docarray.math.distance.paddle module

docarray.math.distance.paddle.cosine(x_mat, y_mat, eps=1e-07, device='cpu')

Cosine distance between each row in x_mat and each row in y_mat.

Parameters:

• x_mat – np.ndarray with ndim=2

• y_mat – np.ndarray with ndim=2

• eps – a small jitter to avoid divde by zero

• device – the computational device for embed_model, can be either cpu or cuda.

Returns:

np.ndarray with ndim=2

docarray.math.distance.paddle.sqeuclidean(x_mat, y_mat, device='cpu')

Squared euclidean distance between each row in x_mat and each row in y_mat.

Parameters:

• x_mat – paddle array with ndim=2

• y_mat – paddle array with ndim=2

• device – the computational device for embed_model, can be either cpu or cuda.

Returns:

np.ndarray with ndim=2

docarray.math.distance.paddle.euclidean(x_mat, y_mat, device='cpu')

Euclidean distance between each row in x_mat and each row in y_mat.

Parameters:

• x_mat – paddle array with ndim=2

• y_mat – paddle array with ndim=2

• device – the computational device for embed_model, can be either cpu or cuda.

Returns:

np.ndarray with ndim=2