From the course: LLM Foundations: Vector Databases for Caching and Retrieval Augmented Generation (RAG)
Join today to access over 24,000 courses taught by industry experts.
Pros and cons of vector databases
From the course: LLM Foundations: Vector Databases for Caching and Retrieval Augmented Generation (RAG)
Pros and cons of vector databases
In this video, we will discuss some advantages and shortcomings of vector databases, especially the specialized offerings. Let's begin with the advantages. Vector databases support semantic search. They have built-in implementations of approximate nearest neighbor algorithms, as well as a few distance measures. They support bulk data loading, which helps quickly load up large chunks of data like documents. They have indexing for vectors. This helps create indexes on vector fields and helps in executing semantic searches with low latency. They do have efficient data retrieval methods, especially for the large vector stores. They can scale well and can support high data and query volumes. Clustering and fault tolerance capabilities are also available to help with scale and redundancy. They are built for critical production applications. What are some of the shortcomings? They have limited support for traditional querying. Popular RDBMSs support several capabilities like joints and…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.