The Rise and Fall of the Vector DB category: Jo Kristian Bergum (ex-Chief Scientist, Vespa)

Argues vector search is a feature rather than a standalone category, which helps you decide between dedicated vector stores and hybrid search systems for RAG and agent memory.

• hybrid search — Combining keyword and semantic search in one ranked result, so exact terms and paraphrases both find what they should.
• RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• videoThe State of Reasoning — from Nathan Lambert, Interconnects/AI2 [LS Live @ NeurIPS 2024]
• video⚡️ARC-AGI-3: The Interactive Reasoning Benchmark
• videoThe Agents Economy Backbone - with Emily Glassberg Sands, Head of Data & AI at Stripe
• videoOne Year of MCP — with David Soria Parria and AAIF leads from OpenAI, Goose, Linux Foundation

• videoLong Live Context Engineering - with Jeff Huber of ChromaLatent Space
• videoRetrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Eskildsen of TurbopufferLatent Space
• videoBeating Google at Search with Neural PageRank and $5M of H200s — with Will Bryk of Exa.aiLatent Space

Checking sign-in…

Loading comments…