The Ultimate Guide to High Availability with MariaDB

CREATE TABLE with vectors

You are viewing an old version of this article. View the current version here.

MariaDB has a dedicated data type VECTOR(N) with a built-in data validation. N is the number of dimensions that all vector values in the column will have. For example,

CREATE TABLE embeddings (
        doc_id BIGINT UNSIGNED PRIMARY KEY,
        embedding VECTOR(1536)
);

To have a fast vector search one needs to index the vector column, creating a VECTOR index:

CREATE TABLE embeddings (
        doc_id BIGINT UNSIGNED PRIMARY KEY,
        embedding VECTOR(1536) NOT NULL,
        VECTOR INDEX (embedding)
);

Note that there can be only one vector index in the table and the indexed vector column must be NOT NULL.

There are two options that can be used to configure the vector index.

  • M — Larger values mean slower SELECTs and INSERTs, larger index size and higher memory consumption but more accurate results.
  • DISTANCE — Distance function to build the vector index for. Searches using a different distance function will not be able to use a vector index. For example, 
CREATE TABLE embeddings (
        doc_id BIGINT UNSIGNED PRIMARY KEY,
        embedding VECTOR(1536) NOT NULL,
        VECTOR INDEX (embedding) M=8 DISTANCE=cosine
);

Comments

Comments loading...
Content reproduced on this site is the property of its respective owners, and this content is not reviewed in advance by MariaDB. The views, information and opinions expressed by this content do not necessarily represent those of MariaDB or any other party.