Women of Search present Building Recommendation Systems with Vector Search

Erika will give an update from the Women of Search group formed in Relevance Slack and will then deliver her talk: Bad search and recommendation is a major loss for e-commerce businesses. Haystack EU 2022 keynote speaker Dmitry Kan stated that “nearly $300 billion is lost each year from bad online search experiences.” With such a high impact, search and recommendation is an important area to focus on. To begin, we need to represent items and users. They are both typically represented as vectors and indexed for fast computation. Ref2Vec is a feature in Weaviate that converts users to vectors. Ref2Vec presents a graph-structured interface for connecting users and their online interactions to create a digital fingerprint. We can construct a bipartite graph between users and products and represent the user as the average representation of “liked” products. We then achieve recommendation by searching with the user vector as the query. Listeners will gain an understanding of how vector search impacts recommendation and learn how to build a recommendation system. Followed by Q&A on both the talk and the Women of Search initiative.

Erika Cardenas

Weaviate

Erika Cardenas is a developer advocate at Weaviate, the open-source vector database. She has two master's degrees in economics and data science from Florida Atlantic University. Erika was part of the NSF-NRT program, where she published a paper on predicting house prices using structured and unstructured text data. She has written several blog posts such as vector database versus vector library, hybrid search, and integrating LangChain and Weaviate for generative search applications.