Embeddings with /v1/embeddings

This page explains how to use the OpenAI-compatible /v1/embeddings route exposed by the Clovis gateway to generate vector representations (embeddings) from textual content.

Embeddings are used for use cases such as semantic search, similarity, clustering, and vector indexing for a RAG pipeline (retrieval).

Endpoint

Embeddings

POST/v1/embeddings

Full URL (Clovis Gateway)

Clovis Gateway

{
  POST https://llm-gateway.clovis-ai.fr/v1/embeddings
  Authorization: Bearer <CLOVIS_API_KEY>
  Content-Type: application/json
}

Structure

Each request must include a JSON similar to:

Request body

{
  "model": "ClovisEmbedding",
  "input": "Explain what an embedding is.",
  "encoding_format": "float"
}

Multiple input (batch)

{
  "model": "ClovisEmbeddings",
  "input": [
      "Document 1: text to vectorize",
      "Document 2: text to vectorize",
      "Document 3: text to vectorize"
  ],
  "encoding_format": "float"
}

Field description

Field	Type	Required	Description
model	string	✔️	Embedding model name
input	stringarray	✔️	Text (or list of texts) to convert into embeddings
encoding_format	string	✔️	Embedding output format (e.g. float, base64)
user	string		User identifier (useful for traceability / logs)

API Response

Main response object

Response example

{
  "object": "list",
  "data": [
      {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.9821, 0.4421, 0.1182]
      }
  ],
  "model": "ClovisEmbeddings",
  "usage": {
      "prompt_tokens": 12,
      "total_tokens": 12
  }
}

Details of the data field

Field	Type	Description
object	string	Returned object type ("embedding")
index	int	Index corresponding to the input provided in input
embedding	array	Numerical vector (dimension depends on the model)

Info

If input contains multiple texts, data will contain multiple embedding objects, each with a corresponding index.

Details of the usage field

Field	Type	Description
prompt_tokens	int	Number of tokens used for the input
total_tokens	int	Total billed (no generation, so no completion_tokens)

Usage examples

cURL

Request

curl https://llm-gateway.clovis-ai.fr/v1/embeddings -H "Content-Type: application/json" -H "Authorization: Bearer sk-xxxxxxxx" -d '{
  "model": "ClovisEmbeddings",
  "input": "RAG combines vector search and text generation.",
  "encoding_format": "float"
}'

Request

curl https://llm-gateway.clovis-ai.fr/v1/embeddings -H "Content-Type: application/json" -H "Authorization: Bearer sk-xxxxxxxx" -d '{
  "model": "ClovisEmbeddings",
  "input": [
    "Chunk 1: introduction...",
    "Chunk 2: details...",
    "Chunk 3: conclusion..."
  ],
  "encoding_format": "float"
}'

Javascript

require('dotenv').config();
const axios = require('axios');

async function testEmbeddings() {
  try {
    const payload = {
      model: ClovisEmbeddings,
      input: 'Basile',
      encoding_format: 'float'
    };
    const res = await axios.post('https://llm-gateway.clovis-ai.fr/v1/embeddings', payload, {
      headers: {
        Authorization: 'Bearer sk-xxxxxxxx',
        'Content-Type': 'application/json',
      },
    });

    return true;
  } catch (err) {
    console.error('/embeddings failed:', err.response?.status, err.message);
    return false;
  }
}
module.exports = testEmbeddings;