Mito
Mito for Streamlit
  • Mito Documentation
  • Getting Started
    • Installing Mito
      • Fixing Common Install Errors
      • Installing Mito in a Docker Container
      • Installing Mito for Streamlit
      • Installing Mito for Dash
      • Installing Mito in a Jupyter Notebook Directly
      • Installing Mito in Vertex AI
      • Setting Up a Virtual Environment
  • Data Copilot
    • Data Copilot Core Concepts
    • Agent
    • Chat
    • Autocomplete
    • Smart Debugging
    • Configuration Options
    • AI Data Usage FAQ
  • Mito Spreadsheet
    • Core Concepts
    • Creating a Mitosheet
      • Open Existing Virtual Environments
    • Importing Data
      • Importing CSV Files
      • Importing from Excel Files
      • Importing Dataframes
      • Importing from a remote drive
      • Import: Generated UI from any Python Function
      • Importing from other sources
    • Graphing
      • Graph Creation
      • Graph Styling
      • Graph Export
    • Pivoting/Group By
    • Filter
      • Filter By Condition
      • Filter By Value
    • Mito AI
    • Summary Statistics
    • Type Changes
    • Spreadsheet Formulas
      • Custom Spreadsheet Functions
      • Formula Reference
      • Using VLOOKUP
    • Editing Individual Cells
    • Combining Dataframes
      • Merge (horizontal)
      • Concatenate (horizontal)
      • Anti-merge (unique)
    • Sort Data
    • Split Text to Columns
    • Deleting Columns
    • Deleting Rows
    • Column Headers
      • Editing Column Headers
      • Promote Row to Header
    • Deduplicate
    • Fill NaN Values
    • Transpose
    • Reset Index
    • Unpivot a Dataframe (Melt)
    • Formatting
      • Column Formatting
      • Dataframe Colors
      • Conditional Formatting
    • Exporting Data
      • Download as CSV
      • Download as Excel
      • Generate code to create Excel and CSV reports
    • Using the Generated Code
      • Turn generated code into functions
    • Changing Imported Data
    • Code Snippets
    • Custom Editors: Autogenerate UI from Any Function
    • Find and Replace
    • Bulk column header edits
    • Code Options
    • Scheduling your Automation
    • Keyboard Shortcuts
    • Upgrading Mito
    • Enterprise Logging
  • Mito for Streamlit
    • Getting Started with Mito for Streamlit
    • Streamlit Overview
    • Create a Mito for Streamlit App
    • API Reference
      • Understanding import_folder
      • RunnableAnalysis class
      • Column Definitions
    • Streamlit App Gallery
    • Experienced Streamlit Users
    • Common Design Patterns
      • Deploying Mito for Streamlit in a Docker Image
      • Using Mito for Final Mile Data Cleaning
  • Mito for Dash
    • Getting Started
    • Dash Overview
    • Your First Dash App with Mito
    • Mito vs. Other Dash Components
    • API Reference
      • Understanding import_folder
    • Dash App Gallery
    • Common Design Patterns
      • Refresh Sheet Data Periodically
      • Change Sheet Data from a Select
      • Filter Other Elements to Data Selected in Mito
      • Graph New Data after Edits to Mito
      • Set Mito Spreadsheet Theme
  • Tutorials
    • Pass a dataframe into Mito
    • Create a line chart of time series data
    • Delete Columns with Missing Values
    • Split a column on delimiter
    • Rerun analysis on new data
    • Calculate the difference between rows
    • Calculate each cell's percent total of column
    • Import multiple tables from one Excel sheet
    • Share Mito Spreadsheets Across Users
  • Misc
    • Release Notes
      • April 15 - Now Streaming (0.1.18)
      • March 21 - Smarter, Faster, Stronger Agents
      • February 25 - Agent Mode QoL Improvements
      • February 18 - Mito Agents
      • January 2nd - Inline Completions Arrive
      • December 6th - Smarter Workflow
      • November 27th - @ Mentions, Mito AI Server
      • November 4th, 2024 - Hello Mito AI
      • October 8, 2024 - JupyterLab 4
      • Aug 29th, 2024
      • June 12, 2024
      • March 19, 2024
      • March 13th, 2024
      • February 12th, 2024: Graphing Improvements
      • January 25th, 2024
      • January 5th, 2023: Keyboard Shortcuts
      • December 6, 2023: New Context Menu
      • November 28, 2023: Mito's New Toolbar
      • November 7, 2023: Multiplayer Dash
      • October 23, 2023: RunnableAnalysis class
      • October 16, 2023: Mito for Dash, Custom Editors
      • September 29, 2023: VLOOKUP and Find and Replace!
      • September 7, 2023
      • August 2, 2023: Mito for Streamlit!
      • July 10, 2023
      • May 31, 2023: Mito AI Recon
      • May 19, 2023: Mito AI Chat!
      • April 27, 2023: Generate Functions, Performance improvements, bulk column header transformations
      • April 18, 2023: Cell Editor Improvements, BYO Large Language Model, and more
      • April 10, 2023: AI Access, Excel-like Cell Editor, Performance Improvements
      • April 5, 2023: Range formulas, Pandas 2.0, Snowflake Views
      • March 29, 2023: Excel Range Import Improvements
      • March 14, 2023: Mito AI, Public Interface Versioning
      • February 28, 2023: In-place Pivot Errors
      • February 7, 2023: Excel-like Formulas, Snowflake Import
      • January 23, 2023: Excel range importing
      • January 8, 2023: Custom Code snippets
      • December 26, 2022: Code snippets and bug fixes
      • December 12, 2022: Group Dates in Pivot Tables, Reduced Dependencies
      • November 15, 2022: Filter in Pivot
      • November 9, 2022: Import and Enterprise Config
      • October 31, 2022: Replay Analysis Improvements
      • Old Release Notes
      • August 10, 2023: Export Formatting to Excel
    • Mito Enterprise Features
    • FAQ
    • Terms of Service
    • Privacy Policy
  • Mito
Powered by GitBook

© Mito

On this page
  • What is Mito AI?
  • Using Mito AI
  • What tasks is Mito AI good for?
  • Auto Error Correction
  • Mito AI Plans

Was this helpful?

  1. Mito Spreadsheet

Mito AI

Mito AI is one of the fastest ways to transform your data. This documentation explains how.

What is Mito AI?

Mito AI is ChatGPT for your pandas dataframes. Its the easiest way to apply simple edits, like adding filters or parsing strings, to your data.

Like ChatGPT, Mito AI is a chat interface for interacting with OpenAI. Unlike ChatGPT:

  1. When you use Mito AI to transform your data, it automatically executes the code in the context of your analysis so you'll immediately see the effects on your data. This makes it easier to decide if the code generated by OpenAI was correct or whether you want to undo the edit and try again.

  2. Mito AI has context about your data and your analysis. This additional information, which Mito automatically provides to OpenAI without you having to type it out, helps OpenAI generate code that is useful to you right away.

Using Mito AI

  1. Open the AI taskpane by clicking the AI button in the toolbar.

  2. Describe the transformation that you want the AI to make, press Enter, and wait for the result.

  3. Use the results section within the chat, and the difference highlighting within the sheet to understand how the generated code effected your data.

    • Modified dataframes, columns and column headers are colored yellow.

    • Created dataframes and columns are colored green.

    • Deleted dataframes and columns are not colored, but are listed in the results section of the chat interface.

  4. If the results are incorrect, press the Undo button in the Mito toolbar and try updating your command.

  5. If the results are correct, give Mito AI another command.

And remeber, every edit you make in Mito (including through Mito AI) generates code in the code cell directly below the Mito spreadsheet. Scroll down to see your new Python code.

What tasks is Mito AI good for?

Mito AI excels at two types of tasks:

  1. Edits to dataframes. This includes adding columns, removing columns, filtering, aggregating, merging, and any other edits that manipulate the underlying data.

  2. Answering questions about the data. This includes questions like "how many unique values are in column X" or "what is the highest value after this aggregation."

Mito AI does not currently handle formatting changes to the sheet, and may not perform correctly when generating graph code.

Auto Error Correction

When the code generated by Mito AI errors, Mito feeds your original request, the code it generated, and the error back to OpenAI so that it can try again. Often this will resolve simple errors. Things like: columns having different dtypes than the generated code orginally assumed or the generated code relying on a package that was not yet imported in the notebook.

If the Mito AI is not able to automatically resolve the error, try breaking your request into small chunks. For example, if you initially asked Mito AI to Calculate the difference between the start and end times for each trip, you might instead first tell Mito AI to Convert the start and end time columns to datetimes, then Calculate the difference between the start and end time.

Mito AI Plans

Mito AI usage limits

Mito AI uses the ChatGPT API in order to turn your commands into Python code. To make interacting with ChatGPT a seamless experience for our users, we automatically use our own OpenAI API key. And as a result, Mito incures a charge for each user prompt. Therefore, the following applies:

  1. Open Source Mito AI users are allowed 100 free Open AI completions.

  2. All Mito users are able to provide their own OpenAI API key instead of using Mito's. This allows them to generate unlimited AI completions through the Mito interface.

Providing Your Own OpenAI Key

All Mito users are able to provide their own OpenAI API key instead of using Mito's. This allows them to generate unlimited AI completions through the Mito interface. Simply add the following code above where you create Mito spreadsheet:

import os
os.environ['OPENAI_API_KEY'] = '<Key Here>'

On-Prem AI

Configuring Mito to use a different LLM is as simple as setting a couple of environment variables.

PreviousFilter By ValueNextSummary Statistics

Last updated 1 year ago

Was this helpful?

Mito AI is currently in open beta. As such, Mito collects additional usage data: including dataframe names, column names, and some values in the dataframe. By using Mito AI, you are agreeing to our as well as OpenAI's .

Mito and users are allowed unlimited Open AI completions.

Some enterprises are uncomfortable sending any data to OpenAI and instead choose to build their own On-Prem AI. users are able to configure Mito to connect to On-Prem LLMs instead of OpenAI, giving them unlimited AI completions and complete control over their data.

privacy policy
privacy policy
Pro
Enterprise
Mito Enterprise
Conversationally using Mito AI to edit data.