Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,31 @@
+FROM python:3.11-slim
+
+# Install system dependencies including Tesseract OCR
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr \
+    tesseract-ocr-spa \
+    libgl1-mesa-glx \
+    libglib2.0-0 \
+    && 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 app.py .
+
+# Expose port for Gradio
+EXPOSE 7860
+
+# Set environment variables
+ENV GRADIO_SERVER_NAME=0.0.0.0
+ENV GRADIO_SERVER_PORT=7860
+
+# Run the application
+CMD ["python", "app.py"]

README.md

@@ -3,9 +3,7 @@ title: LayoutLMv3 Document Classifier
 emoji: 📄
 colorFrom: blue
 colorTo: indigo
-sdk: gradio
-sdk_version: 5.0.0
-app_file: app.py
+sdk: docker
 pinned: false
 license: apache-2.0
 short_description: Clasificador de documentos legales con LayoutLMv3

requirements.txt

@@ -4,3 +4,4 @@ torch>=2.0.0
 Pillow>=10.0.0
 pymupdf>=1.24.0
 numpy>=1.24.0
+pytesseract>=0.3.10