VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

263-3857-00L 2 Credits MSC D-ITET , D-MATH , D-INFK

Vector Search in Databases for AI Seminar

Lecturers & Examiners: Prof. Dr. Yannis Chronis
The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.
VVZ CR n/a

Last Updated: 2026-06-01 11:30:53

Abstract

The seminar covers core concepts and state-of-the-art research of filtered vector search. Filtered vector search is the building block of database queries that combine vector search with relational query operators. Many databases are adding support for vector search driven by the demand of RAG and semantic search for access to the information that databases store.

Objective

Students will learn to: - Understand trends, opportunities, and requirements of integrating vector search in databases. - Analyze and critique state-of-the-art systems, techniques, and data structures for vector search presented in research papers. - Discuss and analyze the new capabilities enabled by querying structured and unstructured data via vector search. - Lead and participate in technical discussions about research papers

Content

Topics include definition of vector search, discussion of target use cases (RAG, Semantic Search, Recommendation systems), vector search index data structures, query optimization across relational operators and vector search, challenges to achieving high recall and high performance introduced by relational operators.

Resources

Literature

The research paper reading list will be posted on the course website and will include papers from conferences like VLDB, SIGMOD, CIDR, KDD, WWW, USENIX, NIPS.

General Information

Language
English
Levels
MSC

Examination

Type
graded semester performance
Students will present research papers, write reviews about research papers, and participate in discussions in class.

Registration & Places

Max Places
25
Priority: Registration for the course unit is only possible for the primary target group

Course Components

Type Title Time & Place Hours
seminar Vector Search in Databases for AI Seminar
  • Wed 14:15-16:00 (ML H 41.1)
2 h weekly

Offered In