Abstract

This paper introduces a sophisticated knowledge management system developed to address the growing demand for real-time information retrieval and interaction. The system architecture leverages a robust Hypertext Preprocessor (PHP) backend to integrate Google’s Gemini Application Programming Interface (API) for advanced Large Language Model (LLM) functionalities, such as complex querying and content summarization. A key innovation is the implementation of PHP Fibers to manage I/O-bound tasks asynchronously, effectively overcoming the limitations of conventional synchronous processing and preventing application bottlenecks. For data retrieval, the system utilizes SQLite’s FTS5 extension for high-speed, indexed full-text search across large local datasets. To enhance accessibility, the Web Speech API is incorporated for text-to-speech functionality. Quantitative performance evaluation reveals that this asynchronous architecture achieves an improvement of up to 87% terms of information retrieval speed and reduces the average response latency by 35% compared to synchronous counterparts. Furthermore, the text-to-speech feature not only promotes inclusivity for users with disabilities but also facilitates more efficient cognitive processing of large volumes of information. © 2026 by the authors.

Author keywords

asynchronous programming; Hypertext Preprocessor (PHP) language; knowledge management system; Large Language Model (LLM); text-to-speech

Pinyaphat Tasatanattakool, Taskeow Srisod, Prachyanun Nilsook, Panita Wannapiroon, and Jira Jitsupa, “Intelligent (LLM) Knowledge Management System with Asynchronous Technology and Text-to-Speech Using PHP Language,” Journal of Advances in Information Technology, Vol. 17, No. 2, pp. 340-351, 2026.
https://doi.org/10.12720/jait.17.2.340-351