Embeddings

POST

Generate vector data points from text and images.

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

truncatebooleanOptionalDefaults to false

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.

idstringOptional

Unique ID for the embeddings.

objectstringOptional

Type of object (list).

createdintegerOptional

Timestamp of when the embeddings was created.

modelstringOptional

The embeddings model used.

datalist of objectsOptional

The set of vectorized data.

1	curl -X POST https://api.predictionguard.com/embeddings \
2	-H "Authorization: Bearer <token>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"model": "multilingual-e5-large-instruct",
6	"input": "A person is ironing something while standing on the back of a taxi.",
7	"truncate": true,
8	"truncation_direction": "Right"
9	}'

1	{
2	"id": "emb-5b310173-3cc9-4470-aa3b-7503aacb4f38",
3	"object": "list",
4	"created": 1729115349,
5	"model": "multilingual-e5-large-instruct",
6	"data": [
7	{
8	"index": 0,
9	"embedding": [
10	0.0150606595,
11	0.04376322
12	]
13	}
14	]
15	}