Update Dockerfile

Dockerfile

@@ -1,4 +1,5 @@
 # syntax=docker/dockerfile:1.6
+
 ARG PY_BASE=python:3.9-slim-bullseye
 FROM ${PY_BASE}
 
@@ -9,11 +10,12 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     OMP_NUM_THREADS=1 \
     TRANSFORMERS_CACHE=/cache/hf
 
-# Debug/cache-buster so Spaces definitely rebuilds this layer
+# Force a rebuild when you tweak deps
 ARG DEPS_REFRESH=2025-09-07-06
 ENV DEPS_REFRESH=$DEPS_REFRESH
 RUN echo "CACHEBUSTER=$DEPS_REFRESH"
 
+# System deps (tesseract + libs for opencv wheels)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ca-certificates curl \
     tesseract-ocr tesseract-ocr-eng tesseract-ocr-osd \
@@ -25,29 +27,39 @@ ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata
 WORKDIR /app
 COPY requirements.txt .
 
+# Install python deps
 RUN python -m pip install --upgrade pip setuptools wheel \
  && pip install --no-cache-dir -r requirements.txt
 
-# Install spaCy model that matches spaCy 3.2.x WITHOUT pulling new deps
+# Install spaCy model matching spaCy 3.2.x WITHOUT pulling new deps
 RUN pip install --no-deps \
   "en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.2.0/en_core_web_sm-3.2.0-py3-none-any.whl"
 
-# Quick runtime-safe sanity print (instead of `spacy validate`)
+# Robust version dump (no __version__ attribute assumptions)
 RUN python - <<'PY'
 import sys, pkgutil
-import pydantic, spacy, thinc, typing_extensions as t_ext
+try:
+    import importlib.metadata as md
+except ImportError:
+    import importlib_metadata as md  # py3.8 fallback (not used here)
+def v(name):
+    try: return md.version(name)
+    except md.PackageNotFoundError: return "not-installed"
 print("python:", sys.version.split()[0])
-print("pydantic:", pydantic.__version__)
-print("typing-extensions:", t_ext.__version__)
-print("spacy:", spacy.__version__, "thinc:", thinc.__version__)
+for name in ("pydantic","typing-extensions","spacy","thinc","en-core-web-sm"):
+    print(f"{name}:", v(name))
 print("has en_core_web_sm:", bool(pkgutil.find_loader("en_core_web_sm")))
 PY
 
+# App code
 COPY . .
+
+# Writable caches
 RUN mkdir -p /cache/hf /tmp && chmod -R 777 /cache /tmp
 
 ENV PORT=8000
 EXPOSE 8000
+
 HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
   CMD curl -fsS "http://127.0.0.1:${PORT}/health" || exit 1