Zilliz at HackNC 2023

Halloweekend HackNC was great this year! As an alum, it was super exciting to get back to HackNC for my third appearance. This year, I came to represent Zilliz, give a workshop, and give a keynote speech.
There were over 1,300 registrations (wow!), 650 hackers, 80-something projects, and ONE winner for the Best Use of Zilliz! Big congratulations to the team “wellSpent”.
The inspiration for 'wellSpent' stems from a simple question: "Where's my money going?" At its core, it showcases a dynamic pie chart, giving users a quick snapshot of their expenses. But that's just the start. The app lists all transactions, ensuring you never miss where that extra dollar went. With features like travel planner, student debt planner, and other expense planners, users can forecast, strategize, and optimize their financial futures.
When asked what they were proud of, the team said:
When asked to describe their project, the team said:
Big shout out to the University of North Carolina at Chapel Hill organizers for this amazing HackNC! I am so proud of you all, and always great to see excellence from fellow TarHeels. Looking forward to being back next year!
Start Free, Scale Easily
Try the fully-managed vector database built for your GenAI applications.
Try Zilliz Cloud for FreeKeep Reading

Build for the Boom: Why AI Agent Startups Should Build Scalable Infrastructure Early
Explore strategies for developing AI agents that can handle rapid growth. Don't let inadequate systems undermine your success during critical breakthrough moments.

Legal Document Analysis: Harnessing Zilliz Cloud's Semantic Search and RAG for Legal Insights
Zilliz Cloud transforms legal document analysis with AI-driven Semantic Search and Retrieval-Augmented Generation (RAG). By combining keyword and vector search, it enables faster, more accurate contract analysis, case law research, and regulatory tracking.

Matryoshka Representation Learning Explained: The Method Behind OpenAI’s Efficient Text Embeddings
Matryoshka Representation Learning (MRL) is a method for generating hierarchical, nested embeddings that capture information at multiple levels of abstraction.