Update Dockerfile

Dockerfile

@@ -1,7 +1,7 @@
-# Use a base image with Python and system utilities
+# Use slim Python base image
 FROM python:3.10-slim
 
-# Install system packages including Tesseract
+# Install system-level dependencies
 RUN apt-get update && apt-get install -y \
     tesseract-ocr \
     libglib2.0-0 \
@@ -11,26 +11,30 @@ RUN apt-get update && apt-get install -y \
     libxrender-dev \
     poppler-utils \
     ffmpeg \
-    build-essential \
     git \
+    build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# 🔧 Make sure Tesseract is in PATH
-ENV TESSERACT_PATH=/usr/bin/tesseract
-ENV PATH="${TESSERACT_PATH}:${PATH}"
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV PIP_NO_CACHE_DIR=1
+ENV HF_HUB_DISABLE_SYMLINKS_WARNING=1
 
-# Work directory
+# Set working directory
 WORKDIR /home/user/app
 
-# Python packages
+# Copy dependencies and install
 COPY requirements.txt .
 RUN pip install --upgrade pip && pip install -r requirements.txt
 
-# Copy app files
+# Copy app source files
 COPY . .
 
-# Download NLTK tokenizer data
+# Download NLTK data (punkt tokenizer)
 RUN python -m nltk.downloader punkt
 
-# Run the app
+# Expose Gradio's default port
+EXPOSE 7860
+
+# Launch the Gradio app
 CMD ["python", "app.py"]