Skip to main content

Overview

Navigator Toolkit provides a comprehensive suite of AI capabilities powered by state-of-the-art language models and AI services. The toolkit enables UF applications to leverage advanced AI features while maintaining security and control over data. The service is available to UF students, faculty, and staff.

Key Features​

  • Multi-Model Support: Access to leading AI models from:

    • Azure OpenAI (GPT-4 and newer variants)
    • Anthropic (Claude 3 family)
    • Google (Gemini 1.0/1.5 series)
    • Meta (Llama 3 series)
    • Mistral AI (Mixtral, Mistral variants)
    • BlackForest Labs custom models

  • Diverse Capabilities:

    • Text Generation and Chat
    • Embedding Generation
    • Image Generation
    • Speech-to-Text Conversion
    • Function Calling and API Integration

  • Developer Resources:

    • Comprehensive Documentation
    • Best Practices for Prompt Engineering
    • Integration Guides
    • Technical Support and Consultation

Usage​

To gain access, please login with your Gatorlink credentials here:

Cost​

Every UF student, faculty, and staff receives a $5 per month credit to generate personal API keys. That credit limit is reset at the begining of every month. The credit can be used against any of the locally deployed models that are available.

Additionally, researchers can be onboarded as teams with custom budgets to leverage cloud models. Researchers are encouraged to submit a request via the UFIT Help Desk Portal.

To create a new team, we require the following information:

  • UFIT Billing Number
  • UF Unit Name
  • UF Department Name
  • List of Gatorlink IDs that need access
  • Budget

To get a UFIT Billing number, please follow the procedures located in the UF Hosting Sign Up page.

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 permits the usage of restricted or sensitive data with models deployed on UF HiPerGator. The usage of restricted or sensitive data is not permitted with cloud models. Users only have access to their own datasets and conversation history. When interacting with models hosted by vendors, your messages and subsets of your documents will be sent to a LLM instance provided by Microsoft, Amazon, or Google.  All data handled in this fashion is covered by our existing agreements with Microsoft. Amazon, and Google.  None of this data contributes to training the large language model.