Embeddings | Prediction Guard

Generate vector data points from text and images.

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

This endpoint expects an object.

modelstringRequired

The model to use for generating vectors.

inputstring or list of strings or integers or lists of integers or objectsRequired

truncatebooleanOptional

Boolean setting whether to truncate inputs. Not supported by bridgetower.

truncation_directionstringOptional

Which direction to truncate, "Left" or "Right". Not supported by bridgetower.

Successful response.

idstring

Unique ID for the embeddings.

objectstring

Type of object (list).

createdinteger

Timestamp of when the embeddings was created.

modelstring

The embeddings model used.

datalist of objects

The set of vectorized data.

400

Bad Request Error

403

Forbidden Error

$	curl -X POST https://{your-pg.api-domain}.com/embeddings \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "bge-m3",
>	"input": "A person is ironing something while standing on the back of a taxi.",
>	"truncate": true,
>	"truncation_direction": "Right"
>	}'

$	curl -X POST https://{your-pg.api-domain}.com/embeddings \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "bge-m3",
>	"input": "A person is ironing something while standing on the back of a taxi.",
>	"truncate": true,
>	"truncation_direction": "Right"
>	}'