A more effective abstraction is conceptualizing vector embeddings not as independent tables or data types but as a specialized index on the embedded data. This is not to say that vector embeddings are literally indexes in the traditional sense, like those in PostgreSQL or MySQL, which retrieve entire data rows from indexed tables. Instead, vector embeddings function as an indexing mechanism that retrieves the most relevant parts of the data based on its embeddings.

Rather than indexes, we can call this new index-like abstraction a “vectorizer,” as it creates vectors from the underlying source data it is connected to (in other words, vectorizes them).

When we reconceptualize embeddings as derived data, the responsibility for generating and updating them as the underlying data changes should be handed over to the database management system.


Keyboard Shortcuts

Key Action
o Source
e Edit
i Insight
r Random
h Home
s or / Search
www.joshbeckman.org/notes/805256863