Update app_main.py

app_main.py

@@ -10,10 +10,22 @@ import pytesseract
 from transformers import AutoProcessor, AutoModelForImageTextToText
 from langchain_community.document_loaders.image_captions import ImageCaptionLoader
 from werkzeug.utils import secure_filename
-import tempfile
+import tempfile, logging
 
 app = Flask(__name__)
 
+# Configure logging
+logging.basicConfig(
+    level=logging.DEBUG,  # Use INFO or ERROR in production
+    format="%(asctime)s [%(levelname)s] %(message)s",
+    handlers=[
+        logging.FileHandler("app.log"),
+        logging.StreamHandler()
+    ]
+)
+
+logger = logging.getLogger(__name__)
+
 pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
 poppler_path=r"C:\poppler-23.11.0\Library\bin"
 
@@ -131,7 +143,9 @@ def index():
 @app.route('/process_pdf', methods=['POST'])
 def process_pdf():
     try:
+         logger.info("Received request to process PDF.")
         if 'pdf_file' not in request.files:
+            logger.warning("No PDF file found in request.")
             return jsonify({"error": "Missing PDF file in form-data with key 'pdf_file'"}), 400
 
         pdf_file = request.files['pdf_file']
@@ -144,16 +158,21 @@ def process_pdf():
         saved_pdf_path = os.path.join(temp_dir, filename)
         pdf_file.save(saved_pdf_path)
 
+        logger.info(f"Saved uploaded PDF to: {saved_pdf_path}")
+        
         # Extract & process
         json_path = None
         output_path, result = extract_images_from_pdf(saved_pdf_path, json_path)
 
+         logger.info("Received request to process PDF.")
+
         return jsonify({
             "message": "✅ PDF processed successfully",
             "output_json": output_path,
             "sprites": result
         })
     except Exception as e:
+        logger.exception("❌ Failed to process PDF")
         return jsonify({"error": f"❌ Failed to process PDF: {str(e)}"}), 500
 
 if __name__ == '__main__':