Adding ML layer to Search: Hybrid Search Optimizer with Daniel Wrigley and Eric Pugh

About this episode

The episode discusses the evolution and current state of hybrid search, featuring insights from Daniel Wrigley and Eric Pugh.

Vector Podcast website: https://vectorpodcast.com Haystack US 2025: https://haystackconf.com/2025/ Federated search, Keyword & Neural Search, ML Optimisation, Pros and Cons of Hybrid search It is fascinating and funny how things develop, but also turn around. In 2022-23 everyone was buzzing about hybrid search. In 2024 the conversation shifted to RAG, RAG, RAG. And now we are in 2025 and back to hybrid search - on a different level: finally there are strides and contributions towards making hybrid search parameters learnt with ML. How cool is that? Design: Saurabh Rai, https://www.linkedin.com/in/srbhr/ The design of this episode is inspired by a scene in Blade Runner 2049. There's a clear path leading towards where people want to go to, yet they're searching for something. 00:00 Intro 00:54 Eric's intro and Daniel's background 02:50 Importance of Hybrid search: Daniel's take 07:26 Eric's take 10:57 Dmitry's take 11:41 Eric's predictions 13:47 Doug's blog on RRF is not enough 16:18 How to not fall short of the blind picking in RRF: score normalization, combinations and weights 25:03 The role of query understanding: feature groups 35:11 Lesson 1 from Daniel: Simple models…

People in this episode

Host: Dmitry Kan

Guests: Daniel Wrigley, Eric Pugh

Topics covered

• Hybrid Search
• Machine Learning
• Federated Search
• Neural Search
• RAG
• Query Understanding

Keywords

• Hybrid Search
• Machine Learning Optimization
• Federated Search
• Neural Search
• Query Understanding
• Learning To Rank

Mentioned in this episode

Organizations: Haystack US, OpenSearch

Books & works: Blade Runner 2049

More episodes of Vector Podcast

• AI Webinar - Building an AI-Ready Data Backbone · April 10, 2026 · 1h 18m
• Trey Grainger - Wormhole Vectors · November 7, 2025 · 1h 19m
• Economical way of serving vector search workloads with Simon Eskildsen, CEO Turbopuffer · September 19, 2025 · 1h 15m
• Vector Databases: The Rise, Fall and Future - by NotebookLM · March 2, 2025 · 20 min
• Code search, Copilot, LLM prompting with empathy and Artifacts with John Berryman · February 10, 2025 · 1h 7m
• Debunking myths of vector search and LLMs with Leo Boytsov · January 17, 2025 · 1h 8m