This chapter explores the intricacies of vector search, emphasizing the calculation of distances between vectors using both exact and approximate nearest neighbor approaches. It highlights the innovative use of the Hierarchical Navigable Small Worlds Graph (HNSW) for optimizing searches within large databases like MongoDB, making vector search highly efficient. Additionally, the chapter discusses the growing significance of vector search in AI applications and the integration of traditional and modern search methods for improved performance.
MongoDB Atlas is a managed NoSQL database that uses JSON-like documents with optional schemas. The platform recently released new vector search capabilities to facilitate building AI capabilities.
Ben Flast is the Director of Product Management at MongoDB. He joins the show to talk about the company’s developments with vector search.
This episode is hosted by Lee Atchison. Lee Atchison is a software architect, author, and thought leader on cloud computing and application modernization. His best-selling book, Architecting for Scale (O’Reilly Media), is an essential resource for technical teams looking to maintain high availability and manage risk in their cloud environments.
The post MongoDB Vector Search with Ben Flast appeared first on Software Engineering Daily.