OwlChat Toolkit provides every UF student, faculty, and staff the capability to generate API keys and leverage AI models in their current applications. Each FAU user has access to locally deployed models such as Llama, Mixtral, Gemma, Codestral, Stable Diffusion, and Mistral. Additionally, researchers can be onboarded as teams with custom budgets to leverage cloud models.
OwlChat Toolkit (LiteLLM) is an AI routing tool that allows users to aggregate and select the best language models for their needs. It provides a unified interface to access multiple language models, including those from OpenAI, Microsoft, and other providers. This tool is particularly useful for organizations that want to optimize their AI model usage by combining different models to achieve the best results. It also helps in tracking usage and setting budgets for different projects, ensuring cost efficiency.
OwlChat Toolkit simplifies the process of accessing and managing multiple language models. It offers two main components: the OwlChat Toolkit is a Proxy Server that acts as a central service to call over 100 language models, load balance, and track costs across projects. This is ideal for teams that need a centralized solution for managing AI models.
- To gain access to OwlChatApi submit a ticket to [ ticket ] requesting access. An invite will be sent once the request is approved.
- Once access has been granted follow the provided Invite link to create and activate your account.
- Once your account is activated visit https://chat-llm.hpc.fau.edu to review the Swagger docs, and login to the Admin Panel.
The admin panel provides several functions.
Virtual Key Management:
Where users can create API keys to access LLM's they are authorized to access.
Test Key:
Where users can test out an LLM Model they are authorized to use. 
Usage:
Where you can monitor you usage and costs.
Teams:
Where you may check the status of your different teams, budget, members, and settings.
Model Hub:
A list of models you are authorized for including the model's cost etc...
