Update Dockerfile

Dockerfile

@@ -1,12 +1,29 @@
-# Use Hugging Face’s OCR base image (includes Tesseract)
-FROM ghcr.io/huggingface/spaces-sdk:ocr
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
 
-# Copy dependencies and install
+# Set environment variables
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install Tesseract OCR and its dependencies
+RUN apt-get update && apt-get install -y \
+    tesseract-ocr \
+    libtesseract-dev \
+    libleptonica-dev \
+    pkg-config \
+    poppler-utils \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
 COPY requirements.txt .
-RUN pip install -r requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy app code
+# Copy the application code
 COPY app.py .
 
-# Launch the Streamlit app
+# Expose the port Streamlit will run on
+EXPOSE 7860
+
+# Command to run the application
 CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]
+