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.

Headers

X-RosetteAPI-KeystringRequired

Request

This endpoint expects an object.

contentstringOptional

optionsobjectOptional

Response

documentEmbeddinglist of doubles or null

document embeddings

tokenEmbeddingslist of doubles or null

per-token embeddings

tokenslist of strings or null

extracted tokens

1	curl -X POST https://analytics.babelstreet.com/rest/v1/semantics/vector \
2	-H "X-RosetteAPI-Key: <apiKey>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"content": "Cambridge, Massachusetts"
6	}'

1	{
2	"documentEmbedding": [
3	42
4	],
5	"tokenEmbeddings": [
6	42
7	],
8	"tokens": [
9	"foo"
10	]
11	}