Update app.py

app.py

@@ -66,32 +66,51 @@ def process_document(file):
     global DOCUMENT_TEXT
     
     if file is None:
+        DOCUMENT_TEXT = ""  # Reset if no file
         return "❌ No file uploaded"
     
-    file_path = file.name
-    file_extension = file_path.lower().split('.')[-1]
-    
-    if file_extension == 'pdf':
-        DOCUMENT_TEXT = extract_text_from_pdf(file_path)
-    elif file_extension in ['docx', 'doc']:
-        DOCUMENT_TEXT = extract_text_from_docx(file_path)
-    else:
-        return "❌ Unsupported file format. Please upload PDF or DOCX files."
-    
-    if DOCUMENT_TEXT and len(DOCUMENT_TEXT.strip()) > 0:
-        word_count = len(DOCUMENT_TEXT.split())
-        return f"✅ Document processed successfully!\n📄 Word count: {word_count}\n📝 Preview: {DOCUMENT_TEXT[:200]}..."
-    else:
-        return "❌ Could not extract text from the document"
+    try:
+        file_path = file.name
+        file_extension = file_path.lower().split('.')[-1]
+        
+        if file_extension == 'pdf':
+            extracted_text = extract_text_from_pdf(file_path)
+        elif file_extension in ['docx', 'doc']:
+            extracted_text = extract_text_from_docx(file_path)
+        else:
+            DOCUMENT_TEXT = ""  # Reset on unsupported format
+            return "❌ Unsupported file format. Please upload PDF or DOCX files."
+        
+        # Check if extraction was successful
+        if extracted_text.startswith("Error"):
+            DOCUMENT_TEXT = ""  # Reset on error
+            return extracted_text
+        
+        # Set the global variable
+        DOCUMENT_TEXT = extracted_text.strip()
+        
+        if DOCUMENT_TEXT and len(DOCUMENT_TEXT) > 0:
+            word_count = len(DOCUMENT_TEXT.split())
+            preview = DOCUMENT_TEXT[:200] + "..." if len(DOCUMENT_TEXT) > 200 else DOCUMENT_TEXT
+            return f"✅ Document processed successfully!\n📄 Word count: {word_count}\n📝 Preview: {preview}"
+        else:
+            DOCUMENT_TEXT = ""  # Reset if no text extracted
+            return "❌ Could not extract text from the document. The document might be empty or contain only images."
+            
+    except Exception as e:
+        DOCUMENT_TEXT = ""  # Reset on any error
+        return f"❌ Error processing document: {str(e)}"
 
 @spaces.GPU
 def generate_content(prompt: str, max_tokens: int = 2000) -> str:
     """Generate content using the AI model"""
+    global DOCUMENT_TEXT
+    
     if not API_KEY:
         return "❌ Please configure your API key first"
     
-    if not DOCUMENT_TEXT:
-        return "❌ Please upload and process a document first"
+    if not DOCUMENT_TEXT or len(DOCUMENT_TEXT.strip()) == 0:
+        return "❌ Please upload and process a document first. Make sure the document contains readable text."
     
     try:
         client = create_client()
@@ -359,6 +378,15 @@ def generate_practice_problems():
     """
     return generate_content(prompt, max_tokens=3500)
 
+def check_document_status():
+    """Check if document is loaded"""
+    global DOCUMENT_TEXT
+    if DOCUMENT_TEXT and len(DOCUMENT_TEXT.strip()) > 0:
+        word_count = len(DOCUMENT_TEXT.split())
+        return f"✅ Document loaded ({word_count} words)"
+    else:
+        return "❌ No document loaded"
+
 # Create Gradio interface
 def create_interface():
     with gr.Blocks(title="📚 Educational Content Creator Assistant", theme=gr.themes.Soft()) as app:
@@ -389,6 +417,9 @@ def create_interface():
                 )
                 process_btn = gr.Button("🔄 Process Document", variant="secondary")
                 process_status = gr.Textbox(label="Processing Status", interactive=False)
+                
+                # Add document status indicator
+                doc_status = gr.Textbox(label="Document Status", value="❌ No document loaded", interactive=False)
             
             with gr.Column(scale=2):
                 gr.Markdown("### 🎯 Generate Educational Content")
@@ -444,10 +475,15 @@ def create_interface():
             outputs=[setup_status]
         )
         
+        def process_and_update_status(file):
+            result = process_document(file)
+            status = check_document_status()
+            return result, status
+        
         process_btn.click(
-            process_document,
+            process_and_update_status,
             inputs=[file_upload],
-            outputs=[process_status]
+            outputs=[process_status, doc_status]
         )
         
         summary_btn.click(
@@ -489,6 +525,12 @@ def create_interface():
             generate_practice_problems,
             outputs=[output]
         )
+        
+        # Update document status when page loads
+        app.load(
+            check_document_status,
+            outputs=[doc_status]
+        )
     
     return app