Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.11-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE 1
ENV PYTHONUNBUFFERED 1
ENV HOME=/home/user
ENV PATH=/home/user/.local/bin:$PATH
ENV PYTHONPATH=$HOME/app

# Install system dependencies
USER root
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Create a non-root user
RUN useradd -m -u 1000 user
USER user
WORKDIR $HOME/app

# Copy requirements and install dependencies
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# Pre-download models to avoid cold-start lag and runtime network issues
# We download both the embedding model and the reranker
RUN python -c "from sentence_transformers import SentenceTransformer, CrossEncoder; \
    SentenceTransformer('BAAI/bge-small-en-v1.5'); \
    CrossEncoder('BAAI/bge-reranker-base')"

# Copy the rest of the application code
COPY --chown=user . .

# Hugging Face Spaces expect the app on port 7860
EXPOSE 7860

# Run the application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]