# Stage 1: Builder (for heavy Python dependencies including CUDA-enabled PyTorch) FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 as builder WORKDIR /opt/venv # Install Python 3.11 and venv in the builder stage RUN apt-get update && apt-get install -y python3.11 python3.11-venv # Create a virtual environment and install Python dependencies COPY requirements.txt . COPY patches/ ./patches/ RUN python3.11 -m venv . && . /opt/venv/bin/activate && pip install --no-cache-dir -r requirements.txt && \ chmod +x ./patches/fix-misaki-espeak.sh && ./patches/fix-misaki-espeak.sh # Stage 2: Runner (The final slim image) FROM python:3.11-slim # Install system dependencies needed at runtime # ffmpeg is required for audio conversion # espeak-ng is required for Kokoro TTS phonemization RUN apt-get update && apt-get install -y --no-install-recommends \ ffmpeg \ espeak-ng \ && rm -rf /var/lib/apt/lists/* # Create an unprivileged user RUN useradd --create-home --shell /bin/bash appuser # Set working directory for the application code WORKDIR /home/appuser # Copy the entire virtual environment from the builder stage COPY --from=builder /opt/venv /opt/venv # Add venv to PATH and PYTHONPATH so packages and scripts work correctly ENV PATH="/opt/venv/bin:$PATH" ENV PYTHONPATH="/opt/venv/lib/python3.11/site-packages:$PYTHONPATH" # Create espeak-ng-data symlink for misaki compatibility RUN mkdir -p /home/runner/work/espeakng-loader/espeakng-loader/espeak-ng/_dynamic/share/ && \ ln -sf /usr/lib/x86_64-linux-gnu/espeak-ng-data /home/runner/work/espeakng-loader/espeakng-loader/espeak-ng/_dynamic/share/espeak-ng-data # Copy the application code into the container COPY app/ ./app # Expose the application port EXPOSE 8000 # Run as the unprivileged user USER appuser # Command to run the application using uvicorn for development with auto-reloading CMD ["python3.11", "-m", "uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--log-level", "debug"]