dockerfile nltk update

Dockerfile

@@ -1,6 +1,6 @@
 ARG BASE_IMAGE=ghcr.io/meta-pytorch/openenv-base:latest
 
-# -------- BUILDER STAGE (Python 3.12) --------
+# -------- BUILDER STAGE --------
 FROM python:3.12-slim AS builder
 
 WORKDIR /app
@@ -8,18 +8,16 @@ WORKDIR /app
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         git curl \
-        build-essential \                  
+        build-essential \
     && rm -rf /var/lib/apt/lists/*
 
 COPY . /app/env
 WORKDIR /app/env
 
-# Install uv
 RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
     mv /root/.local/bin/uv /usr/local/bin/uv && \
     mv /root/.local/bin/uvx /usr/local/bin/uvx
 
-# Install dependencies
 RUN --mount=type=cache,target=/root/.cache/uv \
     if [ -f uv.lock ]; then \
         uv sync --frozen --no-install-project --no-editable; \
@@ -34,6 +32,11 @@ RUN --mount=type=cache,target=/root/.cache/uv \
         uv sync --no-editable; \
     fi
 
+# ← moved here, after venv is built, nltk is guaranteed to exist
+RUN /app/env/.venv/bin/python -m nltk.downloader \
+        wordnet omw-1.4 stopwords punkt \
+        averaged_perceptron_tagger_eng punkt_tab
+
 
 # -------- RUNTIME STAGE --------
 FROM ${BASE_IMAGE}
@@ -42,12 +45,12 @@ WORKDIR /app
 
 COPY --from=builder /app/env/.venv /app/.venv
 COPY --from=builder /app/env /app/env
+# NLTK data sits in /root/nltk_data inside the builder — copy it over too
+COPY --from=builder /root/nltk_data /root/nltk_data
 
 ENV PATH="/app/.venv/bin:$PATH"
 ENV PYTHONPATH="/app/env:$PYTHONPATH"
 
-RUN /app/.venv/bin/python -m nltk.downloader wordnet omw-1.4 stopwords punkt averaged_perceptron_tagger_eng punkt_tab
-
 HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
     CMD curl -f http://localhost:7860/health || exit 1