> For the complete documentation index, see [llms.txt](https://mariadb.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://mariadb.com/docs/server/reference/sql-structure/vectors/create-table-with-vectors.md).
# CREATE TABLE with Vectors
WEBINAR
The Next Generation of MariaDB: Powered by Vector Search
{% hint style="info" %}
[Vectors](/docs/server/reference/sql-structure/vectors.md) are available from [MariaDB 11.7](/docs/release-notes/community-server/old-releases/11.7/what-is-mariadb-117.md).
{% endhint %}
MariaDB has a dedicated [VECTOR(N)](/docs/server/reference/sql-structure/vectors/vector.md) data type with a built-in data validation. `N` is the number of dimensions that all vector values in the column have.
{% hint style="info" %}
* Vector indexes are dimensionality-specific.
* All vectors inserted into an indexed column must match the index's target dimensionality.
* Inserting vectors with different dimensionalities will result in an error.
{% endhint %}
Consider the following table:
```sql
CREATE TABLE embeddings (
doc_id BIGINT UNSIGNED PRIMARY KEY,
embedding VECTOR(1536)
);
```
To have a fast vector search, you have to index the vector column, creating a `VECTOR` index:
```sql
CREATE TABLE embeddings (
doc_id BIGINT UNSIGNED PRIMARY KEY,
embedding VECTOR(1536) NOT NULL,
VECTOR INDEX (embedding)
);
```
{% hint style="warning" %}
Note that there can be only one vector index in the table, and the indexed vector column must be `NOT NULL`.
{% endhint %}
There are two options that can be used to configure the vector index:
* `M` — Larger values mean slower `SELECT` and `INSERT` statements, larger index size and higher memory consumption, but more accurate results. The valid range is from `3` to `200`.
* `DISTANCE` — Distance function to build the vector index for. Searches using a different distance function will not be able to use a vector index. Valid values are `cosine` and `euclidean` (the default).
```sql
CREATE TABLE embeddings (
doc_id BIGINT UNSIGNED PRIMARY KEY,
embedding VECTOR(1536) NOT NULL,
VECTOR INDEX (embedding) M=8 DISTANCE=cosine
);
```
{% hint style="info" %}
Declare `DISTANCE` explicitly. The default is `euclidean`, and a query using a different distance function than the one the index was built for cannot use the index, it falls back to a full table scan. Match the distance function to the metric your embedding model recommends.
{% endhint %}
*This page is licensed: CC BY-SA / Gnu FDL*
{% @marketo/form formId="4316" %}