Creates an embedding vector representing the input text or image.

post https://integrate.api.nvidia.com/v1/embeddings

Invokes inference using the embedding parameters. If uploading large images, this POST should be used in conjunction with the NVCF API which allows for the upload of large assets.
You can find details on how to use NVCF Asset APIs here: https://docs.api.nvidia.com/cloud-functions/reference/createasset.

Body Params

input

required

The list of images or texts that you want to generate embeddings for. Images should be in form of data:image/{format};base64,{base64encodedimage}. If the size of an image is more than 200KB, it needs to be uploaded to a presigned S3 bucket using NVCF Asset APIs. Once uploaded you can refer to it using the following format: <img src="data:image/png;asset_id,{asset_id}" />. Accepted formats are jpg, png and jpeg.

encoding_format

string

Defaults to float

The format to return the embeddings in. Can be either float or base64.

model

string

required

ID of the embedding model.

dimensions

int32

1 to 1

Not implemented, but provided for API compliance. This field is ignored.

user

string

length ≤ 204800

Not implemented, but provided for API compliance. This field is ignored.

Headers

NVCF-INPUT-ASSET-REFERENCES

uuid

length ≤ 370

String of asset IDs separated by commas. Data is uploaded to AWS S3 using NVCF Asset APIs and associated with these asset IDs.If the size of an image is more than 180KB, it needs to be uploaded to a presigned S3 URL bucket. The presigned URL allows for secure and temporary access to the S3 bucket for uploading the image. Once the asset is requested, an asset ID is generated for it. Please include this asset ID in this header and to use the uploaded image in a prompt, you need to refer to it using the following format: <img src="data:image/png;asset_id,{asset_id}" />.

Responses

Language

Credentials

Bearer


xxxxxxxxxx
10
1
curl --request POST \
2
     --url https://integrate.api.nvidia.com/v1/embeddings \
3
     --header 'accept: application/json' \
4
     --header 'content-type: application/json' \
5
     --data '
6
{
7
  "input": [
8
    "The quick brown fox jumped over the lazy dog",
9
    "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAAEElEQVR4nGK6HcwNCAAA//8DTgE8HuxwEQAAAABJRU5ErkJggg=="
10
  ],
11
  "encoding_format": "float",
12
  "model": "nvidia/nvclip",
13
  "dimensions": 0,
14
  "user": "user123"
15
}
16
'

Click Try It! to start a request and see the response here! Or choose an example:

application/json

200Invocation is fulfilled.

402Payment Required.

422Validation failed, provided entity could not be processed.

500The invocation ended with an error.