Chat

Chat is like collaborating with a colleague who sees your code, knows your data, and is a Python expert. Its ChatGPT integrated directly into Jupyter. It knows the current code cell you are editing and the column headers of your data, so it can generate code that runs in your analysis without copying and pasting or editing variable names.

How to use Chat?

1. Open the chat taskpane by clicking the icon in the toolbar on the left hand side of JupyterLab or by pressing cmd / ctrl + E.
2. Instruct the AI to write code for you. Talk to it like you would a colleague who is looking at your computer screen. Mito provides the AI with context about your code and currently defined variables. For example, if you want the AI to filter the column loan_amount in datframe loans_df, the instruction "Filter loan amount to greater than 100k" should get the job done."

3. Review the AI generated code. New code created by the AI is highlighted in green. Code deleted by the AI is highlighted in red. Review the code to make sure the AI has not made any unwanted changes and that you understand the new code.

4. Accept or Reject the AI generated code.

   1. Press cmd / ctrl + Y to accept the AI generated code and write it to the current active code cell

   2. Press cmd / ctrl + U to reject the AI generated code and return the code cell to its previous state.

Using Variable Mentions

To mention a specific variable in chat, enter the @ symbol.

You'll then see a list of variables. If you don't see the variable you're looking for, keep tying to filter.

Chat History

You can select an existing chat history, or start a new chat thread by using the icons in the Mito AI sidebar. Use new chat threads to work on isolated problems, or switch to an existing conversation to pick up where you left off.