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.
 
Keywords—knowledge management system, asynchronous programming, Large Language Model (LLM), text-to-speech, Hypertext Preprocessor (PHP) language


Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).