Update app.py

app.py

@@ -1,12 +1,20 @@
 import streamlit as st
-import pytesseract
-from transformers import pipeline
-from PIL import Image
-import fitz  # PyMuPDF for PDF processing
 import logging
 from concurrent.futures import ThreadPoolExecutor
-import cv2
-import numpy as np
+import subprocess
+import sys
+
+# Attempt to import libraries, with fallback
+try:
+    import pytesseract
+    import cv2
+    import numpy as np
+    from PIL import Image
+    import fitz  # PyMuPDF for PDF processing
+    from transformers import pipeline
+except ImportError:
+    st.error("Required libraries are missing. Please install them using pip.")
+    st.stop()
 
 # Setup logging
 def setup_logging():
@@ -15,6 +23,46 @@ def setup_logging():
         format="%(asctime)s - %(levelname)s - %(message)s",
     )
 
+# Tesseract installation check and guide
+def check_tesseract():
+    try:
+        # Try to get Tesseract version
+        version = subprocess.check_output(['tesseract', '--version'], 
+                                          stderr=subprocess.STDOUT).decode('utf-8')
+        return True
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        # Provide installation instructions based on operating system
+        st.error("Tesseract OCR is not installed.")
+        st.markdown("### Tesseract Installation Guide:")
+        
+        if sys.platform.startswith('linux'):
+            st.code("""
+            # For Ubuntu/Debian
+            sudo apt-get update
+            sudo apt-get install -y tesseract-ocr
+            
+            # For Fedora
+            sudo dnf install -y tesseract
+            
+            # For CentOS/RHEL
+            sudo yum install -y tesseract
+            """)
+        elif sys.platform.startswith('darwin'):
+            st.code("""
+            # For macOS (using Homebrew)
+            brew install tesseract
+            """)
+        elif sys.platform.startswith('win'):
+            st.markdown("""
+            1. Download Tesseract installer from:
+               https://github.com/UB-Mannheim/tesseract/wiki
+            2. Run the installer
+            3. Add Tesseract directory to your system PATH
+            """)
+        
+        st.info("After installation, restart your application.")
+        return False
+
 # Load models globally for faster performance
 @st.cache_resource
 def load_models():
@@ -42,6 +90,11 @@ def preprocess_image(image):
     
     # Apply deskewing if needed
     coords = np.column_stack(np.where(gray > 0))
+    
+    # Prevent error if no foreground pixels found
+    if coords.size == 0:
+        return gray
+    
     angle = cv2.minAreaRect(coords)[-1]
     
     # The cv2.minAreaRect returns values in the range [:-90, 0)
@@ -90,6 +143,10 @@ def process_chunks(text, model, chunk_size=500):
 
 # Main app logic
 def main():
+    # Check Tesseract installation first
+    if not check_tesseract():
+        return
+
     setup_logging()
     st.title("Advanced Lab Report Analyzer")
     st.write("Upload a file (Image, PDF, or Text) to analyze and summarize the lab report in English, Hindi, and Urdu.")