Update app.py

app.py

@@ -5,48 +5,14 @@ import os
 import re
 from PyPDF2 import PdfReader
 from collections import defaultdict
+from openai import OpenAI  # pip install openai
 
-# ========== TRANSCRIPT PARSING FUNCTIONS ==========
-def extract_courses_with_grade_levels(text):
-    grade_level_pattern = r"(Grade|Year)\s*[:]?\s*(\d+|Freshman|Sophomore|Junior|Senior)"
-    grade_match = re.search(grade_level_pattern, text, re.IGNORECASE)
-    current_grade_level = grade_match.group(2) if grade_match else "Unknown"
-
-    course_pattern = r"""
-        (?:^|\n)
-        (?: (Grade|Year)\s*[:]?\s*(\d+|Freshman|Sophomore|Junior|Senior)\s*[\n-]* )?
-        (
-            (?:[A-Z]{2,}\s?\d{3})
-            |
-            [A-Z][a-z]+(?:\s[A-Z][a-z]+)*
-        )
-        \s*
-        (?: [:\-]?\s* ([A-F][+-]?|\d{2,3}%)? )?
-    """
-
-    courses_by_grade = defaultdict(list)
-    current_grade = current_grade_level
-
-    for match in re.finditer(course_pattern, text, re.VERBOSE | re.MULTILINE):
-        grade_context, grade_level, course, grade = match.groups()
-
-        if grade_context:
-            current_grade = grade_level
-
-        if course:
-            course_info = {"course": course.strip()}
-            if grade:
-                course_info["grade"] = grade.strip()
-            courses_by_grade[current_grade].append(course_info)
-
-    return dict(courses_by_grade)
+# Initialize OpenAI client (you'll need an API key)
+client = OpenAI(api_key="your-api-key-here")  # Replace with your actual API key
 
+# ========== TRANSCRIPT PARSING FUNCTIONS ==========
 def parse_transcript(file):
-    if file.name.endswith('.csv'):
-        df = pd.read_csv(file)
-    elif file.name.endswith('.xlsx'):
-        df = pd.read_excel(file)
-    elif file.name.endswith('.pdf'):
+    if file.name.endswith('.pdf'):
         text = ''
         reader = PdfReader(file)
         for page in reader.pages:
@@ -58,17 +24,16 @@ def parse_transcript(file):
         grade_match = re.search(r'(Grade|Year)[\s:]*(\d+|Freshman|Sophomore|Junior|Senior)', text, re.IGNORECASE)
         grade_level = grade_match.group(2) if grade_match else "Unknown"
 
-        # Enhanced GPA extraction
+        # GPA extraction
         gpa_data = {'weighted': "N/A", 'unweighted': "N/A"}
         gpa_patterns = [
             r'Weighted GPA[\s:]*(\d\.\d{1,2})',
             r'GPA \(Weighted\)[\s:]*(\d\.\d{1,2})',
-            r'Cumulative GPA \(Weighted\)[\s:]*(\d\.\d{1,2})',
             r'Unweighted GPA[\s:]*(\d\.\d{1,2})',
             r'GPA \(Unweighted\)[\s:]*(\d\.\d{1,2})',
-            r'Cumulative GPA \(Unweighted\)[\s:]*(\d\.\d{1,2})',
             r'GPA[\s:]*(\d\.\d{1,2})'
         ]
+        
         for pattern in gpa_patterns:
             for match in re.finditer(pattern, text, re.IGNORECASE):
                 gpa_value = match.group(1)
@@ -82,8 +47,6 @@ def parse_transcript(file):
                     if gpa_data['weighted'] == "N/A":
                         gpa_data['weighted'] = gpa_value
 
-        courses_by_grade = extract_courses_with_grade_levels(text)
-
         output_text = f"Grade Level: {grade_level}\n\n"
         if gpa_data['weighted'] != "N/A" or gpa_data['unweighted'] != "N/A":
             output_text += "GPA Information:\n"
@@ -94,43 +57,12 @@ def parse_transcript(file):
         else:
             output_text += "No GPA information found\n"
 
-        output_text += "\n(Courses not shown here)"
-
         return output_text, {
             "gpa": gpa_data,
-            "grade_level": grade_level,
-            "courses": courses_by_grade
+            "grade_level": grade_level
         }
     else:
-        return "Unsupported file format", None
-
-    # For CSV/XLSX fallback
-    gpa = "N/A"
-    for col in ['GPA', 'Grade Point Average', 'Cumulative GPA']:
-        if col in df.columns:
-            gpa = df[col].iloc[0] if isinstance(df[col].iloc[0], (float, int)) else "N/A"
-            break
-
-    grade_level = "N/A"
-    for col in ['Grade Level', 'Grade', 'Class', 'Year']:
-        if col in df.columns:
-            grade_level = df[col].iloc[0]
-            break
-
-    courses = []
-    for col in ['Course', 'Subject', 'Course Name', 'Class']:
-        if col in df.columns:
-            courses = df[col].tolist()
-            break
-
-    output_text = f"Grade Level: {grade_level}\nGPA: {gpa}\n\nCourses:\n"
-    output_text += "\n".join(f"- {course}" for course in courses)
-
-    return output_text, {
-        "gpa": {"unweighted": gpa, "weighted": "N/A"},
-        "grade_level": grade_level,
-        "courses": courses
-    }
+        return "Currently only PDF transcripts are supported", None
 
 # ========== LEARNING STYLE QUIZ ==========
 learning_style_questions = [
@@ -138,22 +70,7 @@ learning_style_questions = [
     "When you need directions to a new place, you prefer:",
     "When you learn a new skill, you prefer to:",
     "When you're trying to concentrate, you:",
-    "When you meet new people, you remember them by:",
-    "When you're relaxing, you prefer to:",
-    "When you're explaining something to someone, you:",
-    "When you're trying to remember something, you:",
-    "When you're in a classroom, you learn best when:",
-    "When you're trying to solve a problem, you:",
-    "When you're taking notes, you:",
-    "When you're learning new software, you prefer to:",
-    "When you're at a museum, you spend the most time:",
-    "When you're assembling furniture, you:",
-    "When you're learning new vocabulary, you:",
-    "When you're giving a presentation, you prefer:",
-    "When you're at a party, you enjoy:",
-    "When you're taking a break from studying, you:",
-    "When you're learning dance moves, you:",
-    "When you're choosing a book, you prefer:"
+    "When you meet new people, you remember them by:"
 ]
 
 learning_style_options = [
@@ -161,22 +78,7 @@ learning_style_options = [
     ["Look at a map (Visual)", "Have someone tell you (Auditory)", "Write down directions (Reading/Writing)", "Try walking/driving there (Kinesthetic)"],
     ["Read instructions (Reading/Writing)", "Have someone show you (Visual)", "Listen to explanations (Auditory)", "Try it yourself (Kinesthetic)"],
     ["Need quiet (Reading/Writing)", "Need background noise (Auditory)", "Need to move around (Kinesthetic)", "Need visual stimulation (Visual)"],
-    ["Their face (Visual)", "Their name (Auditory)", "What you talked about (Reading/Writing)", "What you did together (Kinesthetic)"],
-    ["Read (Reading/Writing)", "Listen to music (Auditory)", "Watch TV (Visual)", "Do something active (Kinesthetic)"],
-    ["Write it down (Reading/Writing)", "Tell them verbally (Auditory)", "Show them (Visual)", "Demonstrate physically (Kinesthetic)"],
-    ["See it written down (Visual)", "Say it out loud (Auditory)", "Write it down (Reading/Writing)", "Do it physically (Kinesthetic)"],
-    ["Reading materials (Reading/Writing)", "Listening to lectures (Auditory)", "Seeing diagrams (Visual)", "Doing hands-on activities (Kinesthetic)"],
-    ["Write down steps (Reading/Writing)", "Talk through it (Auditory)", "Draw diagrams (Visual)", "Try different approaches (Kinesthetic)"],
-    ["Write detailed notes (Reading/Writing)", "Record lectures (Auditory)", "Draw mind maps (Visual)", "Take minimal notes (Kinesthetic)"],
-    ["Read the manual (Reading/Writing)", "Have someone explain it (Auditory)", "Watch tutorial videos (Visual)", "Just start using it (Kinesthetic)"],
-    ["Reading descriptions (Reading/Writing)", "Listening to audio guides (Auditory)", "Looking at exhibits (Visual)", "Interactive displays (Kinesthetic)"],
-    ["Read instructions first (Reading/Writing)", "Ask someone to help (Auditory)", "Look at diagrams (Visual)", "Start assembling (Kinesthetic)"],
-    ["Write them repeatedly (Reading/Writing)", "Say them repeatedly (Auditory)", "Use flashcards (Visual)", "Use them in conversation (Kinesthetic)"],
-    ["Having detailed notes (Reading/Writing)", "Speaking freely (Auditory)", "Using visual aids (Visual)", "Demonstrating something (Kinesthetic)"],
-    ["Conversations (Auditory)", "People-watching (Visual)", "Dancing/games (Kinesthetic)", "Reading about people (Reading/Writing)"],
-    ["Read for fun (Reading/Writing)", "Listen to music (Auditory)", "Watch videos (Visual)", "Exercise (Kinesthetic)"],
-    ["Watch demonstrations (Visual)", "Listen to instructions (Auditory)", "Read choreography (Reading/Writing)", "Try the moves (Kinesthetic)"],
-    ["Text-heavy books (Reading/Writing)", "Audiobooks (Auditory)", "Books with pictures (Visual)", "Interactive books (Kinesthetic)"]
+    ["Their face (Visual)", "Their name (Auditory)", "What you talked about (Reading/Writing)", "What you did together (Kinesthetic)"]
 ]
 
 def learning_style_quiz(*answers):
@@ -187,35 +89,25 @@ def learning_style_quiz(*answers):
         "Kinesthetic": 0
     }
     
-    # Map each answer to a learning style
     for i, answer in enumerate(answers):
-        if answer in learning_style_options[i][0]:
+        if answer == learning_style_options[i][0]:
             scores["Reading/Writing"] += 1
-        elif answer in learning_style_options[i][1]:
+        elif answer == learning_style_options[i][1]:
             scores["Auditory"] += 1
-        elif answer in learning_style_options[i][2]:
+        elif answer == learning_style_options[i][2]:
             scores["Visual"] += 1
-        elif answer in learning_style_options[i][3]:
+        elif answer == learning_style_options[i][3]:
             scores["Kinesthetic"] += 1
     
-    # Get the highest score(s)
     max_score = max(scores.values())
     dominant_styles = [style for style, score in scores.items() if score == max_score]
     
-    # Generate result
     if len(dominant_styles) == 1:
-        result = f"Your primary learning style is: {dominant_styles[0]}"
+        return f"Your primary learning style is: {dominant_styles[0]}"
     else:
-        result = f"You have multiple strong learning styles: {', '.join(dominant_styles)}"
-    
-    # Add detailed breakdown
-    result += "\n\nDetailed Scores:\n"
-    for style, score in sorted(scores.items(), key=lambda x: x[1], reverse=True):
-        result += f"{style}: {score}/20\n"
-    
-    return result
+        return f"You have multiple strong learning styles: {', '.join(dominant_styles)}"
 
-# ========== SAVE STUDENT PROFILE FUNCTION ==========
+# ========== PROFILE MANAGEMENT ==========
 def save_profile(name, age, interests, transcript, learning_style, favorites, blog):
     data = {
         "name": name,
@@ -230,56 +122,66 @@ def save_profile(name, age, interests, transcript, learning_style, favorites, bl
     json_path = os.path.join("student_profiles", f"{name.replace(' ', '_')}_profile.json")
     with open(json_path, "w") as f:
         json.dump(data, f, indent=2)
-
-    markdown_summary = f"""### Student Profile: {name}
-**Age:** {age}  
-**Interests:** {interests}  
-**Learning Style:** {learning_style}  
-#### Transcript:
-{transcript_display(transcript)}
-#### Favorites:
-- Movie: {favorites['movie']} ({favorites['movie_reason']})
-- Show: {favorites['show']} ({favorites['show_reason']})
-- Book: {favorites['book']} ({favorites['book_reason']})
-- Character: {favorites['character']} ({favorites['character_reason']})
-#### Blog:
-{blog if blog else "_No blog provided_"}
-"""
-    return markdown_summary
-
-def transcript_display(transcript_dict):
-    if not transcript_dict:
-        return "No transcript uploaded."
-    if isinstance(transcript_dict, dict) and all(isinstance(v, list) for v in transcript_dict.values()):
-        display = ""
-        for grade_level, courses in transcript_dict.items():
-            display += f"\n**Grade {grade_level}**\n"
-            for course in courses:
-                display += f"- {course['course']}"
-                if 'grade' in course:
-                    display += f" (Grade: {course['grade']})"
-                display += "\n"
-        return display
-    return "\n".join([f"- {course}" for course in transcript_dict["courses"]] +
-                     [f"Grade Level: {transcript_dict['grade_level']}", f"GPA: {transcript_dict['gpa']}"])
+    
+    return "Profile saved successfully!"
+
+def load_profile():
+    profile_path = os.path.join("student_profiles", "student_profile.json")
+    if os.path.exists(profile_path):
+        with open(profile_path, "r") as f:
+            return json.load(f)
+    return {}
+
+# ========== AI TEACHING ASSISTANT ==========
+def generate_response(message, history, profile_data):
+    try:
+        # Prepare the prompt with profile information
+        prompt = f"""
+        You are a personalized teaching assistant. Here's the student profile:
+        
+        Name: {profile_data.get('name', 'N/A')}
+        Age: {profile_data.get('age', 'N/A')}
+        Grade Level: {profile_data.get('transcript', {}).get('grade_level', 'N/A')}
+        GPA: {profile_data.get('transcript', {}).get('gpa', {}).get('unweighted', 'N/A')}
+        Learning Style: {profile_data.get('learning_style', 'N/A')}
+        Interests: {profile_data.get('interests', 'N/A')}
+        
+        Current conversation:
+        {history}
+        
+        Student's message: {message}
+        
+        Provide a helpful, personalized response considering the student's profile.
+        """
+        
+        response = client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are a helpful teaching assistant."},
+                {"role": "user", "content": prompt}
+            ],
+            temperature=0.7
+        )
+        
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"Sorry, I encountered an error: {str(e)}"
 
 # ========== GRADIO INTERFACE ==========
 with gr.Blocks() as app:
+    # Profile tabs (keep your existing tabs)
     with gr.Tab("Step 1: Upload Transcript"):
-        transcript_file = gr.File(label="Upload your transcript (CSV, Excel, or PDF)")
+        transcript_file = gr.File(label="Upload your transcript (PDF)")
         transcript_output = gr.Textbox(label="Transcript Output")
         transcript_data = gr.State()
-        transcript_file.change(fn=parse_transcript, inputs=transcript_file, outputs=[transcript_output, transcript_data])
+        transcript_file.change(parse_transcript, inputs=transcript_file, outputs=[transcript_output, transcript_data])
 
     with gr.Tab("Step 2: Learning Style Quiz"):
-        gr.Markdown("### Complete this 20-question quiz to determine your learning style")
         quiz_components = []
         for i, (question, options) in enumerate(zip(learning_style_questions, learning_style_options)):
-            quiz_components.append(
-                gr.Radio(choices=options, label=f"{i+1}. {question}")
-            )
+            quiz_components.append(gr.Radio(options, label=f"{i+1}. {question}"))
         
-        learning_output = gr.Textbox(label="Learning Style Result", lines=5)
+        learning_output = gr.Textbox(label="Learning Style Result")
         gr.Button("Submit Quiz").click(
             learning_style_quiz,
             inputs=quiz_components,
@@ -300,141 +202,34 @@ with gr.Blocks() as app:
         character_reason = gr.Textbox(label="Why do you like that character?")
         blog_checkbox = gr.Checkbox(label="Do you want to write a blog?", value=False)
         blog_text = gr.Textbox(label="Write your blog here", visible=False, lines=5)
-        blog_checkbox.change(fn=lambda x: gr.update(visible=x), inputs=blog_checkbox, outputs=blog_text)
+        blog_checkbox.change(lambda x: gr.update(visible=x), inputs=blog_checkbox, outputs=blog_text)
 
-    with gr.Tab("Step 4: Save & Review"):
-        output_summary = gr.Markdown()
+    with gr.Tab("Step 4: Save Profile"):
         save_btn = gr.Button("Save Profile")
+        save_output = gr.Textbox(label="Save Status")
+        
+        save_btn.click(
+            save_profile,
+            inputs=[name, age, interests, transcript_data, learning_output, 
+                   {"movie": movie, "movie_reason": movie_reason,
+                    "show": show, "show_reason": show_reason,
+                    "book": book, "book_reason": book_reason,
+                    "character": character, "character_reason": character_reason},
+                   blog_text],
+            outputs=save_output
+        )
 
-        def gather_and_save(name, age, interests, movie, movie_reason, show, show_reason,
-                          book, book_reason, character, character_reason, blog, transcript, learning_style):
-            favorites = {
-                "movie": movie,
-                "movie_reason": movie_reason,
-                "show": show,
-                "show_reason": show_reason,
-                "book": book,
-                "book_reason": book_reason,
-                "character": character,
-                "character_reason": character_reason,
-            }
-            return save_profile(name, age, interests, transcript, learning_style, favorites, blog)
-
-        save_btn.click(fn=gather_and_save,
-                     inputs=[name, age, interests, movie, movie_reason, show, show_reason,
-                            book, book_reason, character, character_reason, blog_text,
-                            transcript_data, learning_output],
-                     outputs=output_summary)
-# Add these new imports at the top
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-from openai import OpenAI  # Make sure to install with pip install openai
-
-# ========== AI CHATBOT SETUP ==========
-# Initialize DeepSeek model for information retrieval
-deepseek_model_name = "deepseek-ai/deepseek-llm-7b"
-deepseek_tokenizer = AutoTokenizer.from_pretrained(deepseek_model_name)
-deepseek_model = AutoModelForCausalLM.from_pretrained(deepseek_model_name, torch_dtype=torch.float16)
-
-# Initialize ChatGPT (you'll need an OpenAI API key)
-client = OpenAI(api_key="your-openai-api-key")  # Replace with your actual API key
-
-def retrieve_information_with_deepseek(query, student_profile):
-    # Prepare context from student profile
-    profile_context = f"""
-    Student Profile:
-    Name: {student_profile.get('name', 'N/A')}
-    Age: {student_profile.get('age', 'N/A')}
-    Grade Level: {student_profile.get('transcript', {}).get('grade_level', 'N/A')}
-    GPA: {student_profile.get('transcript', {}).get('gpa', {}).get('unweighted', 'N/A')} (Unweighted)
-    Learning Style: {student_profile.get('learning_style', 'N/A')}
-    Interests: {student_profile.get('interests', 'N/A')}
-    """
-    
-    # Format the prompt for DeepSeek
-    prompt = f"""
-    [CONTEXT]
-    {profile_context}
-    
-    [QUERY]
-    {query}
-    
-    Based on the student profile and educational context, provide the most accurate and relevant information to answer the query.
-    """
-    
-    # Generate response with DeepSeek
-    inputs = deepseek_tokenizer(prompt, return_tensors="pt")
-    outputs = deepseek_model.generate(**inputs, max_new_tokens=200)
-    accurate_response = deepseek_tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    return accurate_response
-
-def generate_chat_response_with_chatgpt(message, history, student_profile):
-    # First retrieve accurate information with DeepSeek
-    accurate_info = retrieve_information_with_deepseek(message, student_profile)
-    
-    # Prepare conversation history
-    chat_history = "\n".join([f"User: {h[0]}\nAI: {h[1]}" for h in history])
-    
-    # Create ChatGPT prompt
-    prompt = f"""
-    You are a personalized teaching assistant. Use the following accurate information to craft a natural, helpful response:
-    
-    [ACCURATE INFORMATION]
-    {accurate_info}
-    
-    [CONVERSATION HISTORY]
-    {chat_history}
-    
-    [NEW MESSAGE]
-    User: {message}
-    
-    Respond in a friendly, conversational tone while ensuring all factual information remains accurate.
-    """
-    
-    # Get response from ChatGPT
-    response = client.chat.completions.create(
-        model="gpt-3.5-turbo",
-        messages=[
-            {"role": "system", "content": "You are a helpful teaching assistant."},
-            {"role": "user", "content": prompt}
-        ],
-        temperature=0.7
-    )
-    
-    return response.choices[0].message.content
-
-# ========== UPDATE GRADIO INTERFACE ==========
-# Add this new tab to your existing with gr.Blocks() as app:
-with gr.Blocks() as app:
-    # ... (keep all your existing tabs) ...
-    
+    # AI Teaching Assistant Tab
     with gr.Tab("🤖 AI Teaching Assistant"):
         gr.Markdown("## Your Personalized Learning Assistant")
-        gr.Markdown("Chat with your AI assistant for personalized learning support")
-        
         chatbot = gr.ChatInterface(
-            fn=lambda message, history: generate_chat_response_with_chatgpt(
-                message, 
-                history, 
-                student_profile=gr.State()
-            ),
+            fn=lambda message, history: generate_response(message, history, load_profile()),
             examples=[
-                "How should I study for my math test?",
-                "Can you explain this concept to me in a way that matches my learning style?",
-                "What are some good study strategies based on my GPA?",
-                "How can I improve my grades in science?"
-            ],
-            additional_inputs=[transcript_data, learning_output]
+                "How should I study for my next test?",
+                "Can you explain this concept in a way that matches my learning style?",
+                "What are some good study strategies for me?",
+                "How can I improve my grades?"
+            ]
         )
-        
-        # This connects the profile data to the chatbot
-        @app.load
-        def load_profile():
-            profile_path = os.path.join("student_profiles", "student_profile.json")
-            if os.path.exists(profile_path):
-                with open(profile_path, "r") as f:
-                    return json.load(f)
-            return {}
 
 app.launch()