SOFTWARE SYSTEM FOR SEMANTIC TEXT SEARCH USING VECTOR DATABASE TECHNOLOGY

Authors

  • Srđan Šuković Fakultet Tehnickih Nauka Autor

DOI:

https://doi.org/10.24867/28BE32Sukovic

Keywords:

Vector database, vector embedding, semantic search

Abstract

This paper proposes an alternative approach to text search using vector databases and pretrained artificial intelligence models. The paper deals with the process of creating a vector representation of textual data, indexing them into different vector databases and the procedure of searching for similarities with user queries.

References

1. S. J. Russel i P. Norvig, u Artificial intelligence: a modern approach, New Jersey, Pearson Education, 2010, pp. 1-29.
2. J. R, „kaggle.com,“ [Na mreži]. Available: https://www.kaggle.com/datasets/jrobischon/wikipedia-movie-plots.
3. pinecone.io, „https://www.pinecone.io/,“ pinecone.io. [Na mreži].
4. „weaviate.io,“ Weaviate, [Na mreži]. Available: https://weaviate.io/developers/weaviate. [Poslednji pristup 16 February 2024].
5. „qdrant.tech,“ Qdrant, [Na mreži]. Available: https://qdrant.tech/documentation/. [Poslednji pristup 16 February 2024].
6. T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue i A. Moi, „HuggingFace's Transformers: State-of-the-art Natural Language Processing,“ Hugging Face, Brooklyn, 2020.

Published

2024-09-06

Issue

Section

Electrotechnical and Computer Engineering