Integration of web technologies in the management of AI agents for generation of synthetic datasets

Hadžić, Đulaga (author), Pašanbegović, Amer (author), Saletović, Enes (author)

Prispevek predstavlja inovativen pristop k samodejnemu generiranju sintetičnih naborov podatkovnih nizov parov vprašanj in odgovorov (QA) z uporabo večagentnega sistema, ki temelji na umetni inteligenci. Sistem integrira sodobne spletne tehnologije z naprednimi agenti umetne inteligence ter omogoča učinkovito pridobivanje, obdelavo in sintezo znanja iz spletnih virov. Implementacija uporablja zaledni sistem FastAPI z ogrodjem CrewAI za orkestracijo agentov, MongoDB in ChromaDB za shranjevanje podatkov ter sprednji sistem React za uporabniški vmesnik s komunikacijo v realnem času prek WebSocketa.

• Language: Slovenian
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication date: 01.01.2026
• Year: 2026
• Number of pages: Str. 110-124
• Numbering: Letn. 93, št. 3
• PID: 20.500.12556/RUL-189531
• UDC: 004.8:004.738.5.
• ISSN on article: 0013-5852
• COBISS.SI-ID: 294082051
• Publication date in RUL: 08.10.2026

Record is a part of a journal

• Title: Elektrotehniški vestnik
• Publisher: Strokovna zadruga koncesijoniranih elektrotehnikov, Elektrotehniška zveza Slovenije
• ISSN: 0013-5852
• COBISS.SI-ID: 742916

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: English
• Title: Integracija spletnih tehnologij v upravljanje agentov umetne inteligence za generiranje sintetičnih naborov podatkov

Abstract

The paper presents an innovative approach to automatic generation of synthetic question-answer (QA) pair datasets using a multi-agent system based on artificial intelligence. The system integrates modern web technologies with advanced AI agents to enable an efficient retrieval, processing, and synthesis of knowledge from web sources. The implementation utilizes a FastAPI backend with the CrewAI framework for agent orchestration, MongoDB and ChromaDB for the data storage, and a react frontend for the user interface with a real-time communication via WebSocket.

• Keywords: artificial intelligence, multi-agent systems, synthetic data generation, web scraping, natural language processing, CrewAI