Dockerfile

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

# Set working directory
WORKDIR /app

# Prevent Python from writing pyc files and buffering stdout/stderr
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    && rm -rf /lib/apt/lists/*

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

# Copy application source code
COPY gemma_code_llm/ ./gemma_code_llm/
COPY static/ ./static/

# Expose port
EXPOSE 7860

# Default environment variables
ENV BASE_MODEL="google/gemma-3-1b-it"
ENV ADAPTER_PATH="/app/outputs/gemma-code-lora"
ENV QUANTIZATION="none"
ENV DTYPE="auto"
ENV TRUST_REMOTE_CODE="0"

# Start FastAPI application
CMD ["uvicorn", "gemma_code_llm.api:app", "--host", "0.0.0.0", "--port", "7860"]