Developers — Jupyter AI documentation (original) (raw)

This section describes the developer API in Jupyter AI that other Python packages can use to tailor Jupyter AI to their use-case. Here are some examples of what other packages can do with the developer API:

• Add custom AI personas to Jupyter AI
• Add custom model providers to Jupyter AI

The developer API allows other packages to modify both the frontend & the backend. The developer API has two parts: the Entry points API and theLumino plugin API (currently unused, but planned for v3).

• The Entry points API allows packages to add certain objects to Jupyter AI’s backend. This is available to any Python package.

• The Lumino plugin API allows packages to add to, modify, or even override parts of Jupyter AI’s frontend. This is only available to labextension packages.

• Entry points API

  • 'jupyter_ai.personas'
    * Summary
    * How-to: Define a custom AI persona
    * Defining how an AI persona processes messages
    * Using Jupyternaut’s configured chat model
    * Defining AI persona defaults
    * Reference implementation
  • 'jupyter_ai.model_providers'
    * Summary
    * How-to: Define a custom model provider
    * Adding custom API keys and fields
    * How-to: Define custom code completions
    * Using the full notebook content for completions
  • 'jupyter_ai.embeddings_model_providers'
    * Summary
    * How-to: Define a custom embedding model provider
  • Providing entry points