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
  • Available Model Providers
  • Setting Up Environment Variables
  • Data Protection Considerations

Was this helpful?

  1. Data Copilot

Configuration Options

This page explains how to configure Mito Data Copilot to use your own AI API keys instead of the Mito server.

PreviousSmart DebuggingNextAI Data Usage FAQ

Last updated 21 days ago

Was this helpful?

By default, Mito uses our server to send AI requests to the model provider. If instead you want to use your own AI API keys, you can set the following configuration options.

Available Model Providers

Mito supports the following AI models through environment variables:

OpenAI

  • Set OPENAI_API_KEY to your OpenAI API key

  • When using OpenAI, Mito will automatically use gpt-4.1.

Claude (Anthropic)

  • Set CLAUDE_MODEL to (e.g., "claude-3-7-sonnet-latest").

  • Set CLAUDE_API_KEY to your Anthropic API key

Gemini (Google)

  • Set GEMINI_MODEL to (eg., "gemini-2.0-flash").

  • Set GEMINI_API_KEY to your Google API key

Ollama (Self-hosted)

  • Set OLLAMA_MODEL to specify the model

  • Set OLLAMA_BASE_URL to your Ollama server URL (e.g., "http://localhost:11434/v1")

Azure OpenAI

  • Set AZURE_OPENAI_API_KEY to your Azure OpenAI API key

  • Set AZURE_OPENAI_API_VERSION to specify the API version

  • Set AZURE_OPENAI_ENDPOINT to your Azure OpenAI endpoint URL

  • Set AZURE_OPENAI_MODEL to specify the deployed model name

Setting Up Environment Variables

Important: Environment variables must be set before launching JupyterLab, as they are read when the Mito server extension initializes during startup.

Method 1: System Environment Variables

Set environment variables at the system level before starting JupyterLab:

On Windows:

set GEMINI_API_KEY=your-api-key-here
set GEMINI_MODEL=gemini-2.0-flash

On macOS/Linux:

export GEMINI_API_KEY=your-api-key-here
export GEMINI_MODEL=gemini-2.0-flash

Method 2: .env File with jupyter_server_config.py

  1. Create a .env file in your Jupyter config directory:

GEMINI_API_KEY=your-api-key-here
GEMINI_MODEL=gemini-2.0-flash
  1. Create or modify your jupyter_server_config.py file to load these variables on startup:

import os
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv('/path/to/your/.env')

Method 3: Permanent Environment Variables

Add the environment variables to your shell's configuration file for permanent setup:

On Windows:

Add environment variables through System Properties > Environment Variables.

On macOS/Linux:

Add to your .bashrc, .zshrc, or equivalent:

export GEMINI_API_KEY=your-api-key-here
export GEMINI_MODEL=gemini-2.0-flash

Data Protection Considerations

Remember that when using external AI providers:

  • Private data in dataframe names, column headers, or the first five rows of data might be shared with the AI provider

  • To maximize data protection, Mito Enterprise users can connect to a self-hosted model

If you are a user, you can configure Mito to use a Azure OpenAI endpoint instead. If you have questions about Mito Enterprise, please contact .

specify the model
specify the model
Mito Enterprise
jake@sagacollab.com