Context Engineering with Hybrid Search, AI Features in Apache Doris 4.0

Two of the top-of-mind challenges when building AI applications today are handling the scale of the data involved and the accuracy of generated outputs. Context engineering, and more specifically, retrieval-augmented generation with vector search, is a method used to improve accuracy. However, as the amount of data and the number of vectors grow, the cost also rises. At the extreme end, there is constantly a trade-off between accuracy and cost. With Hybrid search, there's no trade-off. In this webinar, you will learn about the new hybrid search features released in Doris 4.0 and how a large tech giant used Apache Doris to gain superior accuracy while keeping costs in check.

Agenda

• A Quick Recap of What's New with Apache Doris 4.0
• VeloDB Cloud Doris 4.0 Tech Preview Announcement and How to Access
• Doris 4.0 Use Case example: Hybrid Search and Analytics Processing Use Case
• Q&A

Speaker

Kevin Shen

Principal Product Manager at VeloDB

Kevin is a principal product manager at VeloDB. Prior to VeloDB, Kevin led various data management products at IBM, such as watsonx.data and IBM Data Virtualization (Watson Query). Aside from working in data management, Kevin has also spent years as a technology consultant at Accenture, working closely with the U.S. federal customers on implementing solutions to reflect legislation.