Custom ChatGPT for your real-time data

Presented by: Bobur Umurzokov

In our modern world where speedy access to the right information matters, going through enormous amounts of records such as legal papers, academic studies, news, and technical guides can be automated using AI. However, an AI chatbot like ChatGPT can not answer questions about unfamiliar topics after 2021, recent events, or non-public documents. This task gets even more complicated when you deal with data that constantly changes. What should you do?

This presentation showcases a solution to these hurdles. You will learn how to build your AI app and how language models such as those provided by OpenAI ChatGPT and Pathway Python libraries can query real-time data intelligently without vector databases. This method opens up the potential to build solid systems for retrieving information, recommending content, or even making chatbots that answer user questions based on ever-changing streaming data.

Tags: Python, Backend, Data ScienceLevel: Introductory and overview