Generate vector embeddings | Babel Street

Vector returns a single vector of floating point numbers for your input, representing the location of the input in semantic space. The length of the input can range from a single word to an entire document. Among other uses, a text vector enables you to calculate the similarity between two documents or two words.

Authentication

X-BabelStreetAPI-Keystring

API Key authentication via header

X-RosetteAPI-Keystring

API Key authentication via header

Request

This endpoint expects an object.

contentstringOptional

contentUristringOptional

optionsobjectOptional

Response

documentEmbeddinglist of doubles

document embeddings

tokenEmbeddingslist of doubles

per-token embeddings

tokenslist of strings

extracted tokens

$	curl -X POST https://analytics.babelstreet.com/rest/v1/semantics/vector \
>	-H "X-BabelStreetAPI-Key: <apiKey>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"contentUri": "https://en.wikipedia.org/wiki/Cambridge,_Massachusetts"
>	}'

1	{
2	"documentEmbedding": [
3	1.1
4	],
5	"tokenEmbeddings": [
6	1.1
7	],
8	"tokens": [
9	"string"
10	]
11	}

$	curl -X POST https://analytics.babelstreet.com/rest/v1/semantics/vector \
>	-H "X-BabelStreetAPI-Key: <apiKey>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"contentUri": "https://en.wikipedia.org/wiki/Cambridge,_Massachusetts"
>	}'

1	{
2	"documentEmbedding": [
3	1.1
4	],
5	"tokenEmbeddings": [
6	1.1
7	],
8	"tokens": [
9	"string"
10	]
11	}