Dockerfile

# Use NVIDIA CUDA base image with Ubuntu and Python support
FROM nvidia/cuda:12.1.1-devel-ubuntu22.04

# Set working directory
WORKDIR /app

# Install Python and system dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3-pip \
    python3.10-venv \
    build-essential \
    cmake \
    git \
    curl \
    wget \
    && rm -rf /var/lib/apt/lists/*

# Use python3.10 as default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1

# Upgrade pip
RUN pip install --upgrade pip

# Set CUDA build flag for llama-cpp-python
ENV CMAKE_ARGS="-DLLAMA_CUBLAS=on"

# Copy requirements first for layer caching
COPY requirements.txt .

# Install dependencies (llama-cpp-python will compile with CUDA here)
RUN pip install --no-cache-dir -r requirements.txt

# Copy app code
COPY . .

# Create models directory
RUN mkdir -p models

# Expose Gradio port
EXPOSE 7860

# Environment for Gradio
ENV GRADIO_SERVER_NAME="0.0.0.0"
ENV GRADIO_SERVER_PORT=7860

# Run the app
CMD ["python", "app.py"]