Actions Panel
Ticket sales end soon
Join us for a 1-hour hands-on workshop and learn how to build context-aware LLMs with Featureform's Virtual Featureform!
By Shabnam MokhtaraniFollow
Date and time
Tuesday, October 17 · 12 – 1pm PDT
Location
Online
About this event
- 1 hour
- Mobile eTicket
Feature stores can be instrumental in managing and serving features that feed into LLMs. By pulling real-time data from feature stores, RAG can provide LLMs with context-rich data, enhancing the model’s ability to generate better and informed responses.
In this 1-hour hands-on workshop, we’ll build a QA chatbot with Featureform and Weaviate. We’ll leverage Featureform to define and serve our vector embeddings and Weaviate’s Vector Database to store them
- Introduction to RAG: Understand how Retrieval Augmented Generation enhances LLMs by pulling real-time data.
- LLM Performance Enhancement: Dive into strategies like improving prompts with RAG and fine-tuning LLMs.
- LLM Workflow Components: Explore how Featureform’s virtual feature store plays a pivotal role in the LLM workflow.
- Building a Q&A Chatbot: A step-by-step guide, from registering sources, transforming transcripts, and embedding transformations, to feeding prompts into OpenAI’s Davinci.
There will also be time for Q&A!
Report this eventTicket sales end soon
