Understanding Vector Dimensionality
Vector dimensionality is the number of numeric values in an embedding. A 384-dimensional embedding has 384 numbers, a…
Read moreTopic
Fundamentals
Core concepts every AI database practitioner needs.
What Is Similarity Search?
Similarity search is the process of finding data items that are closest in meaning, pattern, or behavior to…
Read more
How to Choose the Right Distance Metric for Vector Search
The right distance metric is usually the one your embedding model was trained or documented to use. If…
Read more
Dense vs Sparse Vectors: Definitions, Tradeoffs, and Hybrid Retrieval
Dense vectors and sparse vectors are two different ways to represent text, documents, queries, and other data for…
Read more
The Curse of Dimensionality in AI Databases
The curse of dimensionality describes what happens when data is represented with many features, dimensions, or embedding coordinates:…
Read more
Understanding High-Dimensional Space
High-dimensional space is the mathematical setting where AI systems place embeddings: long lists of numbers that represent text,…
Read more
Vector Search vs Keyword Search: Dense, Sparse, and Hybrid Retrieval Explained
Vector search and keyword search solve different retrieval problems. Vector search, also called dense retrieval, is useful when…
Read more
What Is Semantic Search?
Semantic search is a way to retrieve information by matching the meaning of a query, not just the…
Read more
How Embeddings Capture Meaning
Embeddings capture meaning by turning text, images, code, or other data into vectors: lists of numbers that place…
Read more
Vector Embeddings Explained
A vector embedding is a dense list of numbers that represents the meaning or useful features of data…
Read more