refactor Dockerfile and requirements.txt: update base image, consolidate dependencies, and adjust NLTK data download

Dockerfile

@@ -1,39 +1,43 @@
-# SmartAudit-Env Dockerfile
-# Supports: HF Space (Gradio on :7860) and REST API (FastAPI on :8000)
-#
-# Build:  docker build -t smartaudit-env .
-# Run UI: docker run -p 7860:7860 smartaudit-env
-# Run API:docker run -p 8000:8000 smartaudit-env python -m uvicorn server:app --host 0.0.0.0 --port 8000
-
-FROM python:3.11-slim
-
-# ---- System deps ----
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential \
-    curl \
+ARG BASE_IMAGE=ghcr.io/meta-pytorch/openenv-base:latest
+
+# -------- BUILDER STAGE --------
+FROM python:3.12-slim AS builder
+
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        git curl build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# ---- Create non-root user (required by HF Spaces) ----
-RUN useradd -m -u 1000 user
-USER user
-ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH \
-    PYTHONDONTWRITEBYTECODE=1 \
-    PYTHONUNBUFFERED=1
+COPY . /app/env
+WORKDIR /app/env
+
+# Install all deps except openenv (which lives in the base image)
+RUN --mount=type=cache,target=/root/.cache/pip \
+    grep -v 'openenv' requirements.txt | \
+    pip install --target /app/packages -r /dev/stdin
+
+
+# -------- RUNTIME STAGE --------
+FROM ${BASE_IMAGE}
 
 WORKDIR /app
 
-# ---- Python deps ----
-COPY --chown=user requirements.txt .
-RUN pip install --no-cache-dir --upgrade pip \
- && pip install --no-cache-dir -r requirements.txt
+COPY --from=builder /app/env /app/env
+COPY --from=builder /app/packages /app/packages
+
+# Download NLTK data
+RUN PYTHONPATH=/app/packages python -m nltk.downloader \
+        wordnet omw-1.4 stopwords punkt \
+        averaged_perceptron_tagger_eng punkt_tab
 
-# ---- Application code ----
-COPY --chown=user . .
+# /app/packages first so our versions win; openenv comes from base image's site-packages
+ENV PYTHONPATH="/app/packages:/app/env:$PYTHONPATH"
 
-# ---- HF Space metadata (must expose port 7860) ----
-EXPOSE 7860 8000
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:7860/health || exit 1
 
-# ---- Default: launch Gradio UI ----
+ENTRYPOINT []
 CMD ["python", "-m", "uvicorn", "server.app:app", \
      "--host", "0.0.0.0", "--port", "7860", "--app-dir", "/app/env"]

requirements.txt

@@ -9,5 +9,4 @@ pandas==2.2.2
 numpy==2.1.1
 scikit-learn==1.5.0
 sentence-transformers==3.0.1
-nltk==3.9.4
-openenv[core]>=0.2.0
+nltk==3.9.4