How to query code models

Reviewed on 09 December 2024 • Published on 09 December 2024

Scaleway’s Generative APIs service allows users to interact with powerful code models hosted on the platform.

Code models are inherently language models specialized in understanding code, generating code and fixing code.

As such, they will be available through the same interfaces as language models:

The Scaleway console provides complete playground, aiming to test models, adapt parameters, and observe how these changes affect the output in real-time.
Via the Chat API

For more information on how to query language models, read our dedicated documentation.

Code models are also ideal AI assistants when added to IDEs (integrated development environments).

Before you start

To complete the actions presented below, you must have:

A Scaleway account logged into the console
Owner status or IAM permissions allowing you to perform actions in the intended Organization
A valid API key for API authentication
An IDE such as Visual Studio Code or JetBrains

Install Continue in your IDE

Continue is an open-source code assistant to connect AI models to your IDE.

To get Continue, simply hit install in your IDE’s marketplace:

Configure Scaleway as an API provider in Continue

Continue’s config.json file will set models and providers allowed for chat, autocompletion etc. Here is an example configuration with Scaleway’s OpenAI-compatible provider:

"models": [
    {
      "model": "qwen2.5-coder-32b-instruct",
      "title": "Qwen2.5-coder",
      "apiBase": "https://api.scaleway.ai/v1/",
      "provider": "openai",
      "apiKey": "###SCW SECRET KEY###"
    }
]

Tip

The config.json file is typically stored as ~/.continue/config.json on Linux/macOS systems, and %USERPROFILE%\.continue\config.json on Windows.

Read more about how to set up your config.json on the official Continue documentation.