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/v2/embeddings

Try it

cURL

BasicEmbeddingExample

curl --request POST \
  --url https://paradigm.lighton.ai/api/v2/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "multilingual-e5-large",
  "input": "Hello, world!"
}
'

200

BasicEmbeddingExample

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

Authorizations

Authorization · string · header · required

Bearer token authentication

Body

Request serializer for embeddings endpoint.

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 · any · default: float

The format to return the embeddings in

• float - float
• base64 - 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

Successful response

Response serializer for embeddings endpoint results.

data · object[] · required

The list of embeddings generated by the model

Show child attributes

data. embedding · number<double>[] · required

The embedding vector, which is a list of floats

data. index · integer · required

The index of the embedding in the list of embeddings

data. object · string · default: embedding

The object type, which is always 'embedding'

model · string · required

The model used for generating the embeddings

object · string · default: list

The object type, which is always 'list'