Skip to content

Integrations to use with OVHcloud AI Endpoints

Getting started

OVHcloud AI Endpoints is a serverless platform provided by OVHcloud that offers easy access to a selection of world-renowned, pre-trained AI models.

The platform is designed to be simple, secure, and intuitive, with data privacy as a top priority. Indeed, we do not store user data, making it an ideal solution for developers who want to enhance their applications with AI capabilities while keeping data private and secure.

Healthcare data hosting compliance

Personal healthcare data is particularly sensitive — that's why AI Endpoints is HDS (Hébergeur de Données de Santé / Healthcare data hosting) compliant, as part of the OVHcloud Public Cloud offer. You can have more details on how to enable this feature to your project here.

With no extensive AI expertise required, AI Endpoints is an ideal choice for developers seeking a convenient and secure way to integrate AI into their applications.

Key Features

  • Serverless: No infrastructure to manage or GPUs to provision. Just call the API.
  • OpenAI Compatible: Seamlessly integrate with existing tools and SDKs by simply changing the base URL.
  • Privacy First: Your data is not used for model training and remains within OVHcloud's secure infrastructure.
  • Pay-as-you-go: You are billed based on usage (tokens or requests), ensuring cost efficiency.

Prerequisites

Before sending your first request, ensure you have:

  1. An OVHcloud account and a Public Cloud project.
  2. Generated an AI Endpoints API key

Manage your Access

You can create multiple keys to manage access for different applications or development environments directly from the OVHcloud control panel in the AI Endpoints page.

Integrations

  • Pydantic AI

    A Python agent framework designed to help you quickly, confidently, and painlessly build production grade applications and workflows with Generative AI

    Documentation

  • LlamaIndex

    A leading framework for building LLM-powered agents over your data with LLMs and workflows.

    LLM Embeddings

    Documentation

  • LiveKit

    An open source platform for developers building realtime media applications.

    LLM Audio transcription Speech-to-Text

    Documentation

Quickstart

OpenAI API compliant

OVHcloud AI Endpoints mimics the OpenAI API structure. This means you can use the standard Python or Node.js openai libraries, or standard tools like LangChain and LlamaIndex, just by overriding the base_url with https://oai.endpoints.kepler.ai.cloud.ovh.net/v1.

Using cURL

You can test the API directly from your terminal:

curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer $OVHCLOUD_API_KEY" \
     -d '{
        "model": "<model-id>",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Explain quantum computing in one sentence."}
        ],
        "max_tokens": 100
     }'