Dockerfile

FROM python:3.9-slim

WORKDIR /app

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

# Set environment variables for cache
ENV TRANSFORMERS_CACHE=/app/hf_cache
ENV HF_HOME=/app/hf_cache
ENV HF_DATASETS_CACHE=/app/hf_cache

# Copy dependency list and install Python packages
COPY requirements.txt ./
RUN pip install --no-cache-dir -r requirements.txt

# Pre-download the Hugging Face model and tokenizer
RUN python -c "from transformers import AutoTokenizer, AutoModelForSequenceClassification; \
    AutoTokenizer.from_pretrained('finiteautomata/bertweet-base-sentiment-analysis', cache_dir='/app/hf_cache'); \
    AutoModelForSequenceClassification.from_pretrained('finiteautomata/bertweet-base-sentiment-analysis', cache_dir='/app/hf_cache')"

# Copy app code
COPY app.py ./

# Expose Streamlit port
EXPOSE 8501

# Healthcheck (optional)
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health || exit 1

# Start Streamlit
ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]