Update Dockerfile

Dockerfile

@@ -1,6 +1,4 @@
 # syntax=docker/dockerfile:1.6
-
-# ===== Python base (3.9) =====
 ARG PY_BASE=python:3.9-slim-bullseye
 FROM ${PY_BASE}
 
@@ -11,47 +9,46 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     OMP_NUM_THREADS=1 \
     TRANSFORMERS_CACHE=/cache/hf
 
-# ---- System deps (Tesseract + libs OpenCV wheels expect) ----
+# Debug/cache-buster so Spaces definitely rebuilds this layer
+ARG DEPS_REFRESH=2025-09-07-06
+ENV DEPS_REFRESH=$DEPS_REFRESH
+RUN echo "CACHEBUSTER=$DEPS_REFRESH"
+
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ca-certificates curl \
     tesseract-ocr tesseract-ocr-eng tesseract-ocr-osd \
     libgl1 libglib2.0-0 \
  && rm -rf /var/lib/apt/lists/*
 
-# Tesseract language data path (Debian/Ubuntu)
 ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata
 
-# ---- App setup ----
 WORKDIR /app
-
-# Install Python deps first for better layer caching
 COPY requirements.txt .
 
 RUN python -m pip install --upgrade pip setuptools wheel \
- && pip install -r requirements.txt 
-
-
+ && pip install --no-cache-dir -r requirements.txt
 
+# Install spaCy model that matches 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"
 
-# RUN python -m spacy validate
+# Quick runtime-safe sanity print (instead of `spacy validate`)
+RUN python - <<'PY'
+import sys, pkgutil
+import pydantic, spacy, thinc, typing_extensions as t_ext
+print("python:", sys.version.split()[0])
+print("pydantic:", pydantic.__version__)
+print("typing-extensions:", t_ext.__version__)
+print("spacy:", spacy.__version__, "thinc:", thinc.__version__)
+print("has en_core_web_sm:", bool(pkgutil.find_loader("en_core_web_sm")))
+PY
 
-
-
-# Copy the rest of your app
 COPY . .
-
-# Writable caches (for HF/torch/tmp)
 RUN mkdir -p /cache/hf /tmp && chmod -R 777 /cache /tmp
 
-# App port & healthcheck
 ENV PORT=8000
 EXPOSE 8000
-
 HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
   CMD curl -fsS "http://127.0.0.1:${PORT}/health" || exit 1
 
-# Use $PORT when present (Render sets it), default to 8000 locally - application started
 CMD ["sh","-c","uvicorn backend:app --host 0.0.0.0 --port ${PORT:-8000}"]
-