NaviGator Chat Getting Started

Security, Privacy, Data Classification Usage Guidelines

UF provides this service to allow you to analyze your documents using different language models while keeping those documents secure within UF servers and contracted vendors.  At this time, UF does not permit the usage of restricted or sensitive data with this service. Users only have access to their own datasets and conversation history. When interacting with the language models hosted by vendors, your messages and subsets of your documents will be sent to a LLM instance provided by Microsoft or Google.  All data handled in this fashion is covered by our existing agreements with Microsoft and Google.  None of this data contributes to training the large language model. No data is retained after deletion.  If you have uploaded a file by accident, deleting the file or conversation will completely remove it from the system. 

*Accessing Navigator AI off-campus requires UF Gatorlink VPN Service.

 

Available Language Models 

Language Models and Hosting
UF HiPerGator Microsoft Azure Google Amazon Web Services
  • llama-3.1-8b-instruct
  • nim-llama-3.1-8b-instruct
  • llama-3.1-70b-instruct
  • llama3-8b-instruct
  • llama3-70b-instruct
  • mistral-7b-instruct
  • nim-mistral-7b-instruct
  • mixtral-8x7b-instruct
  • mistral-large
  • codestral-22b
  • gemma-1.1-7b-it
  • Stable Diffusion (image generator)
  • gpt-4o
  • gpt-4o-mini
  • gpt-4-turbo
  • gpt-3.5-turbo
  • DALL-E-3 (image generator)
  • gemini-1.5-flash
  • gemini-1.5-pro
  • gemini-1.0-pro
  • command-r-plus
  • command-r
  • claude-3.5-sonnet
  • claude-3-haiku
  • claude-3-sonnet
  • claude-3-opus

Language model preset parameters

Parameter 

Description 

Model 

Select the model like gpt-3.5-turbo that will be used for generating responses 

Custom Name 

Optionally provide a custom name for your preset. This is the name that will be shown in the UI when using it 

Custom Instructions 

Define instructions or guidelines that will be displayed before each prompt to guide the user in providing input 

Temperature 

Adjust this parameter to control the randomness of the model’s output. A higher value makes the output more random, while a lower value makes it more focused and deterministic 

Top P 

Control the nucleus sampling parameter to influence the diversity of generated text. Lower values make text more focused while higher values increase diversity 

Frequency Penalty 

Use this setting to penalize frequently occurring tokens and promote diversity in responses 

Presence Penalty 

Adjust this parameter to penalize new tokens that are introduced into responses, controlling repetition and promoting consistency 

Enable Image Generation in NaviGator Chat

  1. On the NaviGator toolbar, click “NaviGator AI” and select “Plugins”. 


    Select Plugins

  2. On the new menu item “None selected”, click “Plugin Store. 

    Plugin Store


  3. Within the Plugin store, click “Install” for DALL-E-3 and/or Stable Diffusion to install image generators.

    Install Dall-E


  4. After installation, select the image generator plug-in you wish to use from the Plugin store dropdown menu.

    Under the None selected menu, click on the option for DALL-E-3. Stable Diffusion is also an option.



    You can start generating images by typing your prompts! 

 

NaviGator Chat User Guide

Comprehensive user guide on features and usage for UF NaviGator Chat.

NaviGator Chat User Guide