TSI logo 25 years
LV EN
Home > About Us > Structure and Government > Abstracts

DEGREE

PROGRAMME

FACULTY

YEAR

LANGUAGE

KEYWORDS

COMPARATIVE ANALYSIS OF LLM-BASED APPROACHES FOR SQL GENERATION

The rapid development of Large Language Models has unlocked opportunities for restructuring software development processes in general as well as in such cases as converting natural language into SQL queries. This study seeks to experimentally evaluate the effects of four LLM-based methods on the efficiency and quality of SQL generation. Evaluation is being held based on following metrics: Correctness, Completeness and Consistency. Studied LLM-based SQL generation methods include Specific LLMs tailored for SQL code generation like SQL Coder frameworks for generating SQL code (Vanna.ai, 2023; Llamaindex, 2023) and Multi agent collaborative networks for transforming language into SQL.The research utilizes a mix of literature review case studies and simulations. It offers a comprehensive review of the advancements in LLM-driven SQL generation encompassing concepts, technologies, methodologies, strengths, limitations, and ethical considerations.This research successfully bridges the gap between theoretical foundations and practical application of AI-augmented approaches while promoting the integration of LLM-based SQL generation, into automated software development processes.

Author: Maksim Ilin

Supervisor: Dmitry Pavlyuk

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Assessing the Viability of Natural Language Processing Applications within an Electronic Checklist
System for Freight Forwarders: Rule-based Information Extraction from Cargo Descriptions.

This study investigates the application of Natural Language Processing (NLP) within electronic checklist systems to enhance cargo description and securing practices for freight forwarders. The logistics industry faces significant challenges due to complex and varied legislation and the need for autonomous validation tools for cargo securing. This research aims to develop a rule-based Named Entity Recognition (NER) model to standardize and automate the extraction of entities from cargo descriptions. Key components of this study include the development of an entity extraction mechanism using regular expressions and standardized codes. The research demonstrates the potential of NLP solutions to generate precise, dynamic checklists from detailed cargo descriptions, ensuring that all pertinent tasks are covered. The developed NER model's effectiveness is evaluated through a series of experiments, showcasing high precision, recall, and F1 scores, thus highlighting its practical applicability in real-world logistics operations. The findings underscore the importance of standardizing cargo-related information to facilitate the broader adoption of automated NLP solutions in the logistics industry.

Author: Nikita Mickevičs

Supervisor: Dmitry Pavlyuk

Degree: Professional Bachelor

Year: 2024

Work Language: English

Enhancement Strategies for Retrieval-Augmented Generation Systems

This thesis systematically explores the enhancement of Retrieval-Augmented Generation (RAG) systems within Large Language Models, emphasizing optimization of retrieval parameters and generation accuracy. We investigate optimal configurations in RAG systems, including chunk size and overlap percentages, top-k selection, query transformations, different retrieval methods, different LLMs, namely GPT-3.5-Turbo and GPT-4, discovering that a chunk size of 500 tokens generally offers the best performance. Vector search using cosine similarity emerges as the most effective retrieval method, significantly enhancing both context precision and recall across various tasks and knowledge bases. Experimentation within the CRUD-RAG framework demonstrates its applicability in diverse tasks from content creation to knowledge refinement. Our findings indicate that enhancements in retrieval settings can markedly improve the performance of RAG systems, making them more efficient and adaptable for complex information synthesis and retrieval tasks. These results affirm the potential of systematic enhancements to improve AI-driven language models in practical applications, contributing significant insights and practical approaches to the evolving landscape of RAG system research.

Author: Sigita Lapiņa

Supervisor: Dmitry Pavlyuk

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Application of time series algorithms for container imbalance forecasting using event data.

The research aim is to evaluate a time series models application for container imbalance forecasting using container event data. Compare the model results and conclude the real-world application options and limitations. The research object is time series models of container imbalance forecasting and subject is performance of models for container imbalance forecasting based on event data.There are three chapters of the research. The first one is State of the Art on Empty Container Repositioning (ECR) forecasting methods and approaches. The second part is investigation of container imbalance forecasting opportunities using event data. The third part is an application of time-series methods for forecasting container imbalance, experiments with real data and attempts to develop a novel data-driven framework for event data trained time series model evaluation. The third part consists of training experiment results analysis and interpretation. The 8 different models of ARIMA, VAR, VECM algorithms were tested and evaluated by different container size and type combinations, as well of 6 different port locations. Finally, the research conclusions are followed by references and attachments.

Author: Vjačeslavs Matvejevs

Supervisor: Dmitry Pavlyuk

Degree: Master

Year: 2024

Work Language: English

Study programme: Computer Sciences

More...

Table View
Text View