Create prompts.py

prompts.py

@@ -0,0 +1,229 @@
+"""
+Prompt templates for the multi-agent exam generation system
+"""
+
+# Agent 1 - Generator Prompt (Llama 3.1 70B)
+GENERATOR_PROMPT = """
+You are an expert exam paper generator for engineering education. Create a structured question paper based on the following inputs:
+
+SUBJECT: {subject}
+STREAM: {stream}
+SYLLABUS: {syllabus_text}
+REFERENCE CONTEXT: {reference_text}
+REALTIME UPDATES: {realtime_updates}
+
+QUESTION DISTRIBUTION:
+- Part A: {part_a_count} questions × 2 marks each
+- Part B: {part_b_count} questions × 13 marks each (Either/Or pattern)
+- Part C: {part_c_count} questions × 14 marks each (Case studies)
+
+CRITICAL REQUIREMENTS:
+1. Difficulty Index: Maintain between 1.8-2.5
+2. Unit Distribution: Even coverage across all syllabus units
+3. Bloom's Taxonomy: {bloom_mix}
+4. Tags: {tag_requirements}
+
+{stream_specific_template}
+
+OUTPUT FORMAT - MUST BE VALID JSON:
+{{
+  "metadata": {{
+    "subject": "{subject}",
+    "stream": "{stream}",
+    "difficulty_index": 2.1,
+    "total_marks": {total_marks},
+    "units_covered": [1, 2, 3, 4, 5]
+  }},
+  "questions": [
+    {{
+      "part": "A",
+      "question_no": 1,
+      "sub_no": null,
+      "marks": 2,
+      "unit": 1,
+      "bloom_level": "Remember",
+      "tags": ["{tag_example}"],
+      "course_outcome": "CO1",
+      "question_text": "Define key concept from unit 1"
+    }},
+    {{
+      "part": "B",
+      "question_no": 1,
+      "sub_no": "a",
+      "marks": 13,
+      "unit": 2,
+      "bloom_level": "Apply",
+      "tags": ["{tag_example}"],
+      "course_outcome": "CO2",
+      "question_text": "Explain concept with example OR Solve this problem"
+    }},
+    {{
+      "part": "C",
+      "question_no": 1,
+      "sub_no": null,
+      "marks": 14,
+      "unit": 3,
+      "bloom_level": "Evaluate",
+      "tags": ["Case Study", "{tag_example}"],
+      "course_outcome": "CO3",
+      "question_text": "Analyze the given case study and provide solutions"
+    }}
+  ]
+}}
+
+Generate exactly {total_questions} questions following this structure. Ensure even unit distribution and proper bloom level mixing.
+"""
+
+# Agent 2 - Verifier Prompt (Gemma 2 27B)
+VERIFIER_PROMPT = """
+You are a quality verification agent for exam papers. Analyze the generated question paper and identify issues:
+
+GENERATED CONTENT:
+{generated_content}
+
+VERIFICATION CHECKLIST:
+1. Bloom's Taxonomy Correctness: {bloom_mix}
+2. Unit Distribution: Even across all syllabus units
+3. Question Count: Part A: {part_a_count}, Part B: {part_b_count}, Part C: {part_c_count}
+4. Tag Completeness: {tag_requirements}
+5. Difficulty Index: Between 1.8-2.5
+6. JSON Validity: Proper structure and formatting
+7. Duplicate Check: No repeated concepts
+8. Ambiguity Check: Clear, unambiguous questions
+
+OUTPUT FORMAT:
+{{
+  "status": "valid|needs_correction",
+  "corrections": [
+    {{
+      "target": "question_1",
+      "issue": "Bloom level incorrect",
+      "fix": "Change from 'Remember' to 'Apply'",
+      "priority": "high|medium|low"
+    }}
+  ],
+  "summary": {{
+    "unit_coverage_score": "X/Y units covered",
+    "bloom_distribution": {{"Remember": "X%", "Understand": "Y%", ...}},
+    "difficulty_estimate": 2.1,
+    "overall_quality": "excellent|good|needs_improvement"
+  }}
+}}
+
+Provide specific, actionable corrections.
+"""
+
+# Agent 3 - Formatter Prompt (Mixtral-8x7B)
+FORMATTER_PROMPT = """
+You are the final formatting and output agent. Take the verified content and produce the final structured output.
+
+ORIGINAL CONTENT:
+{original_content}
+
+VERIFICATION CORRECTIONS:
+{corrections}
+
+FINAL OUTPUT REQUIREMENTS:
+1. Apply all corrections from verification
+2. Ensure valid JSON structure
+3. Generate three complete blocks:
+   - Final Question Paper
+   - Answer Key
+   - OBE Summary
+
+ANSWER KEY FORMAT:
+For each question, provide:
+- Model answer
+- Step-by-step solution (where applicable)
+- Marking scheme breakdown
+
+OBE SUMMARY FORMAT:
+- Course outcome mapping
+- Bloom's taxonomy distribution
+- Difficulty analysis
+- Unit coverage report
+
+OUTPUT STRUCTURE:
+{{
+  "final_qp": {original_content},
+  "answers": [
+    {{
+      "question_ref": "A1",
+      "model_answer": "Detailed answer here...",
+      "marking_scheme": ["Point 1: 1 mark", "Point 2: 1 mark"],
+      "bloom_level": "Remember",
+      "course_outcome": "CO1"
+    }}
+  ],
+  "obe": {{
+    "course_outcomes": {{
+      "CO1": {{"coverage": "excellent", "questions": ["A1", "B1a"]}},
+      "CO2": {{"coverage": "good", "questions": ["A2", "B2a"]}}
+    }},
+    "bloom_distribution": {{
+      "Remember": "30%",
+      "Understand": "25%", 
+      "Apply": "20%",
+      "Analyze": "15%",
+      "Evaluate": "10%"
+    }},
+    "difficulty_index": 2.1,
+    "unit_coverage": "5/5 units covered",
+    "recommendations": "Suggestions for improvement"
+  }}
+}}
+"""
+
+# Stream-specific templates
+CSE_TEMPLATE = """
+CSE-SPECIFIC REQUIREMENTS:
+- Company Tags: MAANGO BIG15 (Microsoft, Amazon, Apple, Netflix, Google, Oracle, Bloomberg, IBM, Goldman Sachs, etc.)
+- Focus: Real-world coding problems, system design, algorithms
+- Part B: Either/Or should include coding problems vs theory questions
+- Part C: Case studies from recent tech industry scenarios
+- Bloom's Mix: 60% Remember/Understand, 40% Apply/Analyze/Evaluate
+"""
+
+NON_CSE_TEMPLATE = """
+NON-CSE SPECIFIC REQUIREMENTS:
+- GATE Reference Tags: All questions must reference GATE patterns
+- Focus: Fundamental concepts, problem-solving, theoretical understanding  
+- Part B: Either/Or should include derivation vs application problems
+- Part C: Engineering case studies with real-world applications
+- Bloom's Mix: 50% Remember/Understand, 50% Apply/Analyze/Evaluate
+"""
+
+def get_generator_prompt(subject, stream, syllabus_text, reference_text, realtime_updates,
+                        part_a_count, part_b_count, part_c_count):
+    """Build the complete generator prompt"""
+    
+    total_marks = (part_a_count * 2) + (part_b_count * 13) + (part_c_count * 14)
+    total_questions = part_a_count + (part_b_count * 2) + part_c_count
+    
+    if stream == "CSE":
+        stream_template = CSE_TEMPLATE
+        bloom_mix = "60% Remember/Understand, 40% Apply/Analyze/Evaluate"
+        tag_requirements = "MAANGO BIG15 company tags required"
+        tag_example = "Amazon"
+    else:
+        stream_template = NON_CSE_TEMPLATE  
+        bloom_mix = "50% Remember/Understand, 50% Apply/Analyze/Evaluate"
+        tag_requirements = "GATE reference tags required"
+        tag_example = "GATE-2024"
+    
+    return GENERATOR_PROMPT.format(
+        subject=subject,
+        stream=stream,
+        syllabus_text=syllabus_text[:2000],  # Limit length
+        reference_text=reference_text[:1500],
+        realtime_updates=realtime_updates,
+        part_a_count=part_a_count,
+        part_b_count=part_b_count,
+        part_c_count=part_c_count,
+        total_marks=total_marks,
+        total_questions=total_questions,
+        bloom_mix=bloom_mix,
+        tag_requirements=tag_requirements,
+        stream_specific_template=stream_template,
+        tag_example=tag_example
+    )