We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.

From keyword to vector

Formal Metadata

From keyword to vector
Title of Series
Number of Parts
CC Attribution 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Release Date2023

Content Metadata

Subject Area
The future of search lies in machine learning-based approaches, a realization that has led me to the world of semantic search. As part of my current endeavors with Weaviate, I’ve come to understand the transformative potential of this advanced technology and how it’s reshaping our digital experiences. My journey into this field began during an internship in the early stages of my programming career. A group of my then colleagues ventured out to form a new company called Elasticsearch. Recognizing their potential, my mentor recommended that I focus my personal development on search technologies. This advice sparked my exploration of Lucene, Solr, and Elasticsearch, among others. In the subsequent years as a search consultant, I wrestled with the inherent challenges of keyword-based systems. The tasks were anything but straightforward, from managing semantics, synonyms, and typos to trying to decipher user intent. However, this endeavor was far from fruitless - it led to a deep understanding of the intricate workings of search technologies. This talk will take you through significant advancements in search over the years, peppered with practical insights and hard-earned wisdom I’ve accumulated along the way. The goal is not to argue that vector search replaces keyword search but to illustrate how combining both can yield the best results. Attendees can look forward to a nuanced understanding of search technologies, their evolution, and their potential to shape our future digital experiences.