VaultExam AI: Mock Tests from Your Notes, Without Uploading Them Anywhere

Описание и применение

VaultExam AI позволяет создавать экзаменационные материалы из собственных заметок без загрузки в облако, используя локальные модели и хранение данных, обеспечивая конфиденциальность и экономию на токенах.

Задача

Coaching institutes, tutors, professors, and corporate trainers need to generate mock tests and question banks from proprietary notes without uploading them to cloud APIs, which would expose intellectual property and incur per-token costs.

Результат

VaultExam AI enables privacy‑first, local generation of exam papers from proprietary notes, eliminating cloud dependencies and token costs while providing page‑cited answers and printable PDFs.

Рабочий процесс

• Upload notes in any format; the file is chunked, embedded locally, and deleted from disk immediately.
• Ask questions of the document; answers are sourced only from the notes with page citations.
• Generate an exam by selecting institute name, exam type, difficulty, and number of question types.
• Create Set A/B/C by sampling different document parts and avoiding repeats.
• Validate generated content (question count, options, answer index) and retry on bad JSON.
• Print or save the exam as PDF directly from the browser.

Доказательства

VaultExam AI is a 100% local, privacy-first tool that turns a chapter (In any format) into a ready-to-print question paper + answer key and lets you ask questions of the same document with page-cited answers.

Источник

Upload Notes in any format. It is chunked and embedded locally, and the file is deleted from disk straight after ingestion.

Источник

Everything runs on the user's own machine. No cloud calls, no per-token fees.

Источник

Backend: Java 21, Spring Boot 4.1.1 and Spring AI 2.0.1

Источник

LLM: an open-weight model (qwen3.5:4b) served by local Ollama

Источник

Vector store: PostgreSQL with PGVector (pgvector/pgvector:pg16 via Docker Compose)

Источник

How the exam generator works: it retrieves a sample of chunks from the document, asks the model for MCQs, short answers and long answers in separate structured-output calls, then validates each result (question count, exactly four options, valid answer index) and retries if the local model returns bad JSON.

Источник