Deploy to Hugging Face Space with Docker SDK and Trixie/Debian 13 updates

Dockerfile

@@ -0,0 +1,33 @@
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+COPY packages.txt /tmp/packages.txt
+RUN sed -i 's/main$/main contrib non-free/' /etc/apt/sources.list && \
+    apt-get update && \
+    xargs -r -a /tmp/packages.txt apt-get install -y || true && \
+    apt-get install -y \
+        curl \
+        libgl1-mesa-glx \
+        poppler-utils \
+        tesseract-ocr \
+        libtesseract-dev \
+        libleptonica-dev && \
+    curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && \
+    apt-get install -y nodejs && \
+    rm -rf /var/lib/apt/lists/* && apt-get clean
+
+# Copy requirements and install
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application
+COPY . .
+
+# Expose port 7860 for Gradio
+EXPOSE 7860
+
+# Run the application
+CMD ["python", "app.py"]

README.md

@@ -1,3 +1,13 @@
+---
+title: Passport Extractor
+emoji: 🛂
+colorFrom: blue
+colorTo: green
+sdk: docker
+app_file: app.py
+pinned: false
+---
+
 # Passport OCR Tool
 
 A robust tool to extract data from passport images (PNG, JPG) and PDFs using OCR. It extracts MRZ (Machine Readable Zone) data and exports it to Excel or CSV formats.

app.py

@@ -332,7 +332,6 @@ def build_app():
 if __name__ == "__main__":
     app = build_app()
     app.launch(
-        server_name="127.0.0.1",
+        server_name="0.0.0.0",
         server_port=7860,
-        share=True,
     )

packages.txt

@@ -1,4 +1,6 @@
-libgl1
+libgl1-mesa-glx
 poppler-utils
 tesseract-ocr
+tesseract-ocr-eng
 libtesseract-dev
+libleptonica-dev