My Friend Was Tired of AI Answers That Sounded Right. So I Built One That Checks Itself.
Описание и применение
ARIA – это система, позволяющая студенту по кибербезопасности получать ответы, основанные на его собственных учебных материалах, с помощью гибридного поиска и оценки контекста.
Задача
A cybersecurity student needed precise answers from his own study materials; generic AI responses often did not match the specific documents he was using.
Результат
ARIA provides a transparent, modular pipeline that retrieves and evaluates information from a user’s own cybersecurity resources, ensuring answers are grounded in the specific study materials and allowing for easy inspection and replacement of components.
Рабочий процесс
- 1. User uploads or links cybersecurity resources to ARIA’s knowledge base.
- 2. User asks a question about a topic.
- 3. ARIA performs hybrid retrieval using ChromaDB and BM25 to find relevant documents.
- 4. A Judge LLM evaluates the retrieved context and the generated answer.
- 5. If the answer or retrieval is unsatisfactory, ARIA’s self‑healing engine refines the retrieval and repeats the process.
- 6. Final answer is presented to the user.
- 7. User can inspect, replace, or update models and retrieval components as needed.
Доказательства
I built ARIA to make that process easier.
ARIA lets him add his own cybersecurity resources and ask questions based on those materials.
I use Llama 3.1 8B through Ollama for generation, with ChromaDB and BM25 for hybrid retrieval.
The system retrieves relevant cybersecurity knowledge, then uses a Judge LLM to evaluate the retrieved context and the generated answer.
If the retrieval or answer isn't good enough, ARIA's self‑healing engine can refine the retrieval and try again.
- Дата записи: 2026-10-04T23:25:47.407Z