Dockerfile

FROM python:3.11-slim

WORKDIR /app

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

# Pre-download the embedding model (~420MB, cached in Docker layer)
RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')"

# Copy application code and data
COPY . .

# Build ChromaDB at image build time (no binary files in git)
RUN python -c "import sys; sys.path.insert(0, 'src'); from rag.build_vector_db import build_vector_database; build_vector_database()"

# HF Spaces expects port 7860
EXPOSE 7860

CMD ["streamlit", "run", "src/web/app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.headless=true"]