prompts.py

SYSTEM_PROMPT = """You are an expert educational content analyzer. Your task is to analyze text content, 
identify distinct segments, and create high-quality educational quiz questions for each segment."""

ANALYSIS_PROMPT_TEMPLATE_GEMINI = """Analyze the following text and identify distinct segments within it and do text segmentation:
1. Segments should be STRICTLY max=15
2. For each segment/topic you identify:
   - Provide a SPECIFIC and UNIQUE topic name (3-5 words) that clearly differentiates it from other segments
   - List 3-5 key concepts discussed in that segment (be precise and avoid repetition between segments)
   - Write a brief summary of that segment (3-5 sentences)
   - Create 5 high-quality, meaningful quiz questions based DIRECTLY on the content in that segment only
   - Questions and answers should be only from the content of the segment

For each quiz question:
- Create cognitively demanding questions that test COMPREHENSION and ANALYSIS, not just recall
- Focus on CORE PRINCIPLES, key insights, and conceptual understanding
- Questions should require readers to think critically about the material
- AVOID superficial questions about statistics, numbers, or trivial details 
- AVOID questions about the document structure or presentation
- Create one correct answer that comes DIRECTLY from the text
- Create two plausible but incorrect answers that require discernment
- Ensure all answer options have similar length (± 2 words)
- Ensure the correct answer is clearly indicated with a ✓ symbol
IMPORTANT QUIZ QUESTION CRITERIA:
- Questions should assess understanding of fundamental concepts and principles
- Questions should require application of knowledge, not just memorization
- Questions should focus on important ideas that have educational value
- Questions should be meaningful in an educational context
- Questions should challenge the reader to think about implications and connections
- No need questions on the introduction, conclusion or the demonstration from the context,

ADDITIONAL REQUIREMENT:
- **First, detect the language of the original text.**
- **Generate ALL output (topic names, key concepts, summaries, and quizzes) in the same language as the original text.**
- If the text is in another language, generate responses in that original language.

COURSE INFORMATION:
- Course Name: {course_name}
- Section Name: {section_name}
- Lesson Name: {lesson_name}
- Use this information to contextualize the quiz and make it relevant to the educational content.
- Include this information in the JSON response structure.

Text:
{text}

RESPONSE FORMAT:
Return your answer as a valid JSON object with the following structure:
{{
    "course_info": {{
        "course_name": "{course_name}",
        "section_name": "{section_name}",
        "lesson_name": "{lesson_name}"
    }},
    "segments": [
        {{
            "topic_name": "Unique and Specific Topic Name",
            "key_concepts": ["concept1", "concept2", "concept3"],
            "summary": "Brief summary of this segment.",
            "quiz_questions": [
                {{
                    "question": "Question text?",
                    "options": [
                        {{
                            "text": "Option A",
                            "correct": false
                        }},
                        {{
                            "text": "Option B",
                            "correct": true
                        }},
                        {{
                            "text": "Option C",
                            "correct": false
                        }}
                    ]
                }}
            ]
        }}
    ]
}}
"""


ANALYSIS_PROMPT_TEMPLATE_CLAUDE = """Analyze the following text and identify distinct segments within it and do text segmentation:
1. Segments should be STRICTLY max=15
2. For each segment/topic you identify:
   - Provide a SPECIFIC and UNIQUE topic name (3-5 words) that clearly differentiates it from other segments
   - List 3-5 key concepts discussed in that segment (be precise and avoid repetition between segments)
   - Write a brief summary of that segment (3-5 sentences)
   - Create 5 high-quality, meaningful quiz questions based DIRECTLY on the content in that segment only
   - Questions and answers should be only from the content of the segment

For each quiz question:
- Create cognitively demanding questions that test COMPREHENSION and ANALYSIS, not just recall
- Focus on CORE PRINCIPLES, key insights, and conceptual understanding
- Questions should require readers to think critically about the material
- AVOID superficial questions about statistics, numbers, or trivial details 
- AVOID questions about the document structure or presentation
- Create one correct answer that comes DIRECTLY from the text
- Create two plausible but incorrect answers that require discernment
- Ensure all answer options have similar length (± 2 words)
- Ensure the correct answer is clearly indicated with a ✓ symbol

IMPORTANT QUIZ QUESTION CRITERIA:
- Questions should assess understanding of fundamental concepts and principles
- Questions should require application of knowledge, not just memorization
- Questions should focus on important ideas that have educational value
- Questions should be meaningful in an educational context
- Questions should challenge the reader to think about implications and connections
- No need for questions on the introduction, conclusion or the demonstration from the context

    ADDITIONAL REQUIREMENT:
    - **First, detect the language of the original text.**
    - **Generate ALL output (topic names, key concepts, summaries, and quizzes) in the same language as the original text.**
    - If the text is in Russian, generate all responses in Russian.
    - If the text is in another language, generate responses in that original language.


Text:
{text}

Course information:
- Course name: {course_name}
- Section name: {section_name}
- Lesson name: {lesson_name}

- Do NOT repeat key concepts across multiple segments unless absolutely necessary.
- Ensure the quiz questions challenge the reader and are not easily guessable.
- FOCUS ON CONCEPTUAL UNDERSTANDING, not trivial facts or statistics.
"""