Jupyter AI is a set of extensions that provides agentic AI capabilities directly within JupyterLab. It integrates large language models (LLMs) and agents into notebooks and the JupyterLab interface, offering features like real-time chat, code generation, and AI-powered data analysis. The current version is 3.0.0, with an active development cadence releasing frequently, especially leading up to major versions.
pip install jupyter-aiVerified import paths — ran on the pinned version, not inferred.
To use Jupyter AI, ensure it's installed and your JupyterLab server is running. You primarily interact with Jupyter AI through its dedicated chat interface in the JupyterLab sidebar or directly within notebook cells using magic commands (e.g., `%%ai`). Most LLM providers require an API key, which should be set as an environment variable before launching JupyterLab or configured via JupyterLab's settings. The example demonstrates loading magic commands, listing models, and basic usage for code generation and agent interaction.
Review the official Jupyter AI v3.0.0 documentation and migration guides. Existing codebases or configurations relying on Langchain providers will need to be updated to use LiteLLM. Agent interactions will follow the new ACP model, which may require adjustments to prompts or expectations.
Reconfigure your LLM providers and models according to LiteLLM's conventions. Consult LiteLLM documentation for details on setting up credentials and models. Remove any explicit Langchain dependencies from your environment if they were only for Jupyter AI.
Be aware that agent actions might pause, awaiting your approval in the JupyterLab UI (often in the chat panel or a pop-up dialog). This is a security feature; monitor the agent's output and approve/deny actions as prompted.
If you need to monitor Dask activity for development or debugging, enable it by starting your Jupyter server with `--AiExtension.enable_dask_dashboard=True`. The dashboard will typically be available on port `8787`.