OVHcloud AI Endpoints

OVHcloud AI Endpoints provide OpenAI-compatible embedding models. The service can be used for free with rate limits, or with an API key for higher limits.

OVHcloud is a global player and the leading European cloud provider operating over 450,000 servers within 40 data centers across 4 continents to reach 1.6 million customers in over 140 countries. Our product AI Endpoints offers access to various models with sovereignty, data privacy and GDPR compliance.

You can find the full list of models in the OVHcloud AI Endpoints catalog.

Installation

npm i llamaindex @llamaindex/ovhcloud

Authentication

OVHcloud AI Endpoints can be used in two ways:

Free tier (with rate limits): No API key required. You can omit the apiKey parameter or set it to an empty string.
With API key: For higher rate limits, generate an API key from the OVHcloud Manager → Public Cloud → AI & Machine Learning → AI Endpoints → API keys.

Basic Usage

import { Document, Settings, VectorStoreIndex } from "llamaindex";
import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";

// Update Embed Model (using free tier)
Settings.embedModel = new OVHcloudEmbedding();

// Or with API key from environment variable
import { config } from "dotenv";
config();
Settings.embedModel = new OVHcloudEmbedding({
  apiKey: process.env.OVHCLOUD_API_KEY || "",
});

const document = new Document({ text: essay, id_: "essay" });

const index = await VectorStoreIndex.fromDocuments([document]);

const queryEngine = index.asQueryEngine();

const query = "What is the meaning of life?";

const results = await queryEngine.query({
  query,
});

By default, OVHcloudEmbedding uses the BGE-M3 model. You can change the model by passing the model parameter to the constructor:

import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";

const model = "text-embedding-3-small";
Settings.embedModel = new OVHcloudEmbedding({
  model,
});

You can also set the maxRetries and timeout parameters when initializing OVHcloudEmbedding for better control over the request behavior:

import { Settings } from "llamaindex";
import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";

const model = "text-embedding-3-small";
const maxRetries = 5;
const timeout = 5000; // 5 seconds

Settings.embedModel = new OVHcloudEmbedding({
  model,
  maxRetries,
  timeout,
});

Standalone Usage

import { OVHcloudEmbedding } from "@llamaindex/ovhcloud";
import { config } from "dotenv";
// For standalone usage, you can optionally configure OVHCLOUD_API_KEY in .env file
config();

const main = async () => {
  const model = "BGE-M3";
  // Using without API key (free tier)
  const embeddings = new OVHcloudEmbedding({ model });
  const text = "What is the meaning of life?";
  const response = await embeddings.embed([text]);
  console.log(response);
};

main();

Base URL

The default base URL is https://oai.endpoints.kepler.ai.cloud.ovh.net/v1. You can override it if needed:

const embedding = new OVHcloudEmbedding({
  model: "BGE-M3",
  additionalSessionOptions: {
    baseURL: "https://custom.endpoint.com/v1",
  },
});

Resources

API Reference

OVHcloudEmbedding