Dockerfile

FROM nvidia/cuda:12.1.1-devel-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive

# Install base dependencies
RUN apt-get update && \
    apt-get install -y software-properties-common && \
    add-apt-repository ppa:deadsnakes/ppa && \
    apt-get update && \
    apt-get install -y \
        python3.10 \
        python3.10-venv \
        python3.10-distutils \
        python3-pip \
        wget \
        git \
        libgl1 \
        fontconfig \
        libglib2.0-0 \
        libxrender1 \
        libsm6 \
        libxext6 \
        poppler-utils && \
    rm -rf /var/lib/apt/lists/*

RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1

# Create app directory
WORKDIR /app

# Copy requirements first
COPY requirements.txt .

# Install PyTorch dependencies with explicit compatible versions for NVIDIA L4
RUN pip3 install --no-cache-dir --upgrade pip && \
    pip3 install --no-cache-dir torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu121 && \
    pip3 install --no-cache-dir transformers==4.36.2 && \
    pip3 install --no-cache-dir -r requirements.txt

# Copy the rest of the application
COPY . .

# Expose port
EXPOSE 7860

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