The purpose of this paper is to explore the implementation of retrieval-augmented generation (RAG) technology with open-source large language models (LLMs). A dedicated web-based application, PaSSER, was developed, integrating RAG with Mistral:7b, Llama2:7b, and Orca2:7b models. Various software instruments were used in the application’s development. PaSSER employs a set of evaluation metrics, including METEOR, ROUGE, BLEU, perplexity, cosine similarity, Pearson correlation, and F1 score, to assess LLMs’ performance, particularly within the smart agriculture domain. The paper presents the results and analyses of two tests. One test assessed the performance of LLMs across different hardware configurations, while the other determined which model delivered the most accurate and contextually relevant responses within RAG. The paper discusses the integration of blockchain with LLMs to manage and store assessment results within a blockchain environment. The tests revealed that GPUs are essential for fast text generation, even for 7b models. Orca2:7b on Mac M1 was the fastest, and Mistral:7b had superior performance on the 446 question–answer dataset. The discussion is on technical and hardware considerations affecting LLMs’ performance. The conclusion outlines future developments in leveraging other LLMs, fine-tuning approaches, and further integration with blockchain and IPFS.

Each person’s unique traits hold valuable insights into their consumer behavior, allowing scholars and industry experts to develop innovative marketing strategies, personalized solutions, and enhanced user experiences. This study presents a conceptual framework that explores the connection between fundamental personality dimensions and users’ online shopping styles. By employing the TIPI test, a reliable and validated alternative to the Five-Factor model, individual consumer profiles are established. The results reveal a significant relationship between key personality traits and specific online shopping functionalities. To accurately forecast customers’ needs, expectations, and preferences on the Internet, we propose the implementation of two Machine Learning models, namely Decision Trees and Random Forest. According to the applied evaluation metrics, both models demonstrate fine predictions of consumer behavior based on their personality.

Blockchain oracles are an intermediary designed to connect external non-deterministic information and real-world data to the blockchain digital infrastructure. The variety of proposed solutions and purposes are of great variety and suggest that it is necessary to take into account different features of the process and specifically define the required functionalities. The purpose of this paper is to present the integration of oracles into an EOSIO blockchain-based platform for smart crop production data exchange by smart contracts. The functions of two oracles are presented. Their integration is described at the design level and at the implementation of the smart contracts. The design level is illustrated by workflow diagrams of internal processes between oracle applications and the blockchain smart contract and by external processes in the oracles’ smart contracts. The implementation level is illustrated by oracle application configuration files and elements of C++ smart contracts, such as constant and variable declarations, multi-index tables, internal contract functions, and actions called by other contracts and external programs. As results of the oracles’ operation, a report on the detected emergency failures and an estimate of the cost of ram resource are presented.

Training in STEM centers is becoming increasingly relevant in order to meet the new educational needs caused mainly by the rapid speed with which new technologies have been entering our lives in recent years. Existing university e-learning systems can enhance the capacity of these centers by providing shared learning material. This paper presents a distributed educational platform that supports sharable usage of teaching material at university and in STEM centers in secondary schools. The architecture of the platform is also presented including two basic components. The university e-learning environment operates as a back-end and the front-end component is located in the STEM center. Furthermore, the implemented prototype of the platform is also discussed in the article. The use of the platform is demonstrated by two educational games. The platform is expanded with four educational robots to increase the attractiveness of the educational process.