Debunking myths of vector search and LLMs with Leo Boytsov

Debunking myths of vector search and LLMs with Leo Boytsov

From Vector Podcast by Dmitry Kan

January 17, 2025 · 1h 8m · Season 3 · Episode 8

About this episode

In this episode, Leo Boytsov discusses various aspects of vector search and LLMs, including the technologies behind them and their implications in the industry.

00:00 Intro 01:31 Leo's story 09:59 SPLADE: single model to solve both dense and sparse? 21:06 DeepImpact 29:58 NMSLIB: what are non-metric spaces 34:21 How HNSW and NMSLIB joined forces 41:11 Why FAISS did not choose NMSLIB's algorithm 43:36 Serendipity of discovery and the creation of industries 47:06 Vector Search: intellectually rewarding, professionally undervalued 52:37 Why RDBMS Still Struggles with Scalable Vector and Free-Text Search 1:00:16 Leo's recent favorite papers Leo Boytsov on LinkedIn: https://www.linkedin.com/in/leonidboytsov/ and X: https://x.com/srchvrs Leo Boytsov’s paper list: https://scholar.google.com/citations?hl=en&user=I79y2i4AAAAJ&view_op=list_works&sortby=pubdate Lots of papers and other material from Leo: https://www.youtube.com/watch?v=gzWErcOXIKk

People in this episode

Host: Dmitry Kan

Guest: Leo Boytsov

Topics covered

  • vector search
  • LLMs
  • machine learning
  • NMSLIB
  • FAISS
  • SPLADE
  • deep learning

Keywords

  • vector search
  • LLMs
  • NMSLIB
  • FAISS
  • SPLADE
  • machine learning
  • deep learning
  • algorithm
  • discovery
  • search technology

Mentioned in this episode

Organizations: NMSLIB, FAISS, SPLADE, DeepImpact

Books & works: Leo Boytsov’s paper list, Serendipity of discovery and the creation of industries

More episodes of Vector Podcast

Explore listener stats, chart rankings, contacts and more on the Vector Podcast podcast page.