Episode 34 | Shane Connelly, Vectara Head of Product | Semantic Search and RAG With LLMs

Posted on Monday, Feb 26, 2024 | Category: Cloud Technology | Series: Exploring the Cloud | Cloud, Technology, Sales, Marketing, AI, LLM
Shane is a deep expert in the search and indexing space having started his career at Autonomy working on early search indexing algorithms and setting up solutions for customers before and after the HP acqusition, later leading Product for the Elasticsearch side of the Elastic product suite. Now he’s Head of Product at Vectara building out the next generation of semantic search and retrieval augmented generation platforms. In this episode we touch on benchmarks for gauging the relative performance of difference search algorithms and how it applies to LLMs for doing things like preventing hallucinations in generative AI, what kinds of questions Elasticsearch customers were asking that led Shane to believe that vector based algorithms were the future for doing next generation semantic search, and why he believes Vectara is building the top tier solution to solve these problems.

Show Notes

Episode #34 of “Can I get that software in blue?”, a podcast by and for people engaged in technology sales. If you are in the technology presales, solution architecture, sales, support or professional services career paths then this show is for you!

If you want to get into building AI products, first go to school and learn about antenna design! At least, that’s how our guest for episode 34, Shane Connelly did it.

Shane is a deep expert in the search and indexing space having started his career at Autonomy working on early search indexing algorithms and setting up solutions for customers before and after the HP acqusition, later leading Product for the Elasticsearch side of the Elastic product suite. Now he’s Head of Product at Vectara building out the next generation of semantic search and retrieval augmented generation platforms.

In this episode we touch on benchmarks for gauging the relative performance of difference search algorithms and how it applies to LLMs for doing things like preventing hallucinations in generative AI, what kinds of questions Elasticsearch customers were asking that led Shane to believe that vector based algorithms were the future for doing next generation semantic search, and why he believes Vectara is building the top tier solution to solve these problems.

Our website: https://softwareinblue.com

Twitter: https://twitter.com/softwareinblue

LinkedIn: https://www.linkedin.com/showcase/softwareinblue

Make sure to subscribe or follow us to get notified about our upcoming episodes:

Youtube: https://www.youtube.com/channel/UC8qfPUKO_rPmtvuB4nV87rg

Apple Podcasts: https://podcasts.apple.com/us/podcast/can-i-get-that-software-in-blue/id1561899125

Spotify: https://open.spotify.com/show/25r9ckggqIv6rGU8ca0WP2

Links mentioned in the episode:

History of Lucene: https://www.elastic.co/celebrating-lucene

Attention is all you need: https://arxiv.org/abs/1706.03762

Guests

Shane Connelly

Shane Connelly

Shane Connelly leads the Product team at Vectara (product management, product marketing, design, developer advocacy/relations, and technical writing). Prior to Vectara, heI led the product management team for Kong’s flagship API gateway. Prior to Kong, he led product for Elasticsearch at Elastic.