fix/nltk

Dockerfile

@@ -1,40 +1,31 @@
-FROM python:3.9-slim
+# Use an official Python runtime as a parent image
+FROM python:3.11-slim
 
-# Set working directory
-WORKDIR /app
+# Set the working directory in the container
+WORKDIR /code
 
-# Install system dependencies
-# Update package lists first
-RUN apt-get update
-
-# Install each main package and its dependencies in a separate layer
-RUN apt-get install -y --no-install-recommends libfaiss-dev && rm -rf /var/lib/apt/lists/*
-RUN apt-get update && apt-get install -y --no-install-recommends tesseract-ocr && rm -rf /var/lib/apt/lists/*
-RUN apt-get update && apt-get install -y --no-install-recommends libgl1 && rm -rf /var/lib/apt/lists/*
-
-# Set environment variables for writable directories
-ENV HOME=/tmp
+# Set writable cache directories for Hugging Face models and NLTK data
+ENV HF_HOME=/tmp/huggingface_cache
 ENV NLTK_DATA=/tmp/nltk_data
-ENV TRANSFORMERS_CACHE=/tmp/transformers_cache
-ENV HF_HOME=/tmp/huggingface
-ENV PYTHONUNBUFFERED=1
-
-# Create necessary directories with proper permissions
-RUN mkdir -p /tmp/nltk_data /tmp/transformers_cache /tmp/huggingface /tmp/uploads && \
-    chmod -R 777 /tmp
-
-# Copy requirements and install Python dependencies
+ENV MPLCONFIGDIR=/tmp/matplotlib_cache
+ENV FONTCONFIG_PATH=/tmp/fontconfig
+ENV XDG_CACHE_HOME=/tmp/xdg_cache
+# Copy the system dependencies file and install them
+COPY packages.txt .
+RUN apt-get update && apt-get install -y --no-install-recommends $(cat packages.txt) && \
+    rm -rf /var/lib/apt/lists/*
+
+# Copy the Python requirements file
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
 
-# Download NLTK data during build
-RUN python -c "import nltk; nltk.download('punkt', download_dir='/tmp/nltk_data'); nltk.download('stopwords', download_dir='/tmp/nltk_data')"
+# Install the Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy application files
+# Copy the rest of your application code into the container
 COPY . .
 
-# Expose port
+# Expose the port that Hugging Face Spaces uses
 EXPOSE 7860
 
-# Run the application
-CMD ["gunicorn", "-b", "0.0.0.0:7860", "--timeout", "300", "--workers", "1", "app:app"]
+# Command to run your application using gunicorn
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]