Artwork

Content provided by Data Driven. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Data Driven or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.
Player FM - Aplicație Podcast
Treceți offline cu aplicația Player FM !

Arjun Patel on Vector Databases and the Future of Semantic Search

51:31
 
Distribuie
 

Manage episode 462329534 series 1450892
Content provided by Data Driven. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Data Driven or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.

Today, we delve into the intriguing world of vector databases, retrieval augmented generation, and a surprising twist—origami.

Our special guest, Arjun Patel, a developer advocate at Pinecone, will be walking us through his mission to make vector databases and semantic search more accessible. Alongside his impressive technical expertise, Arjun is also a self-taught origami artist with a background in statistics from the University of Chicago. Together with co-host Frank La Vigne, we explore Arjun’s unique journey from making speech coaching accessible with AI at Speeko to detecting AI-generated content at Appen.

In this episode, get ready to unravel the mysteries of natural language processing, understand the impact of the attention mechanism in transformers, and discover how AI can even assist in the art of paper folding. From discussing the nuances of RAG systems to sharing personal insights on learning and technology, we promise a session that’s both enlightening and entertaining. So sit back, relax, and get ready to fold your way into the fascinating layers of AI with Arjun Patel on Data Driven.

Show Notes

00:00 Arjun Patel: Bridging AI & Education

04:39 Traditional NLP and Geometric Models

08:40 Co-occurrence and Meaning in Text

13:14 Masked Language Modeling Success

16:50 Understanding Tokenization in AI Models

18:12 "Understanding Large Language Models"

22:43 Instruction-Following vs Few-Shot Learning

26:43 "Rel AI: Open Source Data Tool"

31:14 "Retrieval-Augmented Generation Explained"

33:58 "Pinecone: Efficient Vector Database"

37:31 "AI Found Me: Intern to Innovator"

41:10 "Impact of Code Generation Models"

45:25 Personalized Learning Path Technology

46:57 Mathematical Complexity in Origami Design

50:32 "Data, AI, and Origami Insights"

  continue reading

301 episoade

Artwork
iconDistribuie
 
Manage episode 462329534 series 1450892
Content provided by Data Driven. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Data Driven or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.

Today, we delve into the intriguing world of vector databases, retrieval augmented generation, and a surprising twist—origami.

Our special guest, Arjun Patel, a developer advocate at Pinecone, will be walking us through his mission to make vector databases and semantic search more accessible. Alongside his impressive technical expertise, Arjun is also a self-taught origami artist with a background in statistics from the University of Chicago. Together with co-host Frank La Vigne, we explore Arjun’s unique journey from making speech coaching accessible with AI at Speeko to detecting AI-generated content at Appen.

In this episode, get ready to unravel the mysteries of natural language processing, understand the impact of the attention mechanism in transformers, and discover how AI can even assist in the art of paper folding. From discussing the nuances of RAG systems to sharing personal insights on learning and technology, we promise a session that’s both enlightening and entertaining. So sit back, relax, and get ready to fold your way into the fascinating layers of AI with Arjun Patel on Data Driven.

Show Notes

00:00 Arjun Patel: Bridging AI & Education

04:39 Traditional NLP and Geometric Models

08:40 Co-occurrence and Meaning in Text

13:14 Masked Language Modeling Success

16:50 Understanding Tokenization in AI Models

18:12 "Understanding Large Language Models"

22:43 Instruction-Following vs Few-Shot Learning

26:43 "Rel AI: Open Source Data Tool"

31:14 "Retrieval-Augmented Generation Explained"

33:58 "Pinecone: Efficient Vector Database"

37:31 "AI Found Me: Intern to Innovator"

41:10 "Impact of Code Generation Models"

45:25 Personalized Learning Path Technology

46:57 Mathematical Complexity in Origami Design

50:32 "Data, AI, and Origami Insights"

  continue reading

301 episoade

Toate episoadele

×
 
Loading …

Bun venit la Player FM!

Player FM scanează web-ul pentru podcast-uri de înaltă calitate pentru a vă putea bucura acum. Este cea mai bună aplicație pentru podcast și funcționează pe Android, iPhone și pe web. Înscrieți-vă pentru a sincroniza abonamentele pe toate dispozitivele.

 

Ghid rapid de referință

Listen to this show while you explore
Play