Create app.py

app.py

@@ -0,0 +1,311 @@
+import gradio as gr
+import os
+from datetime import datetime
+import json
+import re
+import zipfile
+import docx
+from docx import Document
+import pdfplumber
+from langchain_groq import ChatGroq
+from langchain_community.utilities import SerpAPIWrapper
+from langchain_core.messages import HumanMessage
+
+# Initialize models (will use environment variables)
+def init_models():
+    groq_key = os.getenv("GROQ_API_KEY")
+    serp_key = os.getenv("SERPAPI_API_KEY")
+    
+    if not groq_key or not serp_key:
+        return None, None, None, None
+    
+    model_question_gen = ChatGroq(model="llama-3.3-70b-versatile", api_key=groq_key)
+    model_answer_gen = ChatGroq(model="llama-3.3-70b-versatile", api_key=groq_key)
+    model_trend_analyzer = ChatGroq(model="groq/compound", api_key=groq_key)
+    serp = SerpAPIWrapper(serpapi_api_key=serp_key)
+    
+    return model_question_gen, model_answer_gen, model_trend_analyzer, serp
+
+# Utility functions
+def extract_docx(path):
+    d = docx.Document(path)
+    return "\n".join(p.text for p in d.paragraphs if p.text.strip())
+
+def extract_pdf(path):
+    out = []
+    with pdfplumber.open(path) as pdf:
+        for p in pdf.pages:
+            t = p.extract_text()
+            if t: out.append(t)
+    return "\n".join(out)
+
+def extract_text(path):
+    if path.endswith(".pdf"): return extract_pdf(path)
+    if path.endswith(".docx"): return extract_docx(path)
+    return open(path, 'r', encoding='utf-8').read()
+
+def sanitize_json(text):
+    text = text.replace("```json", "").replace("```", "")
+    m = re.search(r"(\{.*\})", text, flags=re.DOTALL)
+    if not m:
+        raise RuntimeError(f"ERROR: LLM did NOT return JSON.")
+    blob = m.group(1)
+    blob = re.sub(r",\s*(\}|\])", r"\1", blob)
+    return json.loads(blob)
+
+def extract_units(syllabus_text, unit_range):
+    unit_range = unit_range.replace(" ", "")
+    if "-" in unit_range:
+        start, end = map(int, unit_range.split("-"))
+        units = list(range(start, end + 1))
+    else:
+        units = [int(u) for u in unit_range.split(",")]
+    
+    unit_header_pattern = r"(UNIT[\s\-—:]*([0-9IVX]+))"
+    matches = list(re.finditer(unit_header_pattern, syllabus_text, flags=re.I))
+    
+    if not matches:
+        return syllabus_text
+    
+    unit_blocks = []
+    for i, m in enumerate(matches):
+        raw_num = m.group(2).strip()
+        try:
+            if raw_num.isdigit():
+                num = int(raw_num)
+            else:
+                roman_map = {"I":1,"II":2,"III":3,"IV":4,"V":5,"VI":6,"VII":7,"VIII":8,"IX":9,"X":10}
+                num = roman_map.get(raw_num.upper(), None)
+        except:
+            num = None
+        
+        if num:
+            start = m.start()
+            end = matches[i+1].start() if i+1 < len(matches) else len(syllabus_text)
+            unit_blocks.append((num, start, end))
+    
+    extracted = ""
+    for u in units:
+        for block in unit_blocks:
+            if block[0] == u:
+                extracted += syllabus_text[block[1]:block[2]].strip() + "\n\n"
+    
+    return extracted.strip() if extracted else syllabus_text
+
+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
+3. A — Adaptive Difficulty Index
+4. N — Non-Repetitive Deep Coverage
+5. G — Granular Unit Balancing
+6. O — Outcome Mapping Discipline
+7. B — BIG15 Industry Integration
+8. I — Industry Application Layer
+9. G — GATE Layer Injection
+10. 1 — First-Half / Second-Half Coverage Integrity
+11. 5 — Five-Unit Symmetry
+12. S — Structured Output Discipline
+13. E — Exam-Mode Smart Switching
+14. T — Technical Depth Enforcement
+15. H — Holistic Coherence
+=== END OF MAANGO BIG15 FRAMEWORK ===
+"""
+    return maango_block + "\n\n" + base_prompt
+
+def build_question_prompt(subject, syllabus, numA, numB, numC, exam_mode):
+    base_prompt = f"""
+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"}}}}]
+}}
+
+Generate EXACTLY {numA} questions in partA, {numB} pairs in partB, {numC} pairs in partC.
+Syllabus: {syllabus}
+Return ONLY pure JSON. No commentary.
+"""
+    return apply_MAANGO_BIG15_framework(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_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)})")
+    
+    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)")
+    
+    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)")
+    
+    doc.save(output_path)
+
+def create_answer_key(code, name, answers, output_path):
+    doc = Document()
+    doc.add_heading(f"{name} - Answer Key", level=1)
+    doc.add_paragraph(f"Subject Code: {code}\n")
+    
+    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_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 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.save(output_path)
+
+def generate_exam(exam_mode, subject, code, units, numA, numB, numC, syllabus_file, progress=gr.Progress()):
+    try:
+        progress(0, desc="Initializing...")
+        
+        # Initialize models
+        model_q, model_a, model_t, serp = init_models()
+        if not model_q:
+            return None, "❌ API Keys not configured. Please set GROQ_API_KEY and SERPAPI_API_KEY in Hugging Face Spaces secrets."
+        
+        # Extract syllabus
+        progress(0.2, desc="Extracting syllabus...")
+        syllabus_text = extract_text(syllabus_file.name)
+        selected_syllabus = extract_units(syllabus_text, units)
+        
+        # Generate questions
+        progress(0.4, desc="Generating 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)
+        
+        # Generate answers
+        progress(0.7, desc="Generating answer key...")
+        a_prompt = f"Generate answers for: {json.dumps(q_json)}"
+        a_raw = model_a.invoke([HumanMessage(content=a_prompt)]).content
+        a_json = sanitize_json(a_raw)
+        
+        # Create files
+        progress(0.9, desc="Creating documents...")
+        qp_file = f"{code}_QuestionPaper.docx"
+        ak_file = f"{code}_AnswerKey.docx"
+        
+        create_question_paper(code, subject, q_json["partA"], q_json["partB"], q_json["partC"], qp_file)
+        create_answer_key(code, subject, a_json, ak_file)
+        
+        # Create zip
+        zip_file = f"{code}_ExamPackage.zip"
+        with zipfile.ZipFile(zip_file, 'w') as zipf:
+            zipf.write(qp_file)
+            zipf.write(ak_file)
+        
+        progress(1.0, desc="Complete!")
+        return zip_file, f"✅ Successfully generated exam package for {subject}!"
+        
+    except Exception as e:
+        return None, f"❌ Error: {str(e)}"
+
+# Custom CSS
+custom_css = """
+.gradio-container {
+    font-family: 'Inter', sans-serif;
+    max-width: 1200px !important;
+}
+.header-text {
+    text-align: center;
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+    color: white;
+    padding: 2rem;
+    border-radius: 10px;
+    margin-bottom: 2rem;
+}
+.feature-box {
+    background: #f8f9fa;
+    padding: 1rem;
+    border-radius: 8px;
+    border-left: 4px solid #667eea;
+}
+"""
+
+# Create Gradio interface
+with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
+    gr.HTML("""
+    <div class="header-text">
+        <h1>🎓 MAANGO BIG15 Exam Generator</h1>
+        <p>AI-Powered Question Paper & Answer Key Generator</p>
+        <p style="font-size: 0.9rem; opacity: 0.9;">Powered by Advanced LLM Technology | Industry-Standard Framework</p>
+    </div>
+    """)
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("### 📋 Exam Configuration")
+            exam_mode = gr.Dropdown(
+                choices=["Continuous Assessment (CA)", "End Semester Exam (ESE)", "GATE Style Internal Exam"],
+                label="Exam Mode",
+                value="End Semester Exam (ESE)"
+            )
+            subject = gr.Textbox(label="Subject Name", placeholder="e.g., Data Structures")
+            code = gr.Textbox(label="Subject Code", placeholder="e.g., CS301")
+            units = gr.Textbox(label="Units Range", value="1-5", placeholder="e.g., 1-3 or 1,3,5")
+            
+            gr.Markdown("### 📊 Question Distribution")
+            with gr.Row():
+                numA = gr.Number(label="Part A (Short)", value=10, precision=0)
+                numB = gr.Number(label="Part B (Descriptive)", value=5, precision=0)
+                numC = gr.Number(label="Part C (Case Study)", value=1, precision=0)
+        
+        with gr.Column(scale=1):
+            gr.Markdown("### 📁 Syllabus Upload")
+            syllabus_file = gr.File(label="Upload Syllabus", file_types=[".pdf", ".docx", ".txt"])
+            
+            gr.Markdown("""
+            <div class="feature-box">
+            <h4>✨ Key Features</h4>
+            <ul>
+                <li>🎯 Bloom's Taxonomy Alignment</li>
+                <li>🏢 Industry Tag Integration (TCS/Infosys/Wipro)</li>
+                <li>📈 Balanced Unit Coverage</li>
+                <li>🔍 GATE-Style Question Design</li>
+                <li>📝 Automatic Answer Key Generation</li>
+            </ul>
+            </div>
+            """)
+            
+            generate_btn = gr.Button("🚀 Generate Exam Package", variant="primary", size="lg")
+    
+    with gr.Row():
+        output_file = gr.File(label="📦 Download Package")
+        status_msg = gr.Textbox(label="Status", lines=2)
+    
+    generate_btn.click(
+        fn=generate_exam,
+        inputs=[exam_mode, subject, code, units, numA, numB, numC, syllabus_file],
+        outputs=[output_file, status_msg]
+    )
+    
+    gr.Markdown("""
+    ---
+    <center>
+    <p style="color: #666;">Developed with ❤️ using MAANGO BIG15 Framework | © 2024</p>
+    </center>
+    """)
+
+if __name__ == "__main__":
+    demo.launch()