Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Hørup Eskildsen of Turbopuffer
Latent Space: The AI Engineer Podcast
- Published
- March 12, 2026
- Duration
- 1h 0m
- Summary source
- description
- Last updated
- Jul 5, 2026
Discusses rag, vector-search.
Summary
Turbopuffer came out of a reading app.In 2022, Simon was helping his friends at Readwise scale their infra for a highly requested feature: article recommendations and semantic search. Readwise was paying ~$5k/month for their relational database and vector search would cost ~$20k/month making the feature too expensive to ship. In 2023 after mulling over th…
Intelligent Report
Sign in to read teasers, or upgrade to Research Pro to commission intelligent report for this episode. Learn more →
Show notes
Turbopuffer came out of a reading app.In 2022, Simon was helping his friends at Readwise scale their infra for a highly requested feature: article recommendations and semantic search. Readwise was paying ~$5k/month for their relational database and vector search would cost ~$20k/month making the feature too expensive to ship. In 2023 after mulling over the problem from Readwise, Simon decided he wanted to “build a search engine” which became Turbopuffer.We discuss:• Simon’s path: Denmark → Shopi
Themes
- rag
- vector-search