docker

Dockerfile

@@ -1,61 +1,74 @@
-# Dockerfile
+# STAGE 1: BUILDER
+# This stage installs build tools and Python dependencies
+FROM python:3.13.7-slim AS builder
+
+ENV PYTHONUNBUFFERED=1 \
+    DEBIAN_FRONTEND=noninteractive
+
+# Install only the build-time dependencies needed for pip packages
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    pkg-config \
+    git \
+    curl \
+    libxml2-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Copy and install Python requirements to leverage Docker layer caching
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+
+# STAGE 2: FINAL
+# This is the lean, final image for running the application
 FROM python:3.13.7-slim
 
 ENV PYTHONUNBUFFERED=1 \
     DEBIAN_FRONTEND=noninteractive
 
+# Install only the essential runtime dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    tesseract-ocr \
+    # OCR dependencies
-    tesseract-ocr-eng \
+    tesseract-ocr tesseract-ocr-eng tesseract-ocr-deu ghostscript poppler-utils \
-    tesseract-ocr-deu \
-    ghostscript \
-    poppler-utils \
     libreoffice \
-    imagemagick \
+    pandoc texlive-xetex \
-    graphicsmagick \
-    libvips-tools \
-    ffmpeg \
-    libheif-examples \
-    inkscape \
-    calibre \
-    pngquant \
-    pandoc \
-    resvg \
-    sox \
-    libvips-tools \
-    build-essential \
-    pkg-config \
-    git \
-    potrace \
-    curl \
-    texlive \
-    jpegoptim \
     texlive-latex-recommended \
     texlive-fonts-recommended \
-    libxml2 \
+    calibre \
-    texlive-xetex \
+    ffmpeg \
-    texlive-science \
+    libvips-tools \
     libxml2-dev \
+    graphicsmagick \
+    inkscape \
+    resvg \
+    potrace \
+    pngquant \
+    sox \
+    jpegoptim \
+    libsox-fmt-mp3 \
+    lame \
+    # Runtime libraries for Python packages
+    libxml2 \
+    # Process manager
     supervisor \
     && rm -rf /var/lib/apt/lists/*
 
 
-
-# Set working directory inside the container
 WORKDIR /app
 
-# Copy requirements and install dependencies
+# Copy installed Python packages from the builder stage
-COPY requirements.txt .
+COPY --from=builder /usr/local/lib/python3.13/site-packages /usr/local/lib/python3.13/site-packages
-RUN pip install --no-cache-dir -r requirements.txt
+COPY --from=builder /usr/local/bin /usr/local/bin
-COPY supervisor.conf /etc/supervisor/conf.d/supervisor.conf
 
-# Copy the rest of the app
+# Copy supervisor config and application code
+COPY supervisor.conf /etc/supervisor/conf.d/supervisor.conf
 COPY . .
 
-
+# Expose port and set executable permissions
-# Expose the app port
 EXPOSE 8000
 RUN chmod +x run.sh
-# Command to run when container starts
+
-#CMD ["./run.sh"]
+# Start the application
 CMD ["/usr/bin/supervisord", "-n"]

requirements.txt

@@ -15,6 +15,7 @@ pytesseract
 pypdf
 
 # Configuration & Utilities
+werkzeug
 PyYAML
 pydantic
 pydantic-settings