Update app.py

app.py

@@ -95,22 +95,55 @@ def extract_units(syllabus_text, unit_range):
 def apply_MAANGO_BIG15_framework(base_prompt):
     maango_block = """
 === MAANGO BIG15 ADVANCED QUESTION ENGINE FRAMEWORK ===
+
 You MUST follow ALL 15 pillars while generating the question paper:
+
 1. M — Multi-Cognitive Bloom Alignment
-2. A — Apply—Analyze Weightage Boost
+   – Strict distribution of Remember/Understand/Apply/Analyze/Evaluate/Create.
+   – 40% minimum higher-order (Apply/Analyze/Evaluate/Create).
+
+2. A — Apply–Analyze Weightage Boost
+   – At least 2 questions in Part B and 1 in Part C MUST be scenario/analytical.
+
 3. A — Adaptive Difficulty Index
+   – Maintain difficulty index between 1.8 and 2.5 for every question.
+
 4. N — Non-Repetitive Deep Coverage
+   – No overlap in concepts, no repeated phrasing.
+
 5. G — Granular Unit Balancing
+   – Ensure questions cover all units proportionately.
+
 6. O — Outcome Mapping Discipline
+   – Every question must be CO-aligned using strong engineering verbs.
+
 7. B — BIG15 Industry Integration
+   – Each question must include TCS/Infosys/Wipro/Accenture/Generic relevance.
+
 8. I — Industry Application Layer
+   – At least 20% questions include real-world industry scenarios.
+
 9. G — GATE Layer Injection
+   – Higher-order questions must reflect GATE-style design/analysis depth.
+
 10. 1 — First-Half / Second-Half Coverage Integrity
+    – Early questions from Unit 1–2, later from Unit 3–5.
+
 11. 5 — Five-Unit Symmetry
+    – Maintain balance across all parts (A/B/C).
+
 12. S — Structured Output Discipline
+    – Follow exact JSON schema, no deviations.
+
 13. E — Exam-Mode Smart Switching
+    – Auto-adjust tone depending on CA / ESE / GATE mode.
+
 14. T — Technical Depth Enforcement
+    – Strong technical keywords, no vague verbs.
+
 15. H — Holistic Coherence
+    – Ensure clarity, correctness, industry relevance, and zero ambiguity.
+
 === END OF MAANGO BIG15 FRAMEWORK ===
 """
     return maango_block + "\n\n" + base_prompt
@@ -120,52 +153,263 @@ def build_question_prompt(subject, syllabus, numA, numB, numC, exam_mode):
 You are an exam generator for {exam_mode} mode. Output ONLY VALID JSON.
 
 STRICT JSON SCHEMA:
+
 {{
-  "metadata": {{"subject": "{subject}", "date": "{datetime.now().strftime('%Y-%m-%d')}"}},
-  "partA": [{{"question_text": "string", "marks": 2, "unit": 1, "bloom_level": "Remember", "company_tag": "Generic"}}],
-  "partB": [{{"either": {{"question_text": "string", "marks": 10, "unit": 1, "bloom_level": "Analyze", "company_tag": "TCS"}}, "or": {{"question_text": "string", "marks": 10, "unit": 1, "bloom_level": "Analyze", "company_tag": "TCS"}}}}],
-  "partC": [{{"either": {{"question_text": "string", "marks": 15, "unit": 1, "bloom_level": "Create", "company_tag": "Infosys"}}, "or": {{"question_text": "string", "marks": 15, "unit": 1, "bloom_level": "Create", "company_tag": "Infosys"}}}}]
+  "metadata": {{
+    "subject": "{subject}",
+    "date": "{datetime.now().strftime('%Y-%m-%d')}"
+  }},
+  "partA": [
+    {{
+      "question_text": "string",
+      "marks": 2 or 3,
+      "unit": "number",
+      "bloom_level": "Remember/Understand/Apply/Analyze/Evaluate/Create",
+      "company_tag": "TCS/Infosys/Wipro/Generic"
+    }}
+  ],
+  "partB": [
+    {{
+      "either": {{
+        "question_text": "string",
+        "marks": 10,
+        "unit": "number",
+        "bloom_level": "Analyze/Evaluate/Create",
+        "company_tag": "TCS/Infosys/Wipro/Generic"
+      }},
+      "or": {{
+        "question_text": "string",
+        "marks": 10,
+        "unit": "number",
+        "bloom_level": "Analyze/Evaluate/Create",
+        "company_tag": "TCS/Infosys/Wipro/Generic"
+      }}
+    }}
+  ],
+  "partC": [
+    {{
+      "either": {{
+        "question_text": "string",
+        "marks": 15,
+        "unit": "number",
+        "bloom_level": "Create/Evaluate",
+        "company_tag": "TCS/Infosys/Wipro/Generic"
+      }},
+      "or": {{
+        "question_text": "string",
+        "marks": 15,
+        "unit": "number",
+        "bloom_level": "Create/Evaluate",
+        "company_tag": "TCS/Infosys/Wipro/Generic"
+      }}
+    }}
+  ]
 }}
 
-Generate EXACTLY {numA} questions in partA, {numB} pairs in partB, {numC} pairs in partC.
-Syllabus: {syllabus}
+REQUIREMENTS:
+- Generate EXACTLY {numA} questions in partA.
+- Generate EXACTLY {numB} pairs in partB.
+- Generate EXACTLY {numC} pairs in partC.
+- All questions must map correctly to the syllabus.
+- Maintain unit coverage balance.
+- Use industry relevance when appropriate.
+
+Syllabus:
+{syllabus}
+
 Return ONLY pure JSON. No commentary.
 """
     return apply_MAANGO_BIG15_framework(base_prompt)
 
-def build_answer_prompt(questions_json):
-    return f"""
-Generate answers in VALID JSON format for these questions:
+def apply_MAANGO_BIG15_answerkey(base_prompt):
+    maango_key_block = """
+=== MAANGO BIG15 ADVANCED ANSWER-KEY FRAMEWORK ===
+
+All answers MUST follow the 15 MAANGO pillars. Specifically:
+
+1. Bloom Alignment
+   – Answer must match Bloom level of the original question.
+   – Higher-order – include reasoning, evaluation, derivation, design logic.
+
+2. Industry Integration
+   – Wherever possible, include short 1–2 line relevance to TCS/Infosys/Wipro/Accenture/Generic IT.
+
+3. Correctness & Precision
+   – No vague words. Use technical definitions only.
+
+4. Depth Control
+   – Part A: concise (3–6 lines)
+   – Part B: structured multi-step reasoning
+   – Part C: full analytical/creative design solution
+
+5. Non-Repetition
+   – Do not reuse the same explanation style across answers.
+
+6. Difficulty Index Match
+   – Keep answer complexity aligned with the question's difficulty.
+
+7. Structured JSON Schema Enforcement
+   – Must follow the answer-key schema EXACTLY.
+
+8. GATE Style Reinforcement
+   – For higher-order questions, include formulas, assumptions, models.
+
+9. Holistic Clarity
+   – Avoid ambiguities. Provide crisp, exam-ready answers.
+
+=== END OF MAANGO BIG15 ANSWER-KEY FRAMEWORK ===
+"""
+    return maango_key_block + "\n\n" + base_prompt
+
+def build_answer_prompt(syllabus, questions_json):
+    base_prompt = f"""
+You are an expert answer key generator.
+
+Generate ANSWERS ONLY IN VALID JSON.
+
+STRICT JSON FORMAT:
+
+{{
+  "partA": [
+    {{
+      "question_text": "same as input",
+      "answer": "detailed but concise answer",
+      "marks": number
+    }}
+  ],
+  "partB": [
+    {{
+      "question_text": "either OR question merged or handled individually",
+      "answer": "model answer",
+      "marks": 10
+    }}
+  ],
+  "partC": [
+    {{
+      "question_text": "either OR question merged or handled individually",
+      "answer": "model answer",
+      "marks": 15
+    }}
+  ]
+}}
+
+INPUT QUESTIONS:
+{json.dumps(questions_json, indent=2)}
+
+RULES:
+- DO NOT change question text.
+- Provide complete, correct answers.
+- Return ONLY CLEAN JSON.
+"""
+    return apply_MAANGO_BIG15_answerkey(base_prompt)
+
+def apply_MAANGO_BIG15_trendanalysis(base_prompt):
+    maango_trend_block = """
+=== MAANGO BIG15 TREND ANALYSIS FRAMEWORK ===
+
+All analysis MUST follow:
+
+1. Bloom Pattern Extraction
+   – Count and percentage across all levels.
+
+2. Difficulty Distribution Mapping
+   – Detect imbalance or deviations from DI = 1.8–2.5.
+
+3. Unit Coverage Analysis
+   – Identify over-covered / under-covered units.
+
+4. Industry Relevance Analysis
+   – Evaluate TCS/Infosys/Wipro/Generic tag distribution.
+
+5. Question-Type Distribution
+   – Short-answer vs descriptive vs design-oriented.
+
+6. MAANGO Compliance Scoring
+   – Compute 0–100% MAANGO BIG15 alignment score.
+
+7. Improvement Suggestions
+   – Provide actionable, unit-wise refinements.
+
+8. GATE/ESE Competency Mapping
+   – Rate analytical & application strength.
 
+9. Holistic Insights
+   – Detect patterns indicating strong or weak syllabus areas.
+
+=== END OF MAANGO BIG15 TREND ANALYSIS FRAMEWORK ===
+"""
+    return maango_trend_block + "\n\n" + base_prompt
+
+def build_trend_prompt(subject, q_json):
+    base_prompt = f"""
+You are an exam trend analyzer. Output ONLY VALID JSON.
+
+STRICT SCHEMA:
 {{
-  "partA": [{{"question_text": "string", "answer": "detailed answer", "marks": 2}}],
-  "partB": [{{"question_text": "string", "answer": "model answer", "marks": 10}}],
-  "partC": [{{"question_text": "string", "answer": "comprehensive answer", "marks": 15}}]
+  "bloom_distribution": {{
+    "Remember": 0,
+    "Understand": 0,
+    "Apply": 0,
+    "Analyze": 0,
+    "Evaluate": 0,
+    "Create": 0
+  }},
+  "difficulty_insights": "string",
+  "industry_tag_stats": {{
+    "TCS": 0,
+    "Infosys": 0,
+    "Wipro": 0,
+    "Generic": 0
+  }},
+  "unit_coverage": {{
+    "unit1": 0,
+    "unit2": 0,
+    "unit3": 0,
+    "unit4": 0,
+    "unit5": 0
+  }},
+  "maango_score": "0-100",
+  "improvement_suggestions": "string"
 }}
 
-Questions: {json.dumps(questions_json)}
-Return ONLY pure JSON.
+RULE:
+Use the "unit" field inside every question object to compute unit_coverage. DO NOT guess.
+
+SUBJECT:
+{subject}
+
+QUESTIONS FOR ANALYSIS:
+{json.dumps(q_json, indent=2)}
 """
+    return apply_MAANGO_BIG15_trendanalysis(base_prompt)
 
 def create_question_paper(code, name, partA, partB, partC, output_path):
     doc = Document()
     doc.add_heading("SNS College of Technology", level=1)
     doc.add_paragraph(f"Subject Code: {code}    Subject: {name}")
-    doc.add_paragraph(f"Date: {datetime.now().strftime('%Y-%m-%d')}\n")
+    doc.add_paragraph(f"Date: {datetime.now().strftime('%Y-%m-%d')}")
+    doc.add_paragraph("Instructions: Answer as per parts and marks specified.\n")
     
     doc.add_heading("Part A (Short Answer)", level=2)
     for idx, q in enumerate(partA, 1):
-        doc.add_paragraph(f"{idx}. {q.get('question_text','')} (Marks: {q.get('marks',2)})")
+        text = f"{idx}. {q.get('question_text','')}\nMarks: {q.get('marks',0)} | Unit: {q.get('unit','')} | Bloom: {q.get('bloom_level','')} | Tag: {q.get('company_tag','')}"
+        doc.add_paragraph(text)
     
     doc.add_heading("Part B (Either/Or Questions)", level=2)
-    for idx, pair in enumerate(partB, len(partA)+1):
-        doc.add_paragraph(f"{idx}. Either: {pair['either']['question_text']} (10 marks)")
-        doc.add_paragraph(f"    Or: {pair['or']['question_text']} (10 marks)")
+    start_idx = len(partA)+1
+    for idx, pair in enumerate(partB, start_idx):
+        either = pair.get("either", {})
+        orq = pair.get("or", {})
+        doc.add_paragraph(f"{idx}. Either: {either.get('question_text','')}\nMarks: {either.get('marks',0)} | Unit: {either.get('unit','')} | Bloom: {either.get('bloom_level','')} | Tag: {either.get('company_tag','')}")
+        doc.add_paragraph(f"   Or: {orq.get('question_text','')}\nMarks: {orq.get('marks',0)} | Unit: {orq.get('unit','')} | Bloom: {orq.get('bloom_level','')} | Tag: {orq.get('company_tag','')}")
     
     doc.add_heading("Part C (Case/Design Questions)", level=2)
-    for idx, pair in enumerate(partC, len(partA)+len(partB)+1):
-        doc.add_paragraph(f"{idx}. Either: {pair['either']['question_text']} (15 marks)")
-        doc.add_paragraph(f"    Or: {pair['or']['question_text']} (15 marks)")
+    start_idx = start_idx + len(partB)
+    for idx, pair in enumerate(partC, start_idx):
+        either = pair.get("either", {})
+        orq = pair.get("or", {})
+        doc.add_paragraph(f"{idx}. Either: {either.get('question_text','')}\nMarks: {either.get('marks',0)} | Unit: {either.get('unit','')} | Bloom: {either.get('bloom_level','')} | Tag: {either.get('company_tag','')}")
+        doc.add_paragraph(f"   Or: {orq.get('question_text','')}\nMarks: {orq.get('marks',0)} | Unit: {orq.get('unit','')} | Bloom: {orq.get('bloom_level','')} | Tag: {orq.get('company_tag','')}")
     
     doc.save(output_path)
 
@@ -176,16 +420,73 @@ def create_answer_key(code, name, answers, output_path):
     
     doc.add_heading("Part A Answers", level=2)
     for idx, a in enumerate(answers.get("partA", []), 1):
-        doc.add_paragraph(f"{idx}. {a.get('answer','N/A')}")
+        doc.add_paragraph(f"{idx}. {a.get('question_text','')}\nAnswer: {a.get('answer','')}")
     
-    doc.add_heading("Part B Answers", level=2)
-    for idx, a in enumerate(answers.get("partB", []), len(answers.get("partA",[]))+1):
-        doc.add_paragraph(f"{idx}. {a.get('answer','N/A')}")
+    doc.add_heading("Part B Answers (Either option)", level=2)
+    start_idx = len(answers.get("partA", []))+1
+    for idx, a in enumerate(answers.get("partB", []), start_idx):
+        doc.add_paragraph(f"{idx}. {a.get('question_text','')}\nAnswer: {a.get('answer','')}")
     
-    doc.add_heading("Part C Answers", level=2)
-    start = len(answers.get("partA",[]))+len(answers.get("partB",[]))+1
-    for idx, a in enumerate(answers.get("partC", []), start):
-        doc.add_paragraph(f"{idx}. {a.get('answer','N/A')}")
+    doc.add_heading("Part C Answers (Either option)", level=2)
+    start_idx += len(answers.get("partB", []))
+    for idx, a in enumerate(answers.get("partC", []), start_idx):
+        doc.add_paragraph(f"{idx}. {a.get('question_text','')}\nAnswer: {a.get('answer','')}")
+    
+    doc.save(output_path)
+
+def create_trend_report(code, name, trend_json, serp_data, output_path):
+    doc = Document()
+    doc.add_heading(f"{name} - Trend Analysis Report", level=1)
+    doc.add_paragraph(f"Subject Code: {code}")
+    doc.add_paragraph(f"Date: {datetime.now().strftime('%Y-%m-%d')}\n")
+    
+    bd = trend_json.get("bloom_distribution", {})
+    doc.add_heading("Bloom Distribution", level=2)
+    if bd:
+        for k, v in bd.items():
+            doc.add_paragraph(f"- {k}: {v}", style='List Bullet')
+    else:
+        doc.add_paragraph("No bloom distribution data found.")
+    
+    doc.add_heading("Difficulty Insights", level=2)
+    diff = trend_json.get("difficulty_insights", "")
+    doc.add_paragraph(diff if diff else "No difficulty insights provided.")
+    
+    doc.add_heading("Industry Tag Statistics", level=2)
+    its = trend_json.get("industry_tag_stats", {})
+    if its:
+        for k, v in its.items():
+            doc.add_paragraph(f"- {k}: {v}", style='List Bullet')
+    else:
+        doc.add_paragraph("No industry tag stats found.")
+    
+    doc.add_heading("Unit Coverage", level=2)
+    uc = trend_json.get("unit_coverage", {})
+    if uc:
+        for k, v in uc.items():
+            doc.add_paragraph(f"- {k}: {v}", style='List Bullet')
+    else:
+        doc.add_paragraph("No unit coverage data found.")
+    
+    doc.add_heading("MAANGO BIG15 Compliance Score", level=2)
+    maango = trend_json.get("maango_score", "")
+    doc.add_paragraph(f"Score: {maango if maango else 'N/A'}")
+    
+    doc.add_heading("Improvement Suggestions", level=2)
+    sugg = trend_json.get("improvement_suggestions", "")
+    doc.add_paragraph(sugg if sugg else "No suggestions provided.")
+    
+    if serp_data:
+        doc.add_heading("SERP / Reference Data (summary)", level=2)
+        try:
+            serp_text = json.dumps(serp_data, indent=2) if not isinstance(serp_data, str) else serp_data
+        except Exception:
+            serp_text = str(serp_data)
+        max_chars = 6000
+        if len(serp_text) > max_chars:
+            serp_text = serp_text[:max_chars] + "\n\n[Truncated for brevity]"
+        for line in serp_text.splitlines():
+            doc.add_paragraph(line)
     
     doc.save(output_path)
 
@@ -198,26 +499,53 @@ def generate_exam(exam_mode, subject, code, units, numA, numB, numC, syllabus_fi
         syllabus_text = extract_text(syllabus_file.name)
         selected_syllabus = extract_units(syllabus_text, units)
         
+        if not selected_syllabus.strip():
+            return None, "❌ No syllabus found for given units."
+        
+        # STEP 1: Generate Questions
         q_prompt = build_question_prompt(subject, selected_syllabus, numA, numB, numC, exam_mode)
         q_raw = model_q.invoke([HumanMessage(content=q_prompt)]).content
         q_json = sanitize_json(q_raw)
         
-        a_prompt = build_answer_prompt(q_json)
+        partA = q_json.get("partA", [])
+        partB = q_json.get("partB", [])
+        partC = q_json.get("partC", [])
+        
+        if not (partA or partB or partC):
+            return None, "❌ Generated question JSON missing required parts."
+        
+        # STEP 2: Fetch SERP data
+        try:
+            serp_data = serp.run(f"{subject} latest industry syllabus questions trends")
+        except Exception as e:
+            serp_data = f"SERP fetch failed: {e}"
+        
+        # STEP 3: Analyze trends
+        t_prompt = build_trend_prompt(subject, q_json)
+        t_raw = model_t.invoke([HumanMessage(content=t_prompt)]).content
+        t_json = sanitize_json(t_raw)
+        
+        # STEP 4: Generate Answer Key
+        a_prompt = build_answer_prompt(selected_syllabus, q_json)
         a_raw = model_a.invoke([HumanMessage(content=a_prompt)]).content
         a_json = sanitize_json(a_raw)
         
+        # STEP 5: Create DOCX files
         qp_file = f"{code}_QuestionPaper.docx"
         ak_file = f"{code}_AnswerKey.docx"
+        ta_file = f"{code}_TrendAnalysis.docx"
         
-        create_question_paper(code, subject, q_json["partA"], q_json["partB"], q_json["partC"], qp_file)
+        create_question_paper(code, subject, partA, partB, partC, qp_file)
         create_answer_key(code, subject, a_json, ak_file)
+        create_trend_report(code, subject, t_json, serp_data, ta_file)
         
         zip_file = f"{code}_ExamPackage.zip"
         with zipfile.ZipFile(zip_file, 'w') as zipf:
             zipf.write(qp_file)
             zipf.write(ak_file)
+            zipf.write(ta_file)
         
-        return zip_file, f"✅ Successfully generated exam package for {subject}!"
+        return zip_file, f"✅ Successfully generated exam package for {subject}!\n📊 MAANGO Score: {t_json.get('maango_score', 'N/A')}"
         
     except Exception as e:
         return None, f"❌ Error: {str(e)}"
@@ -296,9 +624,9 @@ with gr.Blocks() as demo:
     }
     </style>
     <div class="header-gradient">
-        <h1>SNS Tech - Q&A Agent x Codeboosters Tech</h1>
-        <p><strong>AI-Powered Question Paper & Answer Key Generator</strong></p>
-        <p>Powered by Advanced LLM Technology | Industry-Standard Framework | Developed by Codeboosters Tech Team</p>
+        <h1>🎓 SNS Tech - Q&A Agent x Codeboosters Tech</h1>
+        <p><strong>AI-Powered Question Paper & Answer Key Generator with Trend Analysis</strong></p>
+        <p>Powered by MAANGO BIG15 Framework | Advanced LLM Technology | Developed by Codeboosters Tech Team</p>
     </div>
     """)
     
@@ -326,22 +654,25 @@ with gr.Blocks() as demo:
             
             gr.HTML("""
             <div class="feature-card">
-                <h4>✨ Key Features</h4>
+                <h4>✨ MAANGO BIG15 Features</h4>
                 <ul>
-                    <li>🎯 Bloom's Taxonomy Alignment</li>
+                    <li>🎯 Multi-Cognitive Bloom Alignment</li>
                     <li>🏢 Industry Tag Integration (TCS/Infosys/Wipro)</li>
-                    <li>📈 Balanced Unit Coverage</li>
-                    <li>🔍 GATE-Style Question Design</li>
+                    <li>📈 Granular Unit Balancing</li>
+                    <li>🔍 GATE Layer Injection</li>
                     <li>📝 Automatic Answer Key Generation</li>
+                    <li>📊 Advanced Trend Analysis with SERP Data</li>
+                    <li>🎓 MAANGO Compliance Scoring (0-100)</li>
+                    <li>💡 AI-Powered Improvement Suggestions</li>
                 </ul>
             </div>
             """)
             
-            generate_btn = gr.Button("🚀 Generate Exam Package", variant="primary", size="lg")
+            generate_btn = gr.Button("🚀 Generate Complete Exam Package", variant="primary", size="lg")
     
     with gr.Row():
-        output_file = gr.File(label="📦 Download Package")
-        status_msg = gr.Textbox(label="Status", lines=2)
+        output_file = gr.File(label="📦 Download Package (Question Paper + Answer Key + Trend Analysis)")
+        status_msg = gr.Textbox(label="Status", lines=3)
     
     generate_btn.click(
         fn=generate_exam,
@@ -351,7 +682,8 @@ with gr.Blocks() as demo:
     
     gr.HTML("""
     <footer>
-        <p>Developed with ❤️ by Veerakumar C B | © 2024</p>
+        <p><strong>MAANGO BIG15 Framework</strong> - 15 Pillars of Excellence in Question Paper Generation</p>
+        <p>Developed with ❤️ by Veerakumar C B | Codeboosters Tech | © 2024</p>
     </footer>
     """)