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.

The issues related to the analysis and management of Big Data, aspects of the security, stability and quality of the data, represent a new research, and engineering challenge. In the present paper, techniques for Big Data storage, search, analysis and management in the area of the virtual e-Learning space and the problems in front of them are considered. A numerical example for explorative analysis of data about the students from Burgas Free University is applied, using instrument for Data Mining of Orange. The analysis is a base for a system for localization of students at risk.

This paper presents the main issues on competencies and knowledge, risks and challenges in performing internal audit when adopting blockchains. The main purpose is to propose a framework for stages, procedures and elements for an internal audit plan in organizations that implement blockchains in smart crop production. It is analyzed basic elements of blockchain technology, characteristics and functions of internal audit and internal control, the impacts of blockchains implementation on organization and focus areas affecting human, financial and technical resources, risk identification, blockchain control procedures, risk management and mitigation. It is presented example of suggested framework for internal audit plan.

Increased consumer requirements for quality, safety and traceability of goods in supply chains has accelerated the implementation of blockchain during the COVID-19 pandemic. The right choice of blockchain software is a complicated task and an important prerequisite for successful deployment. In this study, we propose a conceptual framework for group multi-criteria selection of blockchain software in fuzzy environment according to organization needs and experts’ judgements. The applicability of the new framework has been verified through an illustrative example for ranking blockchain systems. The evaluations of compared alternatives were calculated by using measurement of alternatives and ranking according to the compromise solution (MARCOS) method. The robustness of the new framework was proven by sensitivity analysis in which two (crisp and fuzzy) MARCOS models with two different sets of weighting coefficients were compared.

The purpose of this paper is to propose an approach to blockchain-enabled supply-chain model for a smart crop production framework. The defined tasks are: (1) analysis of blockchain ecosystem as a network of stakeholders and as an infrastructure of technical and logical elements; (2) definition of a supply-chain model; (3) design of blockchain reference infrastructure; (4) description of blockchain information channels with smart contracts basic functionalities. The results presented include: а supply-chain model facilitating seeds certification process, monitoring and supervision of the grain process, provenance and as optional interactions with regulatory bodies, logistics and financial services; the three level blockchain reference infrastructure and a blockchain-enabled supply-chain supporting five information channels with nine participants and smart contracts. An account management user application tool, the general descriptions of smart contract basic functionalities and a selected parts of one smart contract code are provided as examples.