Update app.py

app.py

@@ -7,6 +7,7 @@ import json
 import time
 from typing import List, Dict, Any, Optional
 import spaces
+import os
 
 # Global variables to store API key and document text
 API_KEY = ""
@@ -17,13 +18,16 @@ def setup_client(api_key: str):
     """Initialize and test API key"""
     global API_KEY
     try:
-        # Test the API key by creating a client and making a simple request
+        if not api_key or api_key.strip() == "":
+            return "❌ Please enter a valid API key"
+            
+        # Test the API key by creating a client
         client = OpenAI(
             base_url="https://openrouter.ai/api/v1",
-            api_key=api_key,
+            api_key=api_key.strip(),
         )
         # Store the API key globally
-        API_KEY = api_key
+        API_KEY = api_key.strip()
         return "✅ API Key configured successfully!"
     except Exception as e:
         return f"❌ Error configuring API: {str(e)}"
@@ -43,9 +47,15 @@ def extract_text_from_pdf(file_path: str) -> str:
         with open(file_path, 'rb') as file:
             pdf_reader = PyPDF2.PdfReader(file)
             text = ""
-            for page in pdf_reader.pages:
-                text += page.extract_text() + "\n"
-            return text
+            for page_num, page in enumerate(pdf_reader.pages):
+                try:
+                    page_text = page.extract_text()
+                    if page_text:
+                        text += page_text + "\n"
+                except Exception as e:
+                    print(f"Error extracting text from page {page_num}: {e}")
+                    continue
+            return text.strip()
     except Exception as e:
         return f"Error reading PDF: {str(e)}"
 
@@ -55,68 +65,101 @@ def extract_text_from_docx(file_path: str) -> str:
         doc = docx.Document(file_path)
         text = ""
         for paragraph in doc.paragraphs:
-            text += paragraph.text + "\n"
-        return text
+            if paragraph.text.strip():
+                text += paragraph.text + "\n"
+        
+        # Also extract text from tables
+        for table in doc.tables:
+            for row in table.rows:
+                for cell in row.cells:
+                    if cell.text.strip():
+                        text += cell.text + "\n"
+        
+        return text.strip()
     except Exception as e:
         return f"Error reading DOCX: {str(e)}"
 
-@spaces.GPU
 def process_document(file):
     """Process uploaded document and extract text"""
     global DOCUMENT_TEXT
     
+    print(f"Processing file: {file}")  # Debug print
+    
     if file is None:
-        DOCUMENT_TEXT = ""  # Reset if no file
-        return "❌ No file uploaded"
+        DOCUMENT_TEXT = ""
+        return "❌ No file uploaded", "❌ No document loaded"
     
     try:
-        file_path = file.name
+        file_path = file.name if hasattr(file, 'name') else str(file)
+        print(f"File path: {file_path}")  # Debug print
+        
+        # Check if file exists
+        if not os.path.exists(file_path):
+            DOCUMENT_TEXT = ""
+            return "❌ File not found", "❌ No document loaded"
+        
+        # Get file extension
         file_extension = file_path.lower().split('.')[-1]
+        print(f"File extension: {file_extension}")  # Debug print
         
+        # Extract text based on file type
         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."
+            DOCUMENT_TEXT = ""
+            return "❌ Unsupported file format. Please upload PDF or DOCX files.", "❌ No document loaded"
+        
+        print(f"Extracted text length: {len(extracted_text) if extracted_text else 0}")  # Debug print
         
         # Check if extraction was successful
         if extracted_text.startswith("Error"):
-            DOCUMENT_TEXT = ""  # Reset on error
-            return extracted_text
+            DOCUMENT_TEXT = ""
+            return extracted_text, "❌ No document loaded"
         
-        # Set the global variable
+        # Clean and set the global variable
         DOCUMENT_TEXT = extracted_text.strip()
         
-        if DOCUMENT_TEXT and len(DOCUMENT_TEXT) > 0:
+        if DOCUMENT_TEXT and len(DOCUMENT_TEXT) > 10:  # Minimum length check
             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}"
+            char_count = len(DOCUMENT_TEXT)
+            preview = DOCUMENT_TEXT[:300] + "..." if len(DOCUMENT_TEXT) > 300 else DOCUMENT_TEXT
+            
+            status_msg = f"✅ Document loaded ({word_count} words, {char_count} characters)"
+            process_msg = f"✅ Document processed successfully!\n📄 Word count: {word_count}\n📝 Character count: {char_count}\n\n📖 Preview:\n{preview}"
+            
+            print(f"Document processed successfully. Word count: {word_count}")  # Debug print
+            return process_msg, status_msg
         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."
+            DOCUMENT_TEXT = ""
+            return "❌ Could not extract meaningful text from the document. The document might be empty, contain only images, or be corrupted.", "❌ No document loaded"
             
     except Exception as e:
-        DOCUMENT_TEXT = ""  # Reset on any error
-        return f"❌ Error processing document: {str(e)}"
+        DOCUMENT_TEXT = ""
+        error_msg = f"❌ Error processing document: {str(e)}"
+        print(f"Error: {error_msg}")  # Debug print
+        return error_msg, "❌ No document loaded"
 
-@spaces.GPU
 def generate_content(prompt: str, max_tokens: int = 2000) -> str:
     """Generate content using the AI model"""
-    global DOCUMENT_TEXT
+    global DOCUMENT_TEXT, API_KEY
     
-    if not API_KEY:
+    print(f"Generate content called. API_KEY exists: {bool(API_KEY)}, DOCUMENT_TEXT length: {len(DOCUMENT_TEXT) if DOCUMENT_TEXT else 0}")  # Debug print
+    
+    if not API_KEY or API_KEY.strip() == "":
         return "❌ Please configure your API key first"
     
-    if not DOCUMENT_TEXT or len(DOCUMENT_TEXT.strip()) == 0:
+    if not DOCUMENT_TEXT or len(DOCUMENT_TEXT.strip()) < 10:
         return "❌ Please upload and process a document first. Make sure the document contains readable text."
     
     try:
         client = create_client()
         if not client:
             return "❌ Failed to create API client"
-            
+        
+        print("Sending request to API...")  # Debug print
+        
         completion = client.chat.completions.create(
             extra_headers={
                 "HTTP-Referer": "https://educational-assistant.app",
@@ -130,16 +173,23 @@ def generate_content(prompt: str, max_tokens: int = 2000) -> str:
                 },
                 {
                     "role": "user",
-                    "content": f"Document Content:\n{DOCUMENT_TEXT}\n\n{prompt}"
+                    "content": f"Document Content:\n{DOCUMENT_TEXT[:4000]}\n\n{prompt}"  # Limit document content to avoid token limits
                 }
             ],
             max_tokens=max_tokens,
             temperature=0.7
         )
-        return completion.choices[0].message.content
+        
+        result = completion.choices[0].message.content
+        print(f"API response received. Length: {len(result) if result else 0}")  # Debug print
+        return result
+        
     except Exception as e:
-        return f"❌ Error generating content: {str(e)}"
+        error_msg = f"❌ Error generating content: {str(e)}"
+        print(f"API Error: {error_msg}")  # Debug print
+        return error_msg
 
+# Content generation functions with @spaces.GPU decorator
 @spaces.GPU
 def generate_summary():
     """Generate comprehensive summary"""
@@ -378,15 +428,24 @@ def generate_practice_problems():
     """
     return generate_content(prompt, max_tokens=3500)
 
-def check_document_status():
-    """Check if document is loaded"""
+def get_document_status():
+    """Get current document status"""
     global DOCUMENT_TEXT
-    if DOCUMENT_TEXT and len(DOCUMENT_TEXT.strip()) > 0:
+    if DOCUMENT_TEXT and len(DOCUMENT_TEXT.strip()) > 10:
         word_count = len(DOCUMENT_TEXT.split())
-        return f"✅ Document loaded ({word_count} words)"
+        char_count = len(DOCUMENT_TEXT)
+        return f"✅ Document loaded ({word_count} words, {char_count} characters)"
     else:
         return "❌ No document loaded"
 
+def get_api_status():
+    """Get current API status"""
+    global API_KEY
+    if API_KEY and API_KEY.strip():
+        return "✅ API Key configured"
+    else:
+        return "❌ API Key not configured"
+
 # Create Gradio interface
 def create_interface():
     with gr.Blocks(title="📚 Educational Content Creator Assistant", theme=gr.themes.Soft()) as app:
@@ -405,21 +464,27 @@ def create_interface():
                 api_key = gr.Textbox(
                     label="OpenRouter API Key",
                     type="password",
-                    placeholder="Enter your OpenRouter API key..."
+                    placeholder="Enter your OpenRouter API key...",
+                    info="Get your API key from https://openrouter.ai/"
                 )
                 setup_btn = gr.Button("🔧 Configure API", variant="primary")
-                setup_status = gr.Textbox(label="Status", interactive=False)
+                setup_status = gr.Textbox(label="API Status", value=get_api_status(), interactive=False)
                 
                 gr.Markdown("### 📄 Document Upload")
                 file_upload = gr.File(
                     label="Upload Document (PDF or DOCX)",
-                    file_types=[".pdf", ".docx", ".doc"]
+                    file_types=[".pdf", ".docx", ".doc"],
+                    type="filepath"
                 )
                 process_btn = gr.Button("🔄 Process Document", variant="secondary")
-                process_status = gr.Textbox(label="Processing Status", interactive=False)
+                process_status = gr.Textbox(label="Processing Status", interactive=False, lines=4)
                 
-                # Add document status indicator
-                doc_status = gr.Textbox(label="Document Status", value="❌ No document loaded", interactive=False)
+                # Document status indicator
+                doc_status = gr.Textbox(
+                    label="Document Status", 
+                    value=get_document_status(), 
+                    interactive=False
+                )
             
             with gr.Column(scale=2):
                 gr.Markdown("### 🎯 Generate Educational Content")
@@ -448,88 +513,70 @@ def create_interface():
         
         gr.Markdown("""
         ### 📋 How to Use:
-        1. **Get API Key:** Sign up at [OpenRouter](https://openrouter.ai/) and get your API key
-        2. **Configure:** Enter your API key and click "Configure API"
-        3. **Upload:** Upload a PDF or DOCX document
+        1. **Get API Key:** Sign up at [OpenRouter](https://openrouter.ai/) and get your free API key
+        2. **Configure:** Enter your API key and click "Configure API" 
+        3. **Upload:** Upload a PDF or DOCX document (make sure it contains readable text)
         4. **Process:** Click "Process Document" to extract text
         5. **Generate:** Choose any educational content type to generate
         
         ### 🎯 Content Types:
         - **Summary:** Comprehensive overview with key points
         - **Study Notes:** Structured notes with key concepts and memory aids
-        - **Quiz:** Multiple choice, short answer, and essay questions
+        - **Quiz:** Multiple choice, short answer, and essay questions with answers
         - **Flashcards:** Question-answer pairs for memorization
         - **Mind Map:** Visual structure of document concepts
         - **Lesson Plan:** Complete teaching plan with objectives and activities
         - **Concept Explanations:** Deep dive into key concepts with examples
         - **Practice Problems:** Graded exercises from beginner to advanced
         
+        ### 💡 Tips:
+        - Make sure your PDF contains selectable text (not just images)
+        - For best results, use documents with clear structure and headings
+        - The app works with academic papers, textbooks, reports, and study materials
+        
         ### ⚡ Performance Note:
         This app uses ZeroGPU for enhanced processing. Functions will automatically utilize GPU resources when needed.
         """)
         
         # Event handlers
+        def setup_api_and_update_status(api_key):
+            result = setup_client(api_key)
+            status = get_api_status()
+            return result, status
+        
         setup_btn.click(
-            setup_client,
+            setup_api_and_update_status,
             inputs=[api_key],
-            outputs=[setup_status]
+            outputs=[setup_status, setup_status]
         )
         
-        def process_and_update_status(file):
-            result = process_document(file)
-            status = check_document_status()
-            return result, status
+        def process_and_update_all_status(file):
+            process_result, doc_status_result = process_document(file)
+            return process_result, doc_status_result
         
         process_btn.click(
-            process_and_update_status,
+            process_and_update_all_status,
             inputs=[file_upload],
             outputs=[process_status, doc_status]
         )
         
-        summary_btn.click(
-            generate_summary,
-            outputs=[output]
-        )
-        
-        notes_btn.click(
-            generate_study_notes,
-            outputs=[output]
-        )
-        
-        quiz_btn.click(
-            generate_quiz,
-            outputs=[output]
-        )
-        
-        flashcards_btn.click(
-            generate_flashcards,
-            outputs=[output]
-        )
-        
-        mindmap_btn.click(
-            generate_mind_map,
-            outputs=[output]
-        )
+        # Content generation button handlers
+        summary_btn.click(generate_summary, outputs=[output])
+        notes_btn.click(generate_study_notes, outputs=[output])
+        quiz_btn.click(generate_quiz, outputs=[output])
+        flashcards_btn.click(generate_flashcards, outputs=[output])
+        mindmap_btn.click(generate_mind_map, outputs=[output])
+        lesson_btn.click(generate_lesson_plan, outputs=[output])
+        concepts_btn.click(generate_concept_explanations, outputs=[output])
+        problems_btn.click(generate_practice_problems, outputs=[output])
         
-        lesson_btn.click(
-            generate_lesson_plan,
-            outputs=[output]
-        )
-        
-        concepts_btn.click(
-            generate_concept_explanations,
-            outputs=[output]
-        )
-        
-        problems_btn.click(
-            generate_practice_problems,
-            outputs=[output]
-        )
+        # Update status on app load
+        def update_initial_status():
+            return get_api_status(), get_document_status()
         
-        # Update document status when page loads
         app.load(
-            check_document_status,
-            outputs=[doc_status]
+            update_initial_status,
+            outputs=[setup_status, doc_status]
         )
     
     return app
@@ -537,4 +584,7 @@ def create_interface():
 # Launch the application
 if __name__ == "__main__":
     app = create_interface()
-    app.launch()
+    app.launch(
+        debug=True,
+        share=False
+    )