Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 28 for “"Vector Database"”.
-
Vectorising Tabular Data for RAG and Vector Database Validation - A study of tabular data retrieval and anomaly detection methods against poisoning attacks in RAG
… tabular data should be represented for vector retrieval. Secondly, how a validation layer can protect the vector database against data poisoning attacks. The two attacks tested are prompt injections and hate speech. Four table representation methods are evaluated on a corpus of 23,638 …
-
BugLLM: Explainable Bug Localization through LLMs
… OpenAI's Ada V2 model and indexed in a Milvus vector database for efficient querying. In the inference phase, a query is built from the bug report using an LLM to filter out non-technical details. This refined query is then used to search the vector database, retrieving semantically similar …
-
Transformer Neural Networks for Natural Language Processing
… files, to enable context-aware retrieval over a vector database. The system is evaluated on 45 queries comprising question answering, summarization, and CLI code generation, on the Arista EOS 4.17.0F guide used as a test corpus. Empirical performance shows retrieval drastically reduces …
-
A Hybrid SQL and Retrieval-Augmented Generation System for Natural Language Querying of Friction Stir Additive Manufacturing Research Data
… require either programming knowledge for database queries or time-consuming manual literature search. This thesis presents the design, implementation, and evaluation of the FSAM Research Assistant, a hybrid natural language query system that combines a structured SQL database of 57 …
-
Paieška papildyto generavimo metodo taikymo poveikis didžiųjų kalbos modelių generuojamų integracinių testų kokybei /
… context (baseline), semantic search in a vector database with a reranker (naive RAG), and structure‑driven retrieval from a code dependency graph (graph‑based RAG). Each condition was repeated five times with two models — Claude Sonnet 4.5 and DeepSeek V4 Pro. A total of 480 tests were …
-
AI-Powered Multimodal Tour Guide: Enhancing Cultural Tourism with Image Recognition, and Personalized Storytelling
… audio form. The system integrates a persistent vector database of monument images, OpenCLIP-based visual embeddings, and a large multimodal language model to identify visually similar landmarks and generate tailored narratives. Multiple guide personas (e.g., historian, epic storyteller, …
-
High-Performance Computing in Next-Generation Sequencing Read Alignment
… By encoding NGS sequences as learned latent vectors using machine learning models, we design advanced vector-database indexing techniques to efficiently identify alignment locations. An implementation of this new approach on CPUs has comparable accuracy and throughput to BWA-MEM2 for short …
-
Metodologia orientada a agentes de linguagem para assistência automotiva: integrando engenharia de Prompts em Chatbots avançados
… into coherent fragments, indexing them in a vector database, crafting prompts tailored to a Large Language Model, and conducting a comparative evaluation of six RAG variants (Conventional, with Gradient Descent, Multi-Query, Step-Back, Self-RAG, and Self-RAG with Gradient Descent). …
-
Deep Learning-driven Digital Forensics for Cyberattack Attribution in the Internet of Things
… data into embeddings and storing them in a Vector Database (VDB). These contributions significantly enhance IoT forensic investigations by improving cyberattack attribution, ensuring data privacy, and automating forensic reporting, thus advancing IoT security and resilience.
-
Knowledge-Informed Self-Reflective Automated Penetration Testing Based on LLMs
… learning. A comprehensive PT knowledge vector database (VDB) is built from public cybersecurity resources, including MITRE ATT&CK and the OWASP Testing Guide (OTG), forming a tree-structured repository of tactics, techniques, and abstract actions. Experiments were conducted on the Sau …
-
Exploring Code Version Migration Challenges Through the Lens of Neural Analysis
… generation (RAG)-based tool that utilizes a vector database of Stack Overflow Q\&A pairs to assist developers by providing context-aware solutions for migration-related questions. Our contributions in this thesis are three-folds. First, we propose a novel version-migration issue related …
-
Enhancing Reaction-based de novo Design using Machine Learning
… accessible structures. The reaction vector is an example of a representation that encodes topological changes occurring in reactions, which has been integrated within a structure generation algorithm to increase the chances of generating molecules that are synthesisable. The general …
-
Pretrained Transformers for Efficient and Robust Information Retrieval
… collection of documents is indexed into a vector database for nearest neighbor search. Given a query, the first-stage retriever selects the top-k similar documents from the vector database for the second-stage reranker to review. The following second-stage reranker is usually a …
-
Contextual Augmentation in Artificial Intelligence
… tables, are transformed into high-dimensional vectors via LLM-generated embeddings, then stored in a vector database. When a user submits a query, the LLM retrieves the most relevant documents from this vector store, enabling a deeper understanding of the query and improving response quality. A …
-
EFFICIENT DATA SEARCH SERVICES WITH EMBEDDING VECTORS ON CLOUD
… is captured by similarity among embedding vectors generated by machine learning models. The ubiquity of this workload gives rise to dedicated systems on public clouds, yet existing solutions have low resource efficiency, lack fine-grained scalability, and overlook security protection …
-
BLOSSOMSTTM HUB – AN ONLINE TOOL FOR DESIGNING STTM VECTORS AND VISUALIZING PHENOTYPIC CHANGES OF STTM TRANSGENIC LINES
… virus promoter called 35S in a DNA plasmid vector that can carry 35S promoter + STTM expression cassette into nuclei, and then insert it into a genome, where 35S can drive a STTM sequence to express and produce complementary sequences to target miRNA for silencing. Before the DesignSTTM …
-
Breaking the Token Barrier: Leveraging Retrieval Methods to Facilitate Text-to-SQL on Extensive Tabular Data
… LLM would generate the SQL code and query the database. But current text-to-SQL methods are naive, they assume the table’s schemas are small enough to fit inside the LLM’s token limit which is not always the case, especially for Zenseact’s table with 5677 columns. This thesis tackles the …
-
From Data to Descriptions: Efficient Data Retrieval in Autonomous Vehicle Development using Generative AI
… Current solutions mainly use SQL to query the database of logs, this solution does however require knowledge of both SQL and the specifics of the data that you are looking for. This thesis was carried out in collaboration with Zenseact, and aims to create an artifact called "Genius" to enable …
-
RAG aplikace nad spravovanou znalostní bází
Táto práca navrhuje a implementuje Retrieval-Augmented Generation(RAG, generovanie rozšírené o vyhľadávanie) aplikáciu, ktorá zlepšuje kvalitu a dôveryhodnosť odpovede veľkých jazykových modelov pomocou externej znalostnej bázy. Systém prijíma zdrojové dokumenty, extrahuje text a rozdeľuje ho do …
-
Fault And Cyberattack Diagnosis And Handling Via Large Language Models And State Prediction For Manufacturing And Quantum Systems
… LLM’s responses on proprietary data sourced from vectorized sources through a process called retrieval augmented generation (RAG). Through this process documents that are similar to the user’s query will be retrieved from a vector database to assist the LLM’s model in generating a response that …
Page 1 of 2