ipychat: The AI IPython

ipychat is an AI IPython REPL that lets you understand, debug, and write better code faster.

Features

• Context-Aware: Automatically uses relevant context from your IPython session
• Rich Output: Markdown-formatted responses with syntax highlighting
• Multiple AI Models: Supports GPT-4o, Claude 3.5 Sonnet, and Gemini. Local models coming soon.
• Interactive Configuration: Easy model switching and configuration through magic commands

Installation

You can install ipychat using pip:

$ pip install ipychat

Usage

You can start the REPL by running the ipychat command:

$ ipychat
Welcome to ipychat! Use %ask to chat with gpt-4o.
You can change models using %models.

In [1]:

Alternatively, you can load the ipychat extension in an IPython session:

In [1]: %load_ext ipychat

You can then start asking the model any question using the %ask magic.

In [1]: %ask what can I do with the cities dataframe

You can change the current model using the %models magic.

In [1]: %models

Configuration

Based on the model you want to use, either set OPENAI_API_KEY, or ANTHROPIC_API_KEY, or both environment variables. You can also run ipychat config to configure ipychat interactively.

Contributing

Contributions are welcome! Please feel free to submit a pull request.

Versioning

ipychat uses Semantic Versioning. For the available versions, see the tags on the GitHub repository.

License

This project is licensed under the Apache License, see the LICENSE file for details.