Update Dockerfile

Dockerfile

@@ -1,43 +1,36 @@
-# Base image
+# Use a base image with Python and system utilities
 FROM python:3.10-slim
 
-# System dependencies for OCR, PDF, DOCX, fonts, and more
+# Install system packages including Tesseract
 RUN apt-get update && apt-get install -y \
     tesseract-ocr \
     libglib2.0-0 \
     libgl1 \
-    libpoppler-cpp-dev \
-    poppler-utils \
     libsm6 \
     libxext6 \
     libxrender-dev \
+    poppler-utils \
     ffmpeg \
     build-essential \
     git \
- && rm -rf /var/lib/apt/lists/*
-
-# Ensure tesseract is in PATH and test it
-RUN which tesseract && tesseract --version
+    && rm -rf /var/lib/apt/lists/*
 
-# Set environment variables
-ENV PIP_NO_CACHE_DIR=1 \
-    PYTHONUNBUFFERED=1 \
-    HF_HUB_DISABLE_SYMLINKS_WARNING=1 \
-    TESSERACT_PATH=/usr/bin/tesseract \
-    PATH="/usr/bin:$PATH"
+# 🔧 Make sure Tesseract is in PATH
+ENV TESSERACT_PATH=/usr/bin/tesseract
+ENV PATH="${TESSERACT_PATH}:${PATH}"
 
-# Set working directory
+# Work directory
 WORKDIR /home/user/app
 
-# Copy requirements and install
+# Python packages
 COPY requirements.txt .
 RUN pip install --upgrade pip && pip install -r requirements.txt
 
 # Copy app files
 COPY . .
 
-# Download NLTK data
+# Download NLTK tokenizer data
 RUN python -m nltk.downloader punkt
 
-# Start the app
+# Run the app
 CMD ["python", "app.py"]