Dockerfile

# ── Dockerfile ─────────────────────────────────────────────────────────
FROM python:3.10-slim

# Set environment
ENV PYTHONUNBUFFERED=1 \
    STREAMLIT_DATA_DIR=/tmp/.streamlit \
    XDG_STATE_HOME=/tmp \
    STREAMLIT_BROWSER_GATHERUSAGESTATS=false

# OS deps
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential curl && rm -rf /var/lib/apt/lists/*

# Pin numpy to avoid C-extension mismatches
RUN pip install --no-cache-dir numpy==1.23.5

# Install core Python libs + ML/embeddings
RUN pip install --no-cache-dir \
    spacy==3.5.2 transformers huggingface-hub scikit-learn httpx pandas plotly \
    fpdf streamlit streamlit-agraph networkx xmltodict feedparser pydantic openai \
    google-generative-ai

# Download spaCy model
RUN python -m spacy download en_core_web_sm

# Set workdir
WORKDIR /app
COPY . /app
EXPOSE 8501

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