Dockerfile

FROM python:3.10-slim

# Install system dependencies and build tools
RUN apt-get update && apt-get install -y \
    ffmpeg \
    git \
    curl \
    build-essential \
    cmake \
    libgomp1 \
 && apt-get clean && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy application files
COPY . /app

# Install Python dependencies, forcing CPU-only PyTorch
RUN pip install --upgrade pip \
 && pip install --index-url https://download.pytorch.org/whl/cpu \
      torch==2.1.0+cpu torchvision==0.16.0+cpu torchaudio==2.1.0+cpu \
 && pip install -r requirements.txt \
 && pip install huggingface_hub
&& pip install huggingface_hub

# Download GGUF model at build time into models/
RUN mkdir -p models \
 && python - <<EOF
from huggingface_hub import hf_hub_download
hf_hub_download(
    repo_id="TheBloke/Mistral-7B-Instruct-GPTQ",
    filename="mistral-7b-instruct-q4_k_m.gguf",
    cache_dir="models",
    library_name="llama-cpp-python"
)
EOF

# Expose port 7860 for Flask app
EXPOSE 7860

# Start the Flask application
CMD ["python", "app.py"]