11-04, 13:45–14:15 (Asia/Jerusalem), Red Track
In this live coding session you'll learn how to integrate the data you care about into ChatGPT. As a result, you'll be able to ask ChatGPT questions and get answers based on your data!
You've all heard about ChatGPT, one of the most advanced language models out there 🤖. Unfortunately, because the model was trained using the data available at its training time, it may not be aware of the most recent developments 😢
Join us for a live coding session, where we'll utilize TechCrunch as a source for up-to-date information 🗞️. We'll scrape it and embed the articles into a high-dimensional vector space. Now, when a user asks a question, instead of solely relying on ChatGPT’s knowledge, we'll retrieve the most relevant item from the TechCrunch database (using vector similarity) and pass it to ChatGPT.
Finally, one of the most advanced language models will advance to November 2024! 💪🏻
Shiki is a seasoned Data Scientist with an emphasis on NLP, classical ML, visualization, and experimentation.
Driven by a great passion for the field, I am inspired by unintuitive insights and inferences made by smart algorithms. In my talks, I try to convey my typical spirit and enthusiasm while delivering crisp takeaways.
Over 14 years of experience as a software engineer and algorithm developer in various domains, including NLP, recommender systems, vision, and cybersecurity.
I am passionate about good quality code, interesting ideas and sophisticated algorithms. I love encountering elegant equations while trying to solve real-life problems.