fix

Dockerfile

@@ -1,46 +1,42 @@
 FROM python:3.11-slim
+
 ENV DEBIAN_FRONTEND=noninteractive \
     PYTHONUNBUFFERED=1 \
-    # Tesseract path for pytesseract (your code reads this)
     TESSERACT_CMD=/usr/bin/tesseract \
-    # Default Chroma persistence (your code also reads CHROMA_DIR)
-    CHROMA_DIR=/data/chroma
+    CHROMA_DIR=/data/chroma \
+    PYTHONPATH=/app
 
 # System deps + Microsoft key via keyring (for msodbcsql17)
 RUN set -eux; \
     apt-get update; \
     apt-get install -y --no-install-recommends \
-        curl ca-certificates gnupg2 apt-transport-https \
-        unixodbc unixodbc-dev \
+        curl \
+        ca-certificates \
+        gnupg2 \
+        apt-transport-https \
+        unixodbc \
+        unixodbc-dev \
         ffmpeg \
-        # ---- Added for pdf2image + pytesseract ----
-        poppler-utils \          # provides pdftoppm / pdftocairo
-        tesseract-ocr \          # OCR engine
-        tesseract-ocr-eng        # English language data (pulled with tesseract on many distros, kept explicit)
+        poppler-utils \
+        tesseract-ocr \
+        tesseract-ocr-eng \
     ; \
     mkdir -p /etc/apt/keyrings; \
-    curl -fsSL https://packages.microsoft.com/keys/microsoft.asc \
-      | gpg --dearmor -o /etc/apt/keyrings/microsoft.gpg; \
-    echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/microsoft.gpg] https://packages.microsoft.com/debian/12/prod bookworm main" \
-      > /etc/apt/sources.list.d/mssql-release.list; \
+    curl -fsSL https://packages.microsoft.com/keys/microsoft.asc | gpg --dearmor -o /etc/apt/keyrings/microsoft.gpg; \
+    echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/microsoft.gpg] https://packages.microsoft.com/debian/12/prod bookworm main" > /etc/apt/sources.list.d/mssql-release.list; \
     apt-get update; \
     ACCEPT_EULA=Y apt-get install -y msodbcsql17; \
-    # Create a writable place for Chroma persistence
     mkdir -p /data/chroma; \
     rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
-# (Optional but helpful) make sure pip is recent and faster
 RUN python -m pip install --upgrade pip
-
 COPY requirements.txt /app/
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Your code
 COPY . /app
 
 EXPOSE 7860
 
-# Gunicorn entrypoint stays the same
 CMD ["gunicorn","--workers","2","--threads","4","--timeout","120","-b","0.0.0.0:7860","verification:app"]