from educhain import Educhain

client = Educhain()

# Basic MCQ generation
mcq = client.qna_engine.generate_questions(
    topic="Solar System",
    num=3,
    question_type="Multiple Choice"
)

# Advanced MCQ with custom parameters
advanced_mcq = client.qna_engine.generate_questions(
    topic="Solar System",
    num=3,
    question_type="Multiple Choice",
    difficulty_level="Hard",
    custom_instructions="Include recent discoveries"
)

print(mcq.model_dump_json())  # View in JSON format , For Dictionary format use mcq.model_dump()

from educhain import Educhain

client = Educhain()

# Basic lesson plan
lesson = client.content_engine.generate_lesson_plan(
    topic="Photosynthesis"
)

# Advanced lesson plan with specific parameters
detailed_lesson = client.content_engine.generate_lesson_plan(
    topic="Photosynthesis",
    duration="60 minutes",
    grade_level="High School",
    learning_objectives=["Understanding the process", "Identifying key components"]
)

print(lesson.model_dump_json())  # View in JSON format , For Dictionary format use lesson.model_dump()

from educhain import Educhain, LLMConfig
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_openai import ChatOpenAI

# Using Gemini
gemini_model = ChatGoogleGenerativeAI(
    model="gemini-2.0-flash",
    google_api_key="YOUR_GOOGLE_API_KEY"
)
gemini_config = LLMConfig(custom_model=gemini_model)
gemini_client = Educhain(gemini_config)

# Using GPT-4
gpt4_model = ChatOpenAI(
    model_name="gpt-4.1",
    openai_api_key="YOUR_OPENAI_API_KEY"
)
gpt4_config = LLMConfig(custom_model=gpt4_model)
gpt4_client = Educhain(gpt4_config)

from educhain import Educhain

client = Educhain()
questions = client.qna_engine.generate_questions(topic="Climate Change", num=5)

# Export to JSON
questions.json("climate_questions.json")

# Export to PDF
questions.to_pdf("climate_questions.pdf")

# Export to CSV
questions.to_csv("climate_questions.csv")

from educhain import Educhain

client = Educhain()

# Custom template for questions
custom_template = """
Generate {num} {question_type} questions about {topic}.
Ensure the questions are:
- At {difficulty_level} level
- Focus on {learning_objective}
- Include practical examples
- {custom_instructions}
"""

questions = client.qna_engine.generate_questions(
    topic="Machine Learning",
    num=3,
    question_type="Multiple Choice",
    difficulty_level="Intermediate",
    learning_objective="Understanding Neural Networks",
    custom_instructions="Include recent developments",
    prompt_template=custom_template
)

from educhain import Educhain

client = Educhain()

# From URL
url_questions = client.qna_engine.generate_questions_from_data(
    source="https://example.com/article",
    source_type="url",
    num=3
)

# From PDF
pdf_questions = client.qna_engine.generate_questions_from_data(
    source="path/to/document.pdf",
    source_type="pdf",
    num=3
)

# From Text File
text_questions = client.qna_engine.generate_questions_from_data(
    source="path/to/content.txt",
    source_type="text",
    num=3
)

📹 Generate Questions from YouTube Videos

from educhain import Educhain

client = Educhain()

# Basic usage - Generate 3 MCQs from a YouTube video
questions = client.qna_engine.generate_questions_from_youtube(
    url="https://www.youtube.com/watch?v=dQw4w9WgXcQ",
    num=3
)
print(questions.model_dump_json())

# Generate questions preserving original language
preserved_questions = client.qna_engine.generate_questions_from_youtube(
    url="https://www.youtube.com/watch?v=dQw4w9WgXcQ",
    num=2,
    target_language='hi',
    preserve_original_language=True  # Keeps original language
)

🥽 Generate Questions from Images

from educhain import Educhain

client = Educhain() #Default is 4o-mini (make sure to use a multimodal LLM!)

question = client.qna_engine.solve_doubt(
    image_source="path-to-your-image",
    prompt="Explain the diagram in detail",
    detail_level = "High" 
    )

print(question)

🥽 Generate Visual Questions

from langchain_google_genai import ChatGoogleGenerativeAI
from educhain import Educhain, LLMConfig

gemini_flash = ChatGoogleGenerativeAI(model="gemini-2.0-flash", google_api_key=GOOGLE_API_KEY)

flash_config = LLMConfig(custom_model=gemini_flash)

client = Educhain(flash_config)

ques = client.qna_engine.generate_visual_questions(
        topic="GMAT Statistics", num=10 )

print(ques.model_dump_json())

🎓 Generate Pedagogy-Based Content

from educhain import Educhain, LLMConfig

client = Educhain()

# Bloom's Taxonomy - All cognitive levels
blooms_content = client.content_engine.generate_pedagogy_content(
    topic="Data Science Fundamentals",
    pedagogy="blooms_taxonomy",
    target_level="All levels",  # or specific: "Remember", "Understand", "Apply", "Analyze", "Evaluate", "Create"
    grade_level="University",
    custom_instructions="Include Python programming and statistical concepts"
)

# Socratic Questioning - Strategic questioning for critical thinking
socratic_content = client.content_engine.generate_pedagogy_content(
    topic="Climate Change Solutions",
    pedagogy="socratic_questioning",
    depth_level="Intermediate",  # "Basic", "Intermediate", "Advanced"
    student_level="High School",  # "Elementary", "Middle School", "High School", "University"
    custom_instructions="Encourage analysis of multiple perspectives and evidence"
)

# Project-Based Learning - Comprehensive project design
project_content = client.content_engine.generate_pedagogy_content(
    topic="Documentary Filmmaking",
    pedagogy="project_based_learning",
    team_size="2-3 students",  # "Individual", "2-3 students", "4-5 students", "Large group"
    project_duration="2 weeks",  # "1 week", "2 weeks", "4-6 weeks", "Full semester"
    industry_focus="Media Production",  # "General", "Technology", "Healthcare", "Arts", etc.
    custom_instructions="Focus on social justice themes and community impact"
)

# Flipped Classroom - Pre-class study with in-class activities
flipped_content = client.content_engine.generate_pedagogy_content(
    topic="Machine Learning Algorithms",
    pedagogy="flipped_classroom",
    class_duration="40 minutes",  # "30 minutes", "50 minutes", "90 minutes"
    prep_time="30 minutes",  # "15-30 minutes", "30-45 minutes", "45-60 minutes"
    technology_level="Low",  # "Low", "Moderate", "High"
    custom_instructions="Include coding exercises and peer programming"
)

# Inquiry-Based Learning - Student-driven exploration
inquiry_content = client.content_engine.generate_pedagogy_content(
    topic="Impact of Social Media on Democracy",
    pedagogy="inquiry_based_learning",
    inquiry_type="Guided",  # "Guided", "Open", "Structured"
    investigation_scope="Moderate",  # "Narrow", "Moderate", "Broad"
    student_autonomy="Balanced",  # "Low", "Balanced", "High"
    custom_instructions="Use primary sources and contemporary case studies"
)

# Constructivist - Experience-based learning
constructivist_content = client.content_engine.generate_pedagogy_content(
    topic="Statistical Analysis",
    pedagogy="constructivist",
    prior_knowledge_level="Mixed",  # "Beginner", "Mixed", "Advanced"
    social_interaction_focus="Moderate",  # "Low", "Moderate", "High"
    reflection_emphasis="Strong",  # "Weak", "Moderate", "Strong"
    custom_instructions="Use real datasets and collaborative problem-solving"
)

# Gamification - Game mechanics for motivation
gamified_content = client.content_engine.generate_pedagogy_content(
    topic="Japanese Language Fundamentals",
    pedagogy="gamification",
    game_mechanics="Points, streaks, badges, social challenges",  # Customize game elements
    competition_level="Low",  # "Low", "Moderate", "High"
    technology_platform="Mobile App",  # "Web-based", "Mobile App", "Classroom", "Mixed"
    custom_instructions="Include cultural context and conversation practice"
)

# Peer Learning - Structured collaboration
peer_content = client.content_engine.generate_pedagogy_content(
    topic="Contemporary World Literature",
    pedagogy="peer_learning",
    group_size="2-3 students",  # "Pairs", "2-3 students", "3-4 students", "Large groups"
    collaboration_type="Book clubs and discussion circles",  # "Mixed", "Peer tutoring", "Group projects", etc.
    skill_diversity="High",  # "Low", "Moderate", "High"
    custom_instructions="Include cross-cultural perspectives and author research"
)

# Available pedagogies: 'blooms_taxonomy', 'socratic_questioning', 
# 'project_based_learning', 'flipped_classroom', 'inquiry_based_learning',
# 'constructivist', 'gamification', 'peer_learning'

print(blooms_content.model_dump_json())

Error: Authentication failed. Please check your API key.

Solution: Verify that your API key is correct and properly set. For OpenAI or Google API keys, ensure they are active and have sufficient quota remaining.

# Correct way to set API keys
import os
os.environ["OPENAI_API_KEY"] = "your-api-key-here"
# or
os.environ["GOOGLE_API_KEY"] = "your-api-key-here"

Issue: The model generates content that doesn't match your expectations or requirements.

Solution: Try adjusting the parameters or providing more specific instructions:

# Be more specific with your requirements
questions = client.qna_engine.generate_questions(
    topic="Python Programming",
    num=3,
    difficulty_level="Intermediate",
    custom_instructions="Focus on object-oriented programming concepts. Include code examples in each question."
)

ModuleNotFoundError: No module named 'educhain'

Solution: Ensure you've installed the package correctly:

pip install educhain --upgrade

If you're using a virtual environment, make sure it's activated before installing.

Issue: Generating a large number of questions causes memory errors.

Solution: Generate questions in smaller batches:

# Instead of generating 50 questions at once
all_questions = []
for i in range(5):
    batch = client.qna_engine.generate_questions(
        topic="History",
        num=10
    )
    all_questions.extend(batch.questions)