DEV Community

Sonam
Sonam

Posted on

Build an AI Quiz Generator in Python

#python #ai #flask #learning

I put together a small Flask example that turns any article, blog post, documentation page, or training note into a multiple-choice quiz using Telnyx AI Inference.

Code:

https://github.com/team-telnyx/telnyx-code-examples/tree/main/quiz-generator-python

The idea is simple: send the source text to an LLM, ask for structured JSON, and return a quiz your app can render, store, or export.

What it generates

The app returns:

  • a quiz title
  • a short description
  • multiple-choice questions
  • A/B/C/D choices
  • one correct answer per question
  • explanations for the answer key

The main endpoint is:

POST /quiz/generate
Enter fullscreen mode Exit fullscreen mode

Example request:

curl -X POST http://localhost:5000/quiz/generate \
  -H "Content-Type: application/json" \
  -d '{
    "text": "The Telnyx Call Control API allows developers to programmatically control phone calls. You can answer, hangup, transfer, bridge, and record calls. The API is event-driven, meaning you receive webhooks when call events happen.",
    "num_questions": 5,
    "difficulty": "medium"
  }'
Enter fullscreen mode Exit fullscreen mode

Example response shape:

{
  "id": "quiz-1750280400",
  "title": "Telnyx Call Control API Fundamentals",
  "description": "Test your understanding of the Telnyx Call Control API.",
  "difficulty": "medium",
  "questions": [
    {
      "id": 1,
      "question": "What setup is required to receive event notifications?",
      "choices": {
        "A": "Assign a number to a Call Control Application",
        "B": "Enable SMS",
        "C": "Install a softphone",
        "D": "Register with SIP"
      },
      "correct_answer": "A",
      "explanation": "You need a phone number assigned to a Call Control Application with a webhook URL."
    }
  ]
}
Enter fullscreen mode Exit fullscreen mode

How it works

The app calls:

POST /v2/ai/chat/completions
Enter fullscreen mode Exit fullscreen mode

The default model is:

moonshotai/Kimi-K2.6
Enter fullscreen mode Exit fullscreen mode

In .env:

TELNYX_API_KEY=your_telnyx_api_key
AI_MODEL=moonshotai/Kimi-K2.6
HOST=127.0.0.1
Enter fullscreen mode Exit fullscreen mode

The prompt asks the model to return JSON only, with 4 choices per question and short explanations.

Routes included

The sample includes:

  • POST /quiz/generate
  • GET /quizzes
  • GET /quizzes/<id>
  • GET /quizzes/<id>/answers
  • GET /health

I like the separate answer-key route because it maps nicely to real learning apps. The student view and instructor view usually need different fields.

Production ideas

The example stores quizzes in memory so the core flow is easy to see.

For production, I would add:

  • persistent storage
  • authentication
  • review workflows
  • long-document chunking
  • exports to JSON, CSV, or LMS formats
  • support for true/false or short-answer questions
  • stronger JSON validation

This is a starter pattern, but it is a useful one: the LLM is not just returning prose. It is generating structured app data.

Resources:

Top comments (0)