Dockerfile

# Use NVIDIA CUDA base image with Python
FROM nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV TRANSFORMERS_CACHE=/app/cache
ENV PYTHONUNBUFFERED=1
ENV PORT=7860

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3-pip \
    git \
    && rm -rf /var/lib/apt/lists/*

# Create cache directory and set permissions
RUN mkdir -p /app/cache && \
    mkdir -p /app/model/medical_llama_3b && \
    chmod -R 777 /app/cache

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

# Update pip and install dependencies
RUN python3 -m pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# Install specific numpy version to fix compatibility
RUN pip install --no-cache-dir "numpy<2.0.0"

# Copy the rest of the application
COPY . .

# Expose port
EXPOSE 7860

# Set environment variables for GPU
ENV NVIDIA_VISIBLE_DEVICES=all
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

# Command to run the application
CMD ["python3", "-m", "uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]