Dockerfile

# ─────────────────────────────────────────────
# Dockerfile for Hugging Face Spaces (Docker SDK)
# Free tier: 2 vCPU · 16 GB RAM · port 7860
# ─────────────────────────────────────────────
FROM python:3.11-slim

# System packages needed by faiss-cpu / pdf parsing / openpyxl
RUN apt-get update && apt-get install -y --no-install-recommends \
        build-essential \
        curl \
        git \
    && rm -rf /var/lib/apt/lists/*

# HF Spaces requirement: run as uid 1000
RUN useradd -m -u 1000 user
USER user

ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH

WORKDIR $HOME/app

# Install uv
RUN pip install --no-cache-dir uv

# Copy dependency manifest & install
COPY --chown=user pyproject.toml .
RUN uv sync --no-dev

# Copy application source
COPY --chown=user chatbot_final.py .

# Create data directories (ephemeral on free tier; use HF Storage for persistence)
RUN mkdir -p /home/user/app/data/pdfs \
             /home/user/app/data/embeddings \
             /home/user/app/data/users

# Default env vars (can be overridden via HF Space Settings → Variables / Secrets)
ENV PDF_STORE_DIR=/home/user/app/data/pdfs \
    EMBEDDINGS_STORE_DIR=/home/user/app/data/embeddings \
    USER_XL_PATH=/home/user/app/data/users/users.xlsx \
    LLM_BACKEND=huggingface \
    HF_MODEL_ID=mistralai/Mistral-7B-Instruct-v0.3

EXPOSE 7860

HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD curl --fail http://localhost:7860/_stcore/health || exit 1

CMD ["/home/user/app/.venv/bin/streamlit", "run", "chatbot_final.py", \
     "--server.port=7860", \
     "--server.address=0.0.0.0", \
     "--server.headless=true"]