Update Dockerfile

Dockerfile

@@ -1,7 +1,7 @@
-# Start from an official Python image
-FROM python:3.9-slim
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim
 
-# Install system packages (tesseract-ocr, ffmpeg for audio, poppler-utils for PDF if you want advanced PDF to images)
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
     tesseract-ocr \
     libtesseract-dev \
@@ -10,20 +10,30 @@ RUN apt-get update && apt-get install -y \
     libxext6 \
     && rm -rf /var/lib/apt/lists/*
 
+# Install Poppler-utils for advanced PDF processing (optional)
+RUN apt-get update && apt-get install -y poppler-utils && rm -rf /var/lib/apt/lists/*
+
+# Set environment variables
+ENV LANG C.UTF-8
+
 # Create a working directory
 WORKDIR /app
 
-# Copy requirements
+# Copy the requirements file
 COPY requirements.txt .
 
-# Install python dependencies
+# Upgrade pip and install Python dependencies
+RUN pip install --upgrade pip
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy your app code
+# Download NLTK data
+RUN python -m nltk.downloader punkt
+
+# Copy the application code
 COPY app.py .
 
-# Expose Gradio's default port
+# Expose the port Gradio runs on
 EXPOSE 7860
 
-# Run the app
+# Define the default command to run the app
 CMD ["python", "app.py"]