AI/ML/Vector DB

Performance optimization of LLM systems requires a thorough understanding of the full software stack. Somehow I couldn’t find a comprehensive article that covers the big picture yet, so instead of waiting for one, I decided to write this article. This article is not a comprehensive review or best practice guide, but rather a sharing of my overall perspective on the current LLM system landscape.

You might not know it yet, but vector embeddings are everywhere. They are the building blocks of many machine learning and deep learning algorithms used by applications ranging from search to AI assistants. If you’re considering building your own application in this space, you will likely run into vector embeddings at some point. In this post, we’ll try to get a basic intuition for what vector embeddings are and how they can be used.

Discover Vector Databases: How They Work, Examples, Use Cases, Pros & Cons, Selection and Implementation. They have combined capabilities of traditional databases and standalone vector indexes while specializing for vector embeddings.