🔢 Embed

Use the Embed endpoint to obtain a vector representation of a string (see embeddings).

Available at https://api.lighton.ai/muse/v1/embed.

💸️ Pricing

You will be billed for the total number of tokens sent in your request.

---

Example

cURL

curl -X 'POST' \
  'https://api.lighton.ai/muse/v1/embed' \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json' \
  -H 'X-API-KEY: YOUR_API_KEY' \
  -H 'X-Model: orion-fr' \
  -d '{"text": "Il était une fois en Laponie"}'

Python

from lightonmuse import Embed

embedder = Embed("orion-fr")
outputs, cost, request_id = embedder("Il était une fois en Laponie")

JavaScript

let { response, error } = client.query(ApiModel.OrionFr, Endpoint.Embed, {
    text: 'Il était une fois en Laponie',
});

Response (JSON)

{
    "request_id": "a0b4f1e0-e1a7-48b9-8204-6567efe3957d",
    "outputs": [
        [
            {
                "execution_metadata": {
                    "cost": {
                        "tokens_used": 8,
                        "tokens_input": 8,
                        "tokens_generated": 0,
                        "cost_type": "orion-fr@default",
                        "batch_size": 1
                    },
                    "finish_reason": "length"
                },
                "text": "Il était une fois en Laponie",
                "embedding": [
                    -0.28515625, -0.67724609375, -0.0014142990112304688,
                    //...
                    1.488525390625, 0.08782958984375
                ]
            }
        ]
    ],
    "costs": {
        "orion-fr@default": {
            "total_tokens_used": 8,
            "total_tokens_input": 8,
            "total_tokens_generated": 0,
            "batch_size": 1
        }
    }
}

Parameters

• text string/array[string] ⚠️ required

  The input(s) that will be represented.

Response (outputs)

An array of outputs shaped like your batch.

• execution_metadata ExecutionMetadata

  An Execution metadata structure.

• text string

  The text that was represented, from the provided text parameter.

• embedding array[float]

  Vector representation of the provided text. The size of the representation depends on the model used, see models for details.