Unlocking Vector Databases : Search and RAG with Vespa

2412-Vespa-VectorSearch

In this workshop, we will dive in Vector Databases using Vespa, an open-source search engine and vector/tensor DB used in various major projects such as Spotify or Vinted recommandation system. The objective is to give participants tools to work on various use-cases form E-commerce search to recommendations and RAG.

The workshop is made of 6 main chapters :

• Introduction: 10km view of the use-cases and anti-use-cases for Vespa and why. Lab will be centered around CRUD
• Lexical Search: query syntax, boolean clauses, ranking for product search
• Grouping: facets for data exploration on sales data and result diversification
• Tensors: use tensor math for recommendations and vector search on an E-commerce dataset
• Hybrid Search: generate embeddings on the fly; use RRF; implement RAG
• Performance and scaling: intro to how Vespa scales; typical performance bottlenecks

Each chapter is composed of :

•  a short introduction to the topic
• a lab that will be solved in small groups, working on a pre-defined dataset
• a debriefing with the large group
• short wrap-up

Warning : Even though online attendance is opened for this event, we highly encourage participants to attend on site to get the most out of this event (participants will form groups and work together during the workshop).