Update app.py

app.py

@@ -495,45 +495,21 @@ def display_pdf_preview(file_path, model_name):
     """Display PDF preview inline"""
     import os
     
-    # Extract just the filename from the Windows path, ignoring subdirectories
-    # Convert backslashes to forward slashes first
+    # Extract just the filename from the database path
+    # Handle both forward and backslashes
     normalized_path = file_path.replace('\\', '/')
-    pdf_filename = os.path.basename(normalized_path)
-    
-    # Clean up the filename (remove any extra spaces or special characters if needed)
-    pdf_filename = pdf_filename.strip()
-    
-    # Debug info
-    st.write(f"🔍 Looking for PDF: {pdf_filename}")
-    
-    # Try multiple possible locations
-    possible_paths = [
-        os.path.join("pdfs", pdf_filename),  # /pdfs/filename.pdf
-        os.path.join(".", "pdfs", pdf_filename),  # ./pdfs/filename.pdf
-        f"pdfs/{pdf_filename}",  # Direct path string
-    ]
-    
-    # Also try without spaces in filename (in case of naming issues)
-    pdf_filename_no_spaces = pdf_filename.replace(' ', '_')
-    possible_paths.extend([
-        os.path.join("pdfs", pdf_filename_no_spaces),
-        f"pdfs/{pdf_filename_no_spaces}"
-    ])
-    
-    pdf_found = False
-    actual_path = None
-    
-    # Try each possible path
-    for test_path in possible_paths:
-        if os.path.exists(test_path):
-            pdf_found = True
-            actual_path = test_path
-            st.success(f"✅ Found PDF at: {test_path}")
-            break
-    
-    if pdf_found and actual_path is not None:
+    pdf_filename = normalized_path.split('/')[-1]  # Get last part after final slash
+    
+    # The PDFs are in the 'pdfs' subdirectory
+    pdf_path = os.path.join('pdfs', pdf_filename)
+    
+    # Debug info - remove these lines once working
+    # st.write(f"Debug - Looking for: {pdf_path}")
+    # st.write(f"Debug - File exists: {os.path.exists(pdf_path)}")
+    
+    if os.path.exists(pdf_path):
         try:
-            with open(actual_path, "rb") as f:
+            with open(pdf_path, "rb") as f:
                 pdf_data = f.read()
             
             file_size_mb = len(pdf_data) / (1024 * 1024)
@@ -563,10 +539,7 @@ def display_pdf_preview(file_path, model_name):
             st.markdown("---")
             
             if file_size_mb < 10:
-                # Convert to base64
                 base64_pdf = base64.b64encode(pdf_data).decode('utf-8')
-                
-                # Create HTML for inline PDF display
                 pdf_display = f"""
                     <iframe 
                         src="data:application/pdf;base64,{base64_pdf}"
@@ -576,44 +549,26 @@ def display_pdf_preview(file_path, model_name):
                         style="border: 2px solid #4CAF50; border-radius: 8px;">
                     </iframe>
                 """
-                
                 st.markdown(pdf_display, unsafe_allow_html=True)
-                
             else:
                 st.warning("PDF file is too large for inline viewing. Please use the download button.")
                 
         except Exception as e:
             st.error(f"Error reading PDF: {str(e)}")
-            st.info(f"Attempted to read from: {actual_path}")
     else:
         st.error("❌ PDF file not found.")
-        st.info(f"Expected filename: {pdf_filename}")
-        
-        # List files in pdfs directory to help debug
-        try:
-            pdfs_dir = "pdfs"
-            if os.path.exists(pdfs_dir):
-                files_in_pdfs = os.listdir(pdfs_dir)
-                # Find similar filenames
-                similar_files = [f for f in files_in_pdfs if pdf_filename.lower()[:10] in f.lower()]
-                
-                if similar_files:
-                    st.warning("🔍 Similar files found in /pdfs folder:")
-                    for f in similar_files[:5]:  # Show max 5 similar files
-                        st.write(f"- {f}")
-                else:
-                    st.info("No similar files found. The PDF might not have been uploaded.")
-            else:
-                st.error("The /pdfs directory doesn't exist!")
-                
-        except Exception as e:
-            st.error(f"Error listing PDF directory: {e}")
+        st.info(f"Looking for: {pdf_filename} in /pdfs folder")
         
-        # Debug information
-        with st.expander("🔧 Debug Information"):
-            st.write(f"**Original path:** {file_path}")
-            st.write(f"**Extracted filename:** {pdf_filename}")
-            st.write(f"**Model:** {model_name}")
+        # If you're still having issues, uncomment these debug lines:
+        # st.write("Current directory:", os.getcwd())
+        # st.write("Contents of current directory:", os.listdir('.'))
+        # if os.path.exists('pdfs'):
+        #     pdf_list = os.listdir('pdfs')
+        #     st.write(f"Number of PDFs in /pdfs: {len(pdf_list)}")
+        #     # Show first few PDFs that might match
+        #     matching = [p for p in pdf_list if model_name in p]
+        #     if matching:
+        #         st.write("Possible matches:", matching[:5])
 
 def get_high_accuracy_models(limit=8):
     """Get models with highest extraction quality"""