incept-python-sdk 0.1.0

Python SDK for Incept Question Generation API

Incept Python SDK

A Python client library for the Incept Question Generation API.

Installation

pip install incept-python-sdk

Quick Start

from incept import InceptClient

# Initialize the client
client = InceptClient(api_key="your-api-key-here")

# Generate questions
response = client.generate_questions(
    grade=5,
    instructions="Generate questions about fractions",
    count=3,
    difficulty="medium"
)

print(f"Generated {len(response.data)} questions")
for question in response.data:
    print(f"Q: {question.question}")
    print(f"A: {question.answer}")

Configuration

Initialize Client

from incept import InceptClient

# Basic configuration
client = InceptClient(api_key="your-api-key")

# Custom endpoint and timeout
client = InceptClient(
    api_key="your-api-key",
    base_url="https://your-custom-endpoint.com",
    timeout=60  # seconds
)

API Methods

Generate Questions

Generate educational questions with comprehensive options:

response = client.generate_questions(
    grade=7,
    instructions="Create algebra problems",
    count=5,
    question_type="mcq",
    language="english",
    difficulty="medium",
    subject="mathematics",
    model="openai",
    translate=False,
    evaluate=True,
    skill={
        "id": "algebra_basics",
        "title": "Linear Equations",
        "unit_name": "Algebra",
        "lesson_title": "Solving Equations"
    },
    topic="Linear Equations",
    student_level="average"
)

# Access generated questions
for question in response.data:
    print(f"Question: {question.question}")
    print(f"Answer: {question.answer}")
    print(f"Difficulty: {question.difficulty}")
    if question.options:
        print(f"Options: {question.options}")
    if question.detailed_explanation:
        for step in question.detailed_explanation.steps:
            print(f"Step: {step.title} - {step.content}")

# Check evaluation results (if evaluate=True)
if response.evaluation:
    print(f"Overall Score: {response.evaluation.overall_score}")
    print(f"Recommendations: {response.evaluation.recommendations}")

Completions

Get text completions:

response = client.completions(
    messages=[
        {"role": "system", "content": "You are a helpful math tutor"},
        {"role": "user", "content": "Explain the Pythagorean theorem"}
    ],
    provider="openai",
    max_tokens=1000,
    language="english"
)

print(response.response)

Wolfram Alpha Integration

Solve math problems using Wolfram Alpha:

response = client.wolfram_solve(
    question_text="What is the derivative of x^2 + 3x + 2?",
    subject="calculus",
    app_id="your-wolfram-app-id"
)

print(f"Solution: {response.solution}")
if response.steps:
    for step in response.steps:
        print(f"Step: {step}")

Health Check

Check API status:

health = client.health_check()
print(f"Status: {health['status']}")

API Documentation

Get API documentation:

docs = client.get_api_documentation()
print(docs)

Request Parameters

GenerateQuestionsRequest

Parameter	Type	Default	Description
grade	int	required	Grade level (0-12)
instructions	str	required	Instructions for question generation
count	int	5	Number of questions (1-100)
question_type	str	"mcq"	Question type (currently only "mcq")
language	str	"english"	Content language
difficulty	str	"mixed"	Difficulty level: "easy", "medium", "hard", "expert", "mixed"
subject	str	None	Subject override
model	str	"openai"	AI model: "openai", "falcon"
translate	bool	False	Enable translation
evaluate	bool	False	Enable quality evaluation
skill	dict	None	Skill context information
topic	str	None	Topic specification
subtopic	str	None	Subtopic specification
unit	str	None	Unit specification
student_level	str	None	Student level: "struggling", "average", "advanced"
previous_mistakes	list	None	Previous student mistakes

Response Models

GeneratedQuestion

{
    "type": "mcq",
    "question": "What is 2 + 2?",
    "answer": "A",
    "difficulty": "easy",
    "explanation": "Addition of two numbers...",
    "options": ["4", "3", "5", "6"],
    "detailed_explanation": {
        "steps": [...],
        "personalized_academic_insights": [...]
    },
    "voiceover_script": {...},
    "image_url": "https://...",
    "di_formats_used": [...]
}

EvaluationInfo

{
    "overall_score": 0.85,
    "scores": {
        "clarity": 0.9,
        "difficulty": 0.8,
        "relevance": 0.9
    },
    "recommendations": [
        "Consider adding more visual aids",
        "Simplify the language for grade level"
    ],
    "report": "Overall excellent question quality..."
}

Error Handling

The SDK provides specific exception types for different error scenarios:

from incept import InceptClient
from incept.exceptions import (
    AuthenticationError,
    ValidationError,
    RateLimitError,
    ServerError,
    NetworkError,
    InceptAPIError
)

client = InceptClient(api_key="your-api-key")

try:
    response = client.generate_questions(
        grade=5,
        instructions="Generate questions about fractions",
        count=3
    )
except AuthenticationError:
    print("Invalid API key")
except ValidationError as e:
    print(f"Validation error: {e}")
except RateLimitError:
    print("Rate limit exceeded, please wait")
except ServerError as e:
    print(f"Server error: {e}")
except NetworkError as e:
    print(f"Network error: {e}")
except InceptAPIError as e:
    print(f"API error: {e}")

Development

Install from source

git clone https://github.com/incept/incept-python-sdk
cd incept-python-sdk
pip install -e .

Install development dependencies

pip install -e ".[dev]"

Run tests

pytest

Format code

black incept/

Lint code

flake8 incept/

License

MIT License

Support

For support, please contact [e-mail] or visit our documentation at https://docs.inceptapi.com.