Passer au contenu principal
POST
/
openai
/
embeddings
Creates an embedding vector representing the input text.
curl --request POST \
  --url https://api.acedata.cloud/openai/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": "<string>"
}
'
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.015271,
        0.001234
      ]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9
  },
  "created": 1714500000
}

Autorisations

​
Authorization
string
header
requis

API token from https://platform.acedata.cloud

En-têtes

​
accept
enum<string>

Specifies the format of the response from the server.

Options disponibles:
application/json

Corps

application/json
​
model
enum<string>
requis

ID of the embedding model to use (e.g., text-embedding-3-small, text-embedding-3-large).

Options disponibles:
text-embedding-3-small,
text-embedding-3-large,
text-embedding-ada-002
​
input
string
requis

Input to embed: a single string, an array of strings, or token arrays.

​
encoding_format
enum<string>
défaut:float

Format of the returned embeddings.

Options disponibles:
float,
base64
​
dimensions
integer

Optional output embedding size when supported by the model.

Plage requise: x >= 1

Réponse

Embeddings created successfully.

​
object
enum<string>
requis

Type of the returned object.

Options disponibles:
list
​
data
object[]
requis
​
model
string
requis

Model used to generate the embeddings.

​
usage
object
requis
​
created
integer
requis

Unix timestamp (seconds) when the embeddings were created.