CreateAI Support Services
AI Upskilling Friday Office Hour (Virtual)
Join us every Friday from 12–1 PM (AZ time) on Zoom:
- Zoom link:
https://asu.zoom.us/j/87204740314
We encourage you to register (we coordinate attendance with the LX team):
Eventbrite: https://www.eventbrite.com/e/ai-upskilling-office-hours-tickets-1113129132199?aff=odcleoeventsincollection
You’re always welcome to join directly via Zoom as well. The Eventbrite page also includes additional AI learning opportunities you may be interested in.
We’ll have a dedicated breakout room for CreateAI users please, bring your questions, ideas, or projects!
CreateAI Beta Users Office Hour / Beta Testing Group.
Interested in becoming a CreateAI Beta user or interested in joining our Beta testing sessions? Let us know and we’d love to have you.
Personalized 1:1 Consultations
Need deeper support?
We offer tailored 1:1 consultations to help you get the most out of CreateAI.
Book a session to:
- Refine your AI use case
- Optimize your Knowledge Base
- Review governance or privacy questions
- Get hands-on support with your project
We look forward to connecting with you, virtually, in person, or one-on-one.
Keep Reading
How to Use Knowledge Base (RAG)
Jinjing Zhao
Explore an overview of the Knowledge Base and Retrieval Augmented Generation (RAG) methods. Learn about the different types of Knowledge Base retrieval and understand the distinctions between the Knowledge Base and system prompts.
CreateAI Platform Available LLM Models
Faith Timoh Abang
We are proud to offer 70+ models including multi-modal (voice, image, text) for the ASU community to access securely on the CreateAI Platform. Users can find the following models available for experimentation and use in CreateAI Compare, CreateAI Chat, and CreateAI Builder (access request required). Originally posted: January 1, 2025.
Breakdown of RAG Model Parameters, Settings and Their Impact
Kofi Wood
Retrieval-Augmented Generation (RAG) is an advanced approach in natural language processing that integrates information retrieval and generative language modeling. Unlike traditional language models that generate responses solely based on their pre-trained knowledge, RAG combines retrieval mechanisms with generative models to enhance the relevance and accuracy of its responses. This hybrid framework works by first retrieving relevant documents or information from a predefined knowledge base (e.g., databases, documents, or PDFs) and then using a generative model (such as a transformer-based model) to synthesize a response that incorporates the retrieved context.