Create embeddings

This endpoint can be used to convert text chunks into embeddings.

It is a simple proxy forwarding your requests to the desired model.

Input Format:

• input: Text string to convert to embeddings
• encoding_format: Format for returned embeddings (float or base64)
• dimensions: Optional dimension specification for output embeddings

POST /api/v3/embeddings

Create embeddings

cURL

curl --request POST \
  --url https://paradigm.lighton.ai/api/v3/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "input": "<string>"
}
'

import requests

url = "https://paradigm.lighton.ai/api/v3/embeddings"

payload = {
    "model": "<string>",
    "input": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({model: '<string>', input: '<string>'})
};

fetch('https://paradigm.lighton.ai/api/v3/embeddings', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

200

{
  "model": "multilingual-e5-large",
  "input": "Hello, world!"
}

Authorizations

Authorization · string · header · required

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

Body

application/jsonapplication/x-www-form-urlencodedmultipart/form-data

Request serializer for embeddings endpoint (OpenAI-compatible).

model · string · required

Model to use for generating embeddings, must exist and be configured from the admin

input · string · required

Input text to embed, encoded as a string or array of tokens

encoding_format · enum<string> · default: float

The format to return the embeddings in

• float - float
• base64 - base64

Available options: float, base64

dimensions · integer

The number of dimensions the resulting output embeddings should have

user · string

A unique identifier representing your end-user

Response

200 - application/json

Response serializer for embeddings endpoint results.

data · object[] · required

The list of embeddings generated by the model

Show child attributes

model · string · required

The model used for generating the embeddings

object · string · default: list

The object type, which is always 'list'

usage · object

Usage statistics for the embeddings request

Show child attributes