Categories:

Vector similarity functions

VECTOR_INNER_PRODUCTΒΆ

Computes the inner product of two vectors.

The inner product (also known as the dot or scalar product) multiplies two vectors. The result represents the combined direction of the two vectors. Similar vectors result in larger inner products than dissimilar ones.

See also:

VECTOR_COSINE_SIMILARITY , VECTOR_L1_DISTANCE , VECTOR_L2_DISTANCE , Vector Embeddings

SyntaxΒΆ

VECTOR_INNER_PRODUCT( <vector>, <vector> )
Copy

ArgumentsΒΆ

vector

First VECTOR value.

vector

Second VECTOR value.

ReturnsΒΆ

Returns a VECTOR that is the inner product of the two vectors given as inputs.

Usage notesΒΆ

  • Due to computational optimizations in the vector comparison functions, floating-point errors might be slightly larger than usual (that is, about 1e-4).

ExamplesΒΆ

This example uses the VECTOR_INNER_PRODUCT function to determine which vectors in the table are closest to each other between columns a and b:

CREATE TABLE vectors (a VECTOR(FLOAT, 3), b VECTOR(FLOAT, 3));
INSERT INTO vectors SELECT [1.1,2.2,3]::VECTOR(FLOAT,3), [1,1,1]::VECTOR(FLOAT,3);
INSERT INTO vectors SELECT [1,2.2,3]::VECTOR(FLOAT,3), [4,6,8]::VECTOR(FLOAT,3);

-- Compute the pairwise inner product between columns a and b
SELECT VECTOR_INNER_PRODUCT(a, b) FROM vectors;
Copy
+------+
| 6.3  |
|------|
| 41.2 |
+------+
Language: English