Update app.py

app.py

@@ -8,7 +8,7 @@ from collections import defaultdict
 from typing import Dict, List, Optional, Tuple, Union
 import html
 from pathlib import Path
-import fitz  # PyMuPDF for better PDF text extraction
+import fitz  # PyMuPDF
 import pytesseract
 from PIL import Image
 import io
@@ -48,7 +48,7 @@ if HF_TOKEN:
     except Exception as e:
         logging.error(f"Failed to initialize Hugging Face API: {str(e)}")
 
-# ========== OPTIMIZED MODEL LOADING ==========
+# ========== MODEL LOADER ==========
 class ModelLoader:
     def __init__(self):
         self.model = None
@@ -85,10 +85,6 @@ class ModelLoader:
                 "low_cpu_mem_usage": True
             }
             
-            # Add quantization config for low-memory devices
-            if self.device == "cpu":
-                model_kwargs["load_in_8bit"] = True
-            
             if progress:
                 progress(0.3, desc="Loading tokenizer...")
             self.tokenizer = AutoTokenizer.from_pretrained(
@@ -396,10 +392,6 @@ class TranscriptParser:
             "completion_status": self._calculate_completion()
         }, indent=2)
 
-async def parse_transcript_async(file_obj, progress=gr.Progress()):
-    """Async wrapper for transcript parsing"""
-    return await asyncio.to_thread(parse_transcript, file_obj, progress)
-
 def parse_transcript_with_ai(text: str, progress=gr.Progress()) -> Dict:
     """Use AI model to parse transcript text with progress feedback"""
     model, tokenizer = model_loader.load_model(progress)
@@ -438,7 +430,7 @@ def parse_transcript_with_ai(text: str, progress=gr.Progress()) -> Dict:
         
         if progress:
             progress(1.0)
-        return validate_parsed_data(formatted_data)
+        return formatted_data
     
     except Exception as e:
         logging.warning(f"Structured parsing failed, falling back to AI: {str(e)}")
@@ -473,11 +465,11 @@ def parse_transcript_with_ai_fallback(text: str, progress=gr.Progress()) -> Dict
             progress(0.1, desc="Processing transcript with AI...")
         
         # Tokenize and generate response
-        inputs = model_loader.tokenizer(prompt, return_tensors="pt").to(model_loader.device)
+        inputs = tokenizer(prompt, return_tensors="pt").to(model_loader.device)
         if progress:
             progress(0.4)
         
-        outputs = model_loader.model.generate(
+        outputs = model.generate(
             **inputs,
             max_new_tokens=1500,
             temperature=0.1,
@@ -487,7 +479,7 @@ def parse_transcript_with_ai_fallback(text: str, progress=gr.Progress()) -> Dict
             progress(0.8)
         
         # Decode the response
-        response = model_loader.tokenizer.decode(outputs[0], skip_special_tokens=True)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
         
         # Extract JSON from response
         try:
@@ -500,7 +492,7 @@ def parse_transcript_with_ai_fallback(text: str, progress=gr.Progress()) -> Dict
         
         if progress:
             progress(1.0)
-        return validate_parsed_data(parsed_data)
+        return parsed_data
     
     except torch.cuda.OutOfMemoryError:
         raise gr.Error("The model ran out of memory. Try with a smaller transcript.")
@@ -508,32 +500,6 @@ def parse_transcript_with_ai_fallback(text: str, progress=gr.Progress()) -> Dict
         logging.error(f"AI parsing error: {str(e)}")
         raise gr.Error(f"Error processing transcript: {str(e)}")
 
-def validate_parsed_data(data: Dict) -> Dict:
-    """Validate and clean the parsed data structure."""
-    if not isinstance(data, dict):
-        raise ValueError("Invalid data format")
-    
-    # Set default structure if missing
-    if 'grade_level' not in data:
-        data['grade_level'] = 'Unknown'
-    
-    if 'gpa' not in data:
-        data['gpa'] = {'weighted': 'N/A', 'unweighted': 'N/A'}
-    
-    if 'courses' not in data:
-        data['courses'] = []
-    
-    # Clean course data
-    for course in data['courses']:
-        if 'grade' in course:
-            course['grade'] = course['grade'].upper().strip()
-        
-        # Ensure numeric credits are strings
-        if 'credits' in course and isinstance(course['credits'], (int, float)):
-            course['credits'] = str(course['credits'])
-    
-    return data
-
 def format_transcript_output(data: Dict) -> str:
     """Format the parsed data into human-readable text."""
     output = []
@@ -1243,130 +1209,66 @@ def create_interface():
             4: False   # AI Assistant
         })
         
-        # Custom CSS for better styling
+        # Custom CSS
         app.css = """
-        .gradio-container {
-            max-width: 1200px !important;
-            margin: 0 auto;
-        }
-        .tab {
-            padding: 20px;
-            border-radius: 8px;
-            background: white;
-            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
-        }
-        .progress-bar {
-            height: 5px;
-            background: linear-gradient(to right, #4CAF50, #8BC34A);
-            margin-bottom: 15px;
-            border-radius: 3px;
-        }
-        .quiz-question {
-            margin-bottom: 15px;
-            padding: 15px;
-            background: #f5f5f5;
-            border-radius: 5px;
-        }
-        .profile-card {
-            border: 1px solid #e0e0e0;
-            border-radius: 8px;
-            padding: 15px;
-            margin-bottom: 15px;
-            background: white;
-        }
-        .chatbot {
-            min-height: 500px;
-        }
-        .completed-tab {
-            background: #2196F3 !important;
-            color: white !important;
-        }
-        .incomplete-tab {
-            background: #E0E0E0 !important;
-        }
-        .alert-box {
-            padding: 15px;
-            margin-bottom: 20px;
-            border: 1px solid transparent;
-            border-radius: 4px;
-            color: #31708f;
-            background-color: #d9edf7;
-            border-color: #bce8f1;
-        }
-        .nav-message {
-            padding: 10px;
-            margin: 10px 0;
-            border-radius: 4px;
-            background-color: #ffebee;
-            color: #c62828;
-        }
-        .model-loading {
-            padding: 15px;
-            margin: 15px 0;
-            border-radius: 4px;
-            background-color: #fff3e0;
-            color: #e65100;
-        }
+        .gradio-container { max-width: 1200px !important; margin: 0 auto !important; }
+        .tab-content { padding: 20px !important; border: 1px solid #e0e0e0 !important; border-radius: 8px !important; margin-top: 10px !important; }
+        .completed-tab { background: #4CAF50 !important; color: white !important; }
+        .incomplete-tab { background: #E0E0E0 !important; }
+        .nav-message { padding: 10px; margin: 10px 0; border-radius: 4px; background-color: #ffebee; color: #c62828; }
+        .file-upload { border: 2px dashed #4CAF50 !important; padding: 20px !important; border-radius: 8px !important; }
+        .progress-bar { height: 5px; background: linear-gradient(to right, #4CAF50, #8BC34A); margin-bottom: 15px; border-radius: 3px; }
+        .quiz-question { margin-bottom: 15px; padding: 15px; background: #f5f5f5; border-radius: 5px; }
         """
         
+        # Header
         gr.Markdown("""
         # Student Learning Assistant
         **Your personalized education companion**  
         Complete each step to get customized learning recommendations.
         """)
-        
-        # Progress tracker
+
+        # Navigation buttons
         with gr.Row():
-            with gr.Column(scale=1):
-                step1 = gr.Button("1. Upload Transcript", elem_classes="incomplete-tab")
-            with gr.Column(scale=1):
-                step2 = gr.Button("2. Learning Style Quiz", elem_classes="incomplete-tab", interactive=False)
-            with gr.Column(scale=1):
-                step3 = gr.Button("3. Personal Questions", elem_classes="incomplete-tab", interactive=False)
-            with gr.Column(scale=1):
-                step4 = gr.Button("4. Save & Review", elem_classes="incomplete-tab", interactive=False)
-            with gr.Column(scale=1):
-                step5 = gr.Button("5. AI Assistant", elem_classes="incomplete-tab", interactive=False)
-        
-        # Alert box for quiz submission
-        quiz_alert = gr.HTML(visible=False)
-        
-        # Navigation message
-        nav_message = gr.HTML(elem_classes="nav-message", visible=False)
-        
-        # Main tabs (hidden since we're using the button navigation)
-        with gr.Tabs(visible=False) as tabs:
-            # ===== TAB 1: Transcript Upload =====
-            with gr.Tab("Transcript Upload", id=0) as tab1:
+            with gr.Column(scale=1, min_width=100):
+                step1 = gr.Button("1. Transcript", elem_classes="incomplete-tab")
+            with gr.Column(scale=1, min_width=100):
+                step2 = gr.Button("2. Quiz", elem_classes="incomplete-tab", interactive=False)
+            with gr.Column(scale=1, min_width=100):
+                step3 = gr.Button("3. Profile", elem_classes="incomplete-tab", interactive=False)
+            with gr.Column(scale=1, min_width=100):
+                step4 = gr.Button("4. Review", elem_classes="incomplete-tab", interactive=False)
+            with gr.Column(scale=1, min_width=100):
+                step5 = gr.Button("5. Assistant", elem_classes="incomplete-tab", interactive=False)
+
+        nav_message = gr.HTML(visible=False)
+
+        # Main tabs container - Now VISIBLE
+        with gr.Tabs(visible=True) as tabs:
+            # ===== TAB 1: TRANSCRIPT UPLOAD =====
+            with gr.Tab("Transcript", id=0):
                 with gr.Row():
                     with gr.Column(scale=1):
                         gr.Markdown("### Step 1: Upload Your Transcript")
-                        gr.Markdown("Upload a PDF or image of your academic transcript to analyze your courses and GPA.")
-                        
-                        with gr.Group():
-                            transcript_file = gr.File(
-                                label="Transcript (PDF or Image)",
+                        with gr.Group(elem_classes="file-upload"):
+                            file_input = gr.File(
+                                label="Drag and drop your transcript here (PDF or Image)",
                                 file_types=ALLOWED_FILE_TYPES,
                                 type="filepath"
                             )
-                            upload_btn = gr.Button("Upload & Analyze", variant="primary")
-                        
-                        gr.Markdown("""
-                        **Supported Formats**: PDF, PNG, JPG  
-                        **Note**: Your file is processed locally and not stored permanently.
-                        """)
+                            upload_btn = gr.Button("Analyze Transcript", variant="primary")
                     
                     with gr.Column(scale=2):
                         transcript_output = gr.Textbox(
-                            label="Transcript Analysis",
+                            label="Analysis Results", 
                             lines=20,
                             interactive=False
                         )
                         transcript_data = gr.State()
-                
-                def process_transcript_and_update(file_obj, current_tab_status, progress=gr.Progress()):
+
+                def process_transcript(file_obj, current_tab_status):
                     try:
-                        output_text, data = parse_transcript(file_obj, progress)
+                        output_text, data = parse_transcript(file_obj)
                         if "Error" not in output_text:
                             new_status = current_tab_status.copy()
                             new_status[0] = True
@@ -1379,9 +1281,8 @@ def create_interface():
                                 gr.update(visible=False)
                             )
                     except Exception as e:
-                        logging.error(f"Upload error: {str(e)}")
                         return (
-                            f"Error processing transcript: {str(e)}", 
+                            f"Error: {str(e)}", 
                             None, 
                             current_tab_status,
                             gr.update(),
@@ -1390,21 +1291,19 @@ def create_interface():
                         )
                 
                 upload_btn.click(
-                    fn=process_transcript_and_update,
-                    inputs=[transcript_file, tab_completed],
-                    outputs=[transcript_output, transcript_data, tab_completed, step1, step2, nav_message],
-                    concurrency_limit=1
+                    process_transcript,
+                    inputs=[file_input, tab_completed],
+                    outputs=[transcript_output, transcript_data, tab_completed, step1, step2, nav_message]
                 )
-            
-            # ===== TAB 2: Learning Style Quiz =====
-            with gr.Tab("Learning Style Quiz", id=1) as tab2:
+
+            # ===== TAB 2: LEARNING STYLE QUIZ =====
+            with gr.Tab("Learning Style Quiz", id=1):
                 with gr.Row():
                     with gr.Column(scale=1):
                         gr.Markdown("### Step 2: Discover Your Learning Style")
-                        gr.Markdown("Complete this 20-question quiz to identify whether you're a visual, auditory, reading/writing, or kinesthetic learner.")
-                        
                         progress = gr.HTML("<div class='progress-bar' style='width: 0%'></div>")
                         quiz_submit = gr.Button("Submit Quiz", variant="primary")
+                        quiz_alert = gr.HTML(visible=False)
                     
                     with gr.Column(scale=2):
                         quiz_components = []
@@ -1422,7 +1321,7 @@ def create_interface():
                             label="Your Learning Style Results",
                             visible=False
                         )
-                
+
                 # Update progress bar as questions are answered
                 for component in quiz_components:
                     component.change(
@@ -1436,7 +1335,6 @@ def create_interface():
                     )
                 
                 def submit_quiz_and_update(*args):
-                    # The first argument is the tab_completed state, followed by answers
                     current_tab_status = args[0]
                     answers = args[1:]
                     
@@ -1450,11 +1348,10 @@ def create_interface():
                             new_status,
                             gr.update(elem_classes="completed-tab"),
                             gr.update(interactive=True),
-                            gr.update(value="<div class='alert-box'>Quiz submitted successfully! Scroll down to view your results.</div>", visible=True),
+                            gr.update(value="<div class='alert-box'>Quiz submitted successfully!</div>", visible=True),
                             gr.update(visible=False)
                         )
                     except Exception as e:
-                        logging.error(f"Quiz error: {str(e)}")
                         return (
                             f"Error evaluating quiz: {str(e)}",
                             gr.update(visible=True),
@@ -1470,14 +1367,12 @@ def create_interface():
                     inputs=[tab_completed] + quiz_components,
                     outputs=[learning_output, learning_output, tab_completed, step2, step3, quiz_alert, nav_message]
                 )
-            
-            # ===== TAB 3: Personal Questions =====
-            with gr.Tab("Personal Profile", id=2) as tab3:
+
+            # ===== TAB 3: PERSONAL QUESTIONS =====
+            with gr.Tab("Personal Profile", id=2):
                 with gr.Row():
                     with gr.Column(scale=1):
                         gr.Markdown("### Step 3: Tell Us About Yourself")
-                        gr.Markdown("This information helps us provide personalized recommendations.")
-                        
                         with gr.Group():
                             name = gr.Textbox(label="Full Name", placeholder="Your name")
                             age = gr.Number(label="Age", minimum=MIN_AGE, maximum=MAX_AGE, precision=0)
@@ -1488,7 +1383,8 @@ def create_interface():
                         
                         save_personal_btn = gr.Button("Save Information", variant="primary")
                         save_confirmation = gr.HTML(visible=False)
-                        
+                    
+                    with gr.Column(scale=1):
                         gr.Markdown("### Favorites")
                         with gr.Group():
                             movie = gr.Textbox(label="Favorite Movie")
@@ -1499,25 +1395,6 @@ def create_interface():
                             book_reason = gr.Textbox(label="Why do you like it?", lines=2)
                             character = gr.Textbox(label="Favorite Character (from any story)")
                             character_reason = gr.Textbox(label="Why do you like them?", lines=2)
-                    
-                    with gr.Column(scale=1):
-                        gr.Markdown("### Additional Information")
-                        
-                        blog_checkbox = gr.Checkbox(
-                            label="Would you like to write a short blog about your learning experiences?",
-                            value=False
-                        )
-                        blog_text = gr.Textbox(
-                            label="Your Learning Blog",
-                            placeholder="Write about your learning journey, challenges, goals...",
-                            lines=8,
-                            visible=False
-                        )
-                        blog_checkbox.change(
-                            lambda x: gr.update(visible=x),
-                            inputs=blog_checkbox,
-                            outputs=blog_text
-                        )
                 
                 def save_personal_info(name, age, interests, current_tab_status):
                     try:
@@ -1548,27 +1425,23 @@ def create_interface():
                     inputs=[name, age, interests, tab_completed],
                     outputs=[tab_completed, step3, step4, save_confirmation, nav_message]
                 )
-            
-            # ===== TAB 4: Save & Review =====
-            with gr.Tab("Save Profile", id=3) as tab4:
+
+            # ===== TAB 4: SAVE & REVIEW =====
+            with gr.Tab("Save Profile", id=3):
                 with gr.Row():
                     with gr.Column(scale=1):
                         gr.Markdown("### Step 4: Review & Save Your Profile")
-                        gr.Markdown("Verify your information before saving. You can return to previous steps to make changes.")
-                        
-                        save_btn = gr.Button("Save Profile", variant="primary")
-                        
-                        # Profile management section
                         with gr.Group():
                             load_profile_dropdown = gr.Dropdown(
                                 label="Load Existing Profile",
                                 choices=profile_manager.list_profiles(session_token.value),
-                                visible=bool(profile_manager.list_profiles(session_token.value))
+                                visible=False
                             )
                             with gr.Row():
-                                load_btn = gr.Button("Load", visible=bool(profile_manager.list_profiles(session_token.value)))
-                                delete_btn = gr.Button("Delete", variant="stop", visible=bool(profile_manager.list_profiles(session_token.value)))
+                                load_btn = gr.Button("Load", visible=False)
+                                delete_btn = gr.Button("Delete", variant="stop", visible=False)
                         
+                        save_btn = gr.Button("Save Profile", variant="primary")
                         clear_btn = gr.Button("Clear Form")
                     
                     with gr.Column(scale=2):
@@ -1576,21 +1449,15 @@ def create_interface():
                             "Your profile summary will appear here after saving.",
                             label="Profile Summary"
                         )
-                
-                # Save profile
+
                 def save_profile_and_update(*args):
-                    # Extract inputs
                     inputs = args[:-1]  # All except the last which is tab_completed
                     current_tab_status = args[-1]
                     
                     try:
-                        # Call the original save function
                         summary = profile_manager.save_profile(*inputs)
-                        
-                        # Update completion status
                         new_status = current_tab_status.copy()
                         new_status[3] = True
-                        
                         return (
                             summary,
                             new_status,
@@ -1599,7 +1466,6 @@ def create_interface():
                             gr.update(visible=False)
                         )
                     except Exception as e:
-                        logging.error(f"Save profile error: {str(e)}")
                         return (
                             f"Error saving profile: {str(e)}",
                             current_tab_status,
@@ -1613,7 +1479,7 @@ def create_interface():
                     inputs=[
                         name, age, interests, transcript_data, learning_output,
                         movie, movie_reason, show, show_reason,
-                        book, book_reason, character, character_reason, blog_text,
+                        book, book_reason, character, character_reason, "",
                         tab_completed
                     ],
                     outputs=[output_summary, tab_completed, step4, step5, nav_message]
@@ -1628,14 +1494,6 @@ def create_interface():
                     outputs=delete_btn
                 )
                 
-                # Load profile
-                load_btn.click(
-                    fn=lambda name: profile_manager.load_profile(name, session_token.value),
-                    inputs=load_profile_dropdown,
-                    outputs=output_summary
-                )
-                
-                # Delete profile
                 def delete_profile(name, session_token):
                     if not name:
                         raise gr.Error("Please select a profile to delete")
@@ -1645,7 +1503,6 @@ def create_interface():
                             profile_path.unlink()
                         return "Profile deleted successfully", ""
                     except Exception as e:
-                        logging.error(f"Delete profile error: {str(e)}")
                         raise gr.Error(f"Error deleting profile: {str(e)}")
                 
                 delete_btn.click(
@@ -1653,10 +1510,7 @@ def create_interface():
                     inputs=[load_profile_dropdown, session_token],
                     outputs=[output_summary, load_profile_dropdown]
                 ).then(
-                    fn=lambda: gr.update(
-                        choices=profile_manager.list_profiles(session_token.value),
-                        visible=bool(profile_manager.list_profiles(session_token.value))
-                    ),
+                    fn=lambda: profile_manager.list_profiles(session_token.value),
                     outputs=load_profile_dropdown
                 ).then(
                     fn=lambda: gr.update(visible=bool(profile_manager.list_profiles(session_token.value))),
@@ -1666,32 +1520,21 @@ def create_interface():
                     outputs=delete_btn
                 )
                 
-                # Clear form
                 clear_btn.click(
                     fn=lambda: [gr.update(value="") for _ in range(12)],
                     outputs=[
                         name, age, interests, 
                         movie, movie_reason, show, show_reason,
                         book, book_reason, character, character_reason,
-                        blog_text
+                        output_summary
                     ]
-                ).then(
-                    fn=lambda: gr.update(value=""),
-                    outputs=output_summary
-                ).then(
-                    fn=lambda: gr.update(value=False),
-                    outputs=blog_checkbox
-                ).then(
-                    fn=lambda: gr.update(visible=False),
-                    outputs=blog_text
                 )
-            
-            # ===== TAB 5: AI Teaching Assistant =====
-            with gr.Tab("AI Assistant", id=4) as tab5:
+
+            # ===== TAB 5: AI ASSISTANT =====
+            with gr.Tab("AI Assistant", id=4):
                 gr.Markdown("## Your Personalized Learning Assistant")
                 gr.Markdown("Ask me anything about studying, your courses, grades, or learning strategies.")
                 
-                # Chat interface with session token
                 chatbot = gr.ChatInterface(
                     fn=lambda msg, hist: teaching_assistant.generate_response(msg, hist, session_token.value),
                     examples=[
@@ -1703,8 +1546,8 @@ def create_interface():
                     ],
                     title=""
                 )
-        
-        # Tab navigation logic with completion check
+
+        # Navigation logic
         def navigate_to_tab(tab_index: int, tab_completed_status):
             current_tab = tabs.selected
             
@@ -1716,48 +1559,46 @@ def create_interface():
             if not tab_completed_status.get(current_tab, False):
                 return (
                     gr.Tabs(selected=current_tab),
-                    gr.update(value=f"⚠️ Complete Step {current_tab+1} first!", visible=True))
+                    gr.update(value=f"⚠️ Complete Step {current_tab+1} first!", visible=True)
+                )
             
             return gr.Tabs(selected=tab_index), gr.update(visible=False)
         
+        # Connect navigation buttons
         step1.click(
-            fn=lambda idx, status: navigate_to_tab(idx, status),
+            lambda idx, status: navigate_to_tab(idx, status),
             inputs=[gr.State(0), tab_completed],
             outputs=[tabs, nav_message]
         )
         step2.click(
-            fn=lambda idx, status: navigate_to_tab(idx, status),
+            lambda idx, status: navigate_to_tab(idx, status),
             inputs=[gr.State(1), tab_completed],
             outputs=[tabs, nav_message]
         )
         step3.click(
-            fn=lambda idx, status: navigate_to_tab(idx, status),
+            lambda idx, status: navigate_to_tab(idx, status),
             inputs=[gr.State(2), tab_completed],
             outputs=[tabs, nav_message]
         )
         step4.click(
-            fn=lambda idx, status: navigate_to_tab(idx, status),
+            lambda idx, status: navigate_to_tab(idx, status),
             inputs=[gr.State(3), tab_completed],
             outputs=[tabs, nav_message]
         )
         step5.click(
-            fn=lambda idx, status: navigate_to_tab(idx, status),
+            lambda idx, status: navigate_to_tab(idx, status),
             inputs=[gr.State(4), tab_completed],
             outputs=[tabs, nav_message]
         )
         
-        # Load DeepSeek model automatically
-        app.load(
-            fn=lambda: model_loader.load_model(),
-            outputs=[]
-        )
+        # Load model on startup
+        app.load(fn=lambda: model_loader.load_model(), outputs=[])
     
     return app
 
-# Create the interface
+# Create and launch the interface
 app = create_interface()
 
-# For Hugging Face Spaces deployment
 if __name__ == "__main__":
     app.launch()