ocr api

Dockers/ocr-api/Dockerfile

@@ -0,0 +1,46 @@
+# Use Python 3.11 slim image as base
+FROM python:3.11-slim
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr \
+    tesseract-ocr-eng \
+    tesseract-ocr-fra \
+    tesseract-ocr-deu \
+    tesseract-ocr-spa \
+    tesseract-ocr-ita \
+    poppler-utils \
+    libpoppler-cpp-dev \
+    pkg-config \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY main.py .
+
+# Create a non-root user
+RUN useradd --create-home --shell /bin/bash app \
+    && chown -R app:app /app
+USER app
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Run the application
+CMD ["python", "main.py"]