Dockerfile

# 1. Use the stable PyTorch 2.0.1 base image
FROM pytorch/pytorch:2.0.1-cuda11.7-cudnn8-runtime

# Set working directory
WORKDIR /app

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

# 2. Copy requirements
COPY requirements.txt ./

# 3. CRITICAL: Force reinstall to ensure we get Transformers 4.32.0 and NumPy 1.24.4
# This overwrites any pre-installed versions in the base image
RUN pip install --no-cache-dir --upgrade --force-reinstall -r requirements.txt

# 4. Download spaCy model
RUN python3 -m spacy download en_core_web_sm

# 5. Copy your source code (Ensure your code is in src/streamlit_app.py)
COPY src/ ./src/

# 6. Expose port and run
EXPOSE 8501
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]