At GenAI @ UCLA, we are all about making generative AI products that are:

Useful:

Identify and solve real-life problems on the UCLA campus using state-of-the-art generative AI technologies.

Vertical:

Maximize AI potential with untrained, internal data in specialized areas and organizations.

Autonomous:

Enhance organizational efficiency and individual productivity through practical AI-driven solutions.

What to Expect in Fall 2024

We will be diving into RAG, Vector Databases/Embeddings, Agents, and more. These techniques have already been used in many enterprises and organizations.

Here is a quick summary of these terms:

  1. Retrieval-Augmented Generation (RAG) extends the capabilities of LLMs to an organization's internal knowledge base without retraining the model. It references an authoritative knowledge base outside of LLM’s training data sources before generating a response, avoiding hallucinations.
  2. Vector database is a specialized database designed to store and retrieve high-dimensional vectors, which are numerical representations of data encoded by embedding models. By leveraging vector similarity searches, RAG systems can retrieve more contextually relevant information.
  3. AI agents are software programs designed to interact with their environment, collect data, and autonomously perform tasks to achieve predetermined goals. They can improve productivity by automating tasks.

Join GenAI @ UCLA for an exciting dive into the world of generative AI! We focus on developing vertical, autonomous agent-based software to tackle real-world challenges on campus. We're inviting developers and product managers passionate about creating AI products to our first speaker event.

Event Highlights:

Overview: Speaker Series | Language Model Basics