Category AI

Semantic Models

The word semantic is rather heavily used (often incorrectly) when discussing data models. The word semantic itself is an adjective relating to meaning in language or logic. When we think about its use in data models, we think of the…

Embeddings = Lossy Compression

An embedding isn't meaning. It's a lossy compression with a similarity-preserving objective. Once you see it that way, every weird vector search behaviour makes sense.

Vector Databases

Not only does it sound cool, but a vector database is a specialized type of database designed to store, index, and search high-dimensional vectors. These are numerical representations of data such as text, images, audio, or video. In the AI…

Lance Tables

Now for something a bit different. In a world where data is no longer just rows in a database, the rise of vector databases and machine learning pipelines has pushed storage formats to evolve further. One of the most promising…

Model Context Protocol

Generative AI has opened up a whole new world of opportunity. It is now foundational for business strategy and adoption has found it’s way into many homes via Open AI and ChatGPT (other GPTs are available). Being able to ask…