir="/models", local_dir_use_symlinks=False)\n\
hf_hub_download("seamo-ai/marina-species-v1", "marina-benthic-33k.names", local_dir="/models", local_dir_use_symlinks=False)\n\
\n\
# Download sample images\n\
print("Downloading sample images...")\n\
sample_images = [\n\
    "crab.png", "fish.png", "fish_2.png", "fish_3.png", "fish_4.png", "fish_5.png",\n\
    "flat_fish.png", "flat_red_fish.png", "jelly.png", "jelly_2.png", "jelly_3.png",\n\
    "puff.png", "red_fish.png", "red_fish_2.png", "scene.png", "scene_2.png",\n\
    "scene_3.png", "scene_4.png", "scene_5.png", "scene_6.png", "soft_coral.png",\n\
    "starfish.png", "starfish_2.png"\n\
]\n\
\n\
for img in sample_images:\n\
    try:\n\
        hf_hub_download("seamo-ai/marina-species-v1", f"images/{img}", local_dir="/models", local_dir_use_symlinks=False)\n\
        print(f"Downloaded {img}")\n\
    except Exception as e:\n\
        print(f"Failed to download {img}: {e}")\n\
\n\
print("Download complete!")' > /tmp/download_models.py

# Run the download script
RUN python3 /tmp/download_models.py

# Stage 2: Build the application
FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    ffmpeg \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libglib2.0-0 \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Set up a new user named "user" with user ID 1000
RUN useradd -m -u 1000 user

# Switch to the "user" user
USER user

# Set home to the user's home directory
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH

# Set the working directory to the user's home directory
WORKDIR $HOME/app

# Set environment variables for HuggingFace and ML libraries
ENV HF_HUB_OFFLINE=1
ENV TRANSFORMERS_NO_ADVISORY_WARNINGS=1
ENV PYTHONPATH=$HOME/app
ENV TORCH_HOME=$HOME/.cache/torch
ENV HF_HOME=$HOME/.cache/huggingface

# Copy the requirements file and install dependencies
COPY --chown=user ./requirements.txt requirements.txt
RUN pip install --no-cache-dir --upgrade pip
RUN pip install --no-cache-dir --user -r requirements.txt

# Copy the downloaded models from the builder stage
COPY --chown=user --from=model-builder /models $HOME/app/models

# Copy the application code
COPY --chown=user ./app app

# Copy templates and static files for dashboard
COPY --chown=user ./templates templates
COPY --chown=user ./static static

# Copy sample images from models to static directory for web access
RUN mkdir -p static/images/samples
RUN if [ -d "$HOME/app/models/images" ]; then cp $HOME/app/models/images/*.png static/images/samples/ 2>/dev/null || true; fi

# Create necessary directories
RUN mkdir -p $HOME/.cache/huggingface $HOME/.cache/torch

# Expose port 7860 (HuggingFace Spaces standard)
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# Tell uvicorn to run on port 7860, which is the standard for HF Spaces
# Use 0.0.0.0 to make it accessible from outside the container
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]