My buddy John Berryman and I were nicely hosted by Hugo Browne-Anderson on the Vanishing Gradients podcast. We talked about how agentic search stands poised to be more disruptive to the Information Retrieval space than RAG. Check it out! Other upcoming events Tomorrow (free) Cheat at Search Essentials, Vector Search (free) ReasoningLayer.ai - symbolic reasoning with LLMs Tuesday (free) Cheat at Search Essentials - Search Evaluation (WTF is an NDCG?) Friday (free) Doug Turnbull + Daniel...
3 days ago • 1 min read
Youtube masterminded how to turn engagement into insights. Whether search or their feed, you can learn from how they learn from you! They: Create low-friction, sticky, addictive little interactions you do subconsciously on the surface. How often have you found yourself hovering over a video on your feed? Give you many actions to take on a video, even from search results themselves (bookmark, share, etc) Treat their monetization (ads) more as a guardrail. They know engaging you with a sticky,...
3 days ago • 1 min read
For those who don't know, Ralph Wiggum is the name given to the dumb, tail-chasing AI coding loop that often churns and churns, getting itself into trouble generating endless nonsense. With all sorts of mitigations to avoid Ralph ralphing up meaningless, crazy code Another way to think about Ralph is the endless epochs of model training. Sometimes after enough epochs, training goes off the rails, gets overfit, and stops actually improving on the task. That's why, coming from a search domain,...
4 days ago • 1 min read
Many get into search somewhat sideways and want to "fill in gaps" in knowledge. That's what this course is for! So if you're new to search, want to understand some basics, get the big picture "Explain Like I'm Five" perspective Cheat at Search Essentials, my free course, will start tomorrow: Tomorrow - Lexical + BM25 Thursday - Vectors and Embeddings Next Week - Search Evaluation See you there! -Doug Events · Consulting · Training (use code search-tips) You're subscribed to Doug Turnbull's...
5 days ago • 1 min read
When I worked at Shopify, the gold standard was GMV (the dollar amount in revenue). Naturally, that’s what we wanted to move with search A/B tests. Seems sane. BUT it doesn’t actually isolate search per-se. A lot can happen: Someone buys a $50K rolex on control randomly, destroying an A/B test User checkouts happen rarely, add to carts occasionally, and search clicks frequently For these experiments, You’d have to wait for very sparse confounders to even out. That might take months? Or maybe...
5 days ago • 1 min read
You may know ANN Benchmarks - it’s a leaderboard of vector search algorithms. It’s referenced a lot by companies when choosing a vector system. But let’s look at ANN Benchmarks - it measures: Recall Latency What does it NOT measure? Incremental updates impact on search latency Sharding and replication Reliability Consistency / availability of updates Filtering performance Memory usage Recall on YOUR embeddings Depending on YOUR problem, you may choose an ANN Benchmarks loser if say, you care...
8 days ago • 1 min read
A reminder to come hear from John Berryman talk tomorrow: https://maven.com/p/93a8f0/rag-isn-t-a-vector-search-problem -Doug 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:
9 days ago • 1 min read
Full-text search instincts about filters don’t translate to vector search In full-text search, the rule has been to filter before ranking. Make results more precise while speeding up search. While filters do improve precision, they don’t speed up graph based vector search: in fact search gets slower. Navigating vector spaces is like navigating a map. Except in more dimensions. You want to find nearest neighbors to an address? OK, it’s not hard to build a data structure that says “Here’s...
10 days ago • 1 min read
I know people get into search sort of accidentally. They work in search for a while, not fully confident in many core concepts. It can be helpful to have some gaps filled and core concepts explained. That's why I try to offer "Cheat at Search Essentials" once a quarter. It's a free course! And a great background if you're interested in February's paid Cheat at Search with Agents or March's AI Powered Search course. Cheat at Search Essentials. Free course. Starting Jan 20 (in one week!)...
11 days ago • 1 min read
