|
This week the Retrieval Augmented Gathering online conference continues! Last week we explored index-only SPLADE, got a demo of tensors in the search engine, and how to think of agentic memory as telemetry. This week we've got talks below: Embeddings don't solve RAG (today)Solving retrieval for agents isn't as simple as chunk + embed. For one, similarity is not relevance. An decides what's relevant depending on not just raw text, but everything that 'surrounds' it. Places it in context. Would you trust BM25 content written by George RR Martin? Would you want you want recent information? Popular information? Agents need metadata to think about search navigationally, not just as flat retrieved docs. Link: https://maven.com/p/74f7ed/embeddings-don-t-solve-rag IR Today: Theory, Practice, and Agents (tomorrow)LLMs and agentic search have dominated search in 2026. Daniel Tunkelang will give his observations after attending SIGIR, the world’s leading conference on search and information retrieval, as well as reflecting on his own experience as a practitioner. Link: https://maven.com/p/1f1f46/ir-today-theory-practice-and-agents High scale agentic memory with Turbopuffer (Thursday)Agents don't remember what they learn in any one session: Jargon. Personal preferences. What works / doesn't work. In this talk, we'll explore one approach: just index all agentic traces into a high-scale vector database like Turbopuffer. Link: https://maven.com/p/e48f16/high-scale-agentic-memory-with-turbopuffer Cheat at Search w/ Agents training starts next weekI teach people how to improve and build better RAG + Agentic Retrieval. A reminder my course starts in one week. Hope to see you there: http://maven.com/softwaredoug/cheat-at-search Cheers, -Doug Slack Community * Events · Consulting · Training (use code search-tips) You're subscribed to Doug Turnbull's daily search tips where I share tips, blog articles, events, and more. You can always manage your profile: |
I share search tips, blog articles, and free events I'm hosting about the search+retreval industry, vector databases, information retrieval and more.
I am a loyal customer of Alamo Drafthouse and Cinema - a boutique movie theater chain in the US. One nice perk is they allow you to order with a QR code ordering system from your table. Sadly the search doesn't work that well, when you search for "burger" you get "nachos" as the first result. Well that's an annoyance purpose-built for me. So I took it upon myself to recreate the search, then fix it. Did I build vector search? No. Did I try to improve query understanding? No. What I did...
This week+next there's some upcoming, free search events I'm cohosting: AI-Search Fundamentals (free 'intro to search' training) Today 12PM ET (w/ Me + Trey Grainger) Sign up -- https://maven.com/p/b9e696/ai-search-fundamentals-vector-spaces-matching-ranking This session covers foundational concepts in information retrieval around matching and ranking. We'll cover sparse vs. dense vector spaces, lexical (BM25) vs. semantic (embedding) search, and matching and relevance ranking fundamentals....
I wrote a detailed blog article critiquing the traditional judgment list search evaluation regime. It's impossible to NOT have some kind of sampling bias. IE your labels all come from BM25 or some legacy search algorithm. So solutions can, at best, measure their effectiveness reranking within that sample. Indeed, its hard to think of an alternative. Labeling random results will just end up wasting time (99% of the corpus will be irrelevant). In the end, you need a sampling algorithm to mine...