Skip to content
What’s Next in Building Better Generative AI Applications? episode artwork

Oct 12, 2023 11 min

What’s Next in Building Better Generative AI Applications?

from The New Stack Podcast Hosted by The New Stack, SingleStore, Madhukar Kumar, Heather Joslyn

Since the release of OpenAI's ChatGPT-3 in late 2022, various industries have been actively exploring its applications. Madhukar Kumar, CMO of SingleStore, discussed his experiments with large language models (LLMs) in this podcast episode with TNS host Heather Joslyn. He mentioned a specific LLM called Gorilla, which is trained on APIs and can generate APIs based on specific tasks. Kumar also talked about SingleStore Now, an AI conference, where they plan to teach attendees how to build generative AI applications from scratch, focusing on enterprise applications. Kumar highlighted a limitation with current LLMs - they are "frozen in time" and cannot provide real-time information. To address this, a method called "retrieval augmented generation" (RAG) has emerged. SingleStore is using RAG to keep LLMs updated. In this approach, a user query is first matched with up-to-date enterprise data to provide context, and then the LLM is tasked with generating answers based on this context. This method aims to prevent the generation of factually incorrect responses and relies on storing data as vectors for efficient real-time processing, which SingleStore enables. This strategy ensures that LLMs can provide current and contextually accurate information, making AI applications more reliable and responsive for enterprises. Learn more from The New Stack about LLMs and SingleStore: Top 5 Large Language Models and How to Use Them Effectively Using ChatGPT for Questions Specific to Your Company Data 6 Reasons Private LLMs Are Key for Enterprises

Episode details come from the podcast's RSS feed.

Embed this episode

Madhukar Kumar of SingleStore joins us to talk about how the data for large language models is "frozen in time" and need the context offered by retrieval augmented generation and vector databases to grow more useful.

Ready to play

What’s Next in Building Better Generative AI Applications?

0:00 11:49

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of The New Stack Podcast?

This episode is 11 minutes long.

When was this The New Stack Podcast episode published?

This episode was published on October 12, 2023.

Can I download this The New Stack Podcast episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.