Skip to contents

Create matrix of embedding similarities

get_similarity_matrix.Rd

Create a matrix of pairwise similarities between each string in strings_A and strings_B.

Usage

get_similarity_matrix(embeddings, strings_A = NULL, strings_B = NULL)

Arguments

embeddings

A matrix of text embeddings

strings_A

A string vector

strings_B

A string vector

Value

A matrix of cosine similarities between the embeddings of strings_A and the embeddings of strings_B

Examples

embeddings <- get_embeddings(c('UPS', 'USPS', 'Postal Service'))
get_similarity_matrix(embeddings)
#>                      UPS      USPS Postal Service
#> UPS            1.0000002 0.7530467      0.6254707
#> USPS           0.7530467 1.0000000      0.8408279
#> Postal Service 0.6254707 0.8408279      1.0000000
get_similarity_matrix(embeddings, 'Postal Service')
#>                      UPS      USPS Postal Service
#> Postal Service 0.6254707 0.8408279              1
get_similarity_matrix(embeddings, 'Postal Service', c('UPS', 'USPS'))
#>                      UPS      USPS
#> Postal Service 0.6254707 0.8408279