izvorni znanstveni rad
Large Language Models (LLMs) are being employed in various domains to support different tasks. There are many challenges when working with LLMs, such as hallucination and domain knowledge gaps. Retrieval Augmented Generation (RAG) has emerged as one of the best paradigms for enabling LLMs to access domain-specific data and as a mechanism for mitigating hallucinations. In this paper, we are employing RAG and investigating how large language models use repositories of pre-existing knowledge
to enhance the quality and relevance of generated responses. The focus of the paper is the development of real-world RAG applications in the educational domain. The research aims to develop an AI-based chatbot for university students that could answer students` frequently asked questions. Such a chatbot solves several challenges faced by the faculty administration and guides the improvement of the student's study experience. In the implementation, a low-code approach of Flowise AI is used. As a result, the prototype is
developed. From the domain point of view, the prototype represents a step toward an AI-powered educational system that has the potential to further enhance the level of individualized educational support. From the technological point of view, such implementation emphasizes the benefits of LLM and RAGintegration and the advantages of generative artificial intelligence.
Generative artificial intelligence; large language models; retrieval augmented generation; AI chatbot; student support
Razvojem virtualizacijskih tehnologija raste kompleksnost IT sustava, dok korisnici istovremeno zahtijevaju brži pristup resursima, napredne integracije i jednostavnost korištenja. Jedno od ključnih rješenja za ove izazove primjena je…
Ovaj rad istražuje i uspoređuje mogućnosti prosljeđivanja grafičkih kartica na Hyper-V i KVM hipervizorima prema virtualnim strojevima, detaljno opisujući metode, postupke i razlike u arhitekturi koje utječu na…
The ever-growing usage and adaptation of HTTP/3 in web traffic leverages Quick UDP Internet Connections (QUIC) as a transport protocol. QUIC is widely recognized for reduced latency, enhanced…