Create Embedding

Creates an embedding vector that can be easily consumed by machine learning models and algorithms.

POST /v1/embeddings

Request Body

Les paramètres suivants peuvent être inclus dans le corps de la requête :

Paramètres

model

string

Required

Default Value: alphaedge-large-3-2512

ID of the model to use.

input

string array<string>

Required

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

Successful Response

Les champs suivants sont retournés dans une réponse réussie :

Champs de réponse

object

string

Required

The object type, which is always "list".

data

array<Embedding>

Required

The list of embedding objects.

model

string

Required

The model used for the embedding.

usage

UsageInfo

Required

Usage statistics for the embedding request.

Examples

Exemples de code pour utiliser cet endpoint :

typescript

import { AlphaEdge } from '@alphaedge/alphaedge';

const alphaedge = new AlphaEdge({
  apiKey: process.env.ALPHAEDGE_API_KEY,
});

const embedding = await alphaedge.embeddings.create({
  model: 'alphaedge-large-3-2512',
  input: 'The food was delicious and the waiter...'
});

python

from alphaedge import AlphaEdge

alphaedge = AlphaEdge(api_key="your-api-key")

embedding = alphaedge.embeddings.create(
    model="alphaedge-large-3-2512",
    input="The food was delicious and the waiter..."
)

curl

curl https://api.alphaedge-ai.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ALPHAEDGE_API_KEY" \
  -d '{
    "model": "alphaedge-large-3-2512",
    "input": "The food was delicious and the waiter..."
  }'

Response

Exemple de réponse de l'API :

json

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.0023054255
      ],
      "index": 0
    }
  ],
  "model": "alphaedge-large-3-2512",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}