Stream, Process, Embed, Repeat
Are you passionate about the latest advancements in unstructured data and longing to dive into the world of LLMs? Look no further! We're thrilled to announce a dynamic meetup that's part of the Zilliz Unstructured Data and LLMs series, designed to ignite your curiosity and enhance your expertise.
Whether you're coding the future as a developer, unraveling data's deepest secrets as a scientist, fueling your passion for innovation, or captivated by the boundless horizons of AI and ML, this meetup is your gateway to an extraordinary confluence of minds and visionaries.
Who will bee 🐝 a star?
Oli Makhasoeva
Director of Developer Relations and OperationsStream, Process, Embed, Repeat!
One might think implementing a RAG app is time-consuming. Let's challenge that notion. In less than half an hour, we'll construct a real-time RAG pipeline end-to-end in Python. We'll read HackerNews posts in real time, transform and aggregate data, create embedding, and store them in a vector database. Along the way, we'll take advantage of the Python ecosystem's convenient tools, including unstructured, to extract and transform data coming from HackerNews API, Hugging Face models to create embeddings, and Bytewax to glue everything together into a real-time pipeline. Enjoy a little bit of theory and hands-on practice, resources and code samples to kickstart your own RAG projects!
What other tantalizing offerings are on our agenda?
5:00-5:30 Arrival
5:30-5:40 Introduction
5:40-6:10 Chunking + Embedding for RAG - Yujian Tang
6:15-6:45 Constructing a Multidimensional Vector Database of Images for Behavioral Science - Damon Abraham, PhD
6:50-7:20 Stream, Process, Embed, Repeat - Oli Makhasoeva
7:25-8:00: Networking
Oli Makhasoeva
Director of Developer Relations and Operations
Shout-out to the hosts!
Warm thanks to AICamp, Zilliz, and The Milvus Project for their exceptional effort in hosting this event.