Production API

[floresdwm]

Hi guys, first of all congratulations for amazing repo and what you are delivering to the community!

Second, trying to create a docker image to put the models online as 'endpoints' for generate, the libraries using torch and so on, its very huge.

What is the recommendation to put the models ready and online trained using this library?

Thanks in advance,

Douglas

[floresdwm]

I have figure out, how to reduce the size of final image.

# Use Python 3.10 slim image as base
FROM python:3.10-slim

# Set working directory
WORKDIR /app

# Copy source code into container
COPY . .

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

# Install torch first
RUN pip install --no-cache-dir "torch>=1.10.0,<2.0" -f https://download.pytorch.org/whl/cpu

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Expose port if you have a flask api
EXPOSE 8000

# Run Flask application
CMD ["python3", "-m", "app.py"]