This study presents the development of an Artificial Intelligence (AI)-based legal assistant using the Retrieval-Augmented Generation (RAG) architecture to provide legal assistance to citizens of the Republic of Kazakhstan. The proposed solution is designed to generate accurate, evidence-based responses to user queries using the regulatory legal acts of the Republic of Kazakhstan as the primary source of information. A legal corpus comprising 101,000 legislative documents and court decisions, with approximately 77 million tokens in Kazakh and Russian, was constructed to support the retrieval component of the system. To identify the most effective semantic retrieval method, three multilingual embedding models—Multilingual-E5-Large, BGE-M3, and KazEmbed-V5—were evaluated for vector search. The experimental results showed retrieval accuracies of 87.6%, 76.8%, and 83.3%, respectively. The GPT-5.4 and Llama-4-Scout-17B-16E-Instruct large language models were used to generate legal reasoning and responses based on documents retrieved through semantic search. The quality of the generated responses was evaluated using two complementary approaches. First, legal experts assessed the factual correctness and legal validity of the answers. Second, automatic evaluation was performed using word-level F1, BLEU, ROUGE, and BERTScore-F1 metrics. Among all evaluated configurations, GPT-5.4 combined with Multilingual-E5-Large achieved the highest overall accuracy (88.5%), whereas Llama-4-Scout-17B-16E-Instruct combined with KazEmbed-V5 achieved an accuracy of 83.6%. Based on the proposed architecture and the selected semantic retrieval and language models, an AI legal assistant was developed and integrated into the “Adal Azamat” legal services platform providing users in Kazakhstan with practical access to AI-assisted legal consultation.

This paper explores Named Entity Recognition (NER) in the Kazakh language using transformer-based models. NER is a subfield of Natural Language Processing (NLP) that involves the automatic identification of named entities in textual data and their classification into predefined categories. A review of previous studies indicates that further research is needed on this topic in Kazakh texts. Scientific works in the field of information technology were taken as textual data, and in the preparation of dataset, along with named entities, such as the names of people, names of institutions, places of location, terms in the field were marked up in IBO2 format. For the recognition of named entities, the transformer model of the spacy library and the large Llama language model were considered. To solve the task, the internal structural blocks of both models were fully described, a formal description of the implementation of the NER task was given and their fine-tuning was performed. The models were trained on a prepared dataset and various tests were performed. Obtained results are compared with the indicators of other studies and a comparative analysis is presented.