Dockerfile

FROM python:3.9-slim

# Set working directory
RUN useradd -m -u 1000 user

WORKDIR /app

# Set environment variables for optimization
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1
ENV TOKENIZERS_PARALLELISM=false
ENV HF_HUB_DISABLE_SYMLINKS_WARNING=1
ENV  HF_HOME=/data/.huggingface 

RUN mkdir -p /data/chroma_db && chown -R user:user /data/chroma_db

# Set environment variables for persistent mode
ENV PERSISTENT_MODE=true
ENV CHROMA_PERSIST_DIR=/data/chroma_db
ENV CHROMA_COLLECTION_NAME=creative_jobs_rag

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

# Copy requirements first for better caching
COPY --chown=user requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Download NLTK data during build
RUN python -c "import nltk; \
    nltk.download('punkt', quiet=True); \
    nltk.download('punkt_tab', quiet=True); \
    nltk.download('wordnet', quiet=True); \
    nltk.download('omw-1.4', quiet=True); \
    nltk.download('stopwords', quiet=True); \
    nltk.download('averaged_perceptron_tagger', quiet=True); \
    nltk.download('maxent_ne_chunker', quiet=True); \
    nltk.download('words', quiet=True);" || true

# Pre-download SentenceTransformer model to avoid meta tensor issues
RUN python -c "from sentence_transformers import SentenceTransformer; \
    import torch; \
    torch.set_num_threads(1); \
    model = SentenceTransformer('all-MiniLM-L6-v2', device='cpu'); \
    model.encode(['test'], show_progress_bar=False);" || true

# Copy application code
COPY --chown=user . .

# Create necessary directories
RUN mkdir -p /app/temp /app/cache

# Expose port
EXPOSE 8501

# Health check
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

# Run the application
ENTRYPOINT ["streamlit", "run", "streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]