I share search tips, blog articles, and free events I'm hosting about the search+retreval industry, vector databases, information retrieval and more.
Writes make vectorDB benchmarks fall apart
|
I'm writing about the weak spots in vector databases. Where you should prod and poke when selecting a vendor. Today: Updating Vector Databases If you think about the old vector search regime, it involved
We overindexed on this paradigm, creating data structures focused on good search performance that couldn't tolerate updates. I wrote about how sensitive graph-based vector DBs in particular are to updates, picking on Lucene unfairly: https://softwaredoug.com/blog/2026/08/18/update-graph-vector-db -Doug --- PS don't miss out on my Building Production Agents class with Hugo Bowne Anderson on Agentic Search + Building Agents. Sign up here: https://maven.com/softwaredoug/build-enterprise-agents ---- Slack Community * Events · Consulting · Training (use code searchtips) 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: |
Doug Turnbull
I share search tips, blog articles, and free events I'm hosting about the search+retreval industry, vector databases, information retrieval and more.
My work is split between mature search teams and new AI teams. Search teams are often farther along and manage a mature, traditional search product. AI teams, however, often don't know what they don't know yet. They've just been cobbled together, have built a few agent demos, and are often in the process of discovering the three big mistakes I blog here: Evals+measurement need to dominate a lot of your product thinking Retrieval isn't "one thing" (ie classic RAG) - its extremely custom to...
Hey all, I wrote a new article about a technique that has come up over and over in my work, especially in my Cheat at Search training, for doing effective query understanding into a large vocabulary. Instead of asking an LLM to classify into a vocabulary. Ask it to hallucinate fake entities, then resolve those to real ones client side. Save yourself a lot of tokens and use cheaper models. https://softwaredoug.com/blog/2026/08/10/hypothetical-classifications -Doug PS - A reminder that Vectors...
There's a class of search problems where: The total number of records is small ~1 million The index is built up front and doesn't change frequently Don't get hoodwinked into buying a vector database. Just brute-force search your embeddings. A naive Numpy search can do exhaustive vector search at 170QPS. You can replicate and copy that data to scale even further. More in my blog article: https://softwaredoug.com/blog/2026/07/29/just-brute-force-embeddings Wectors Week + Context Camp A reminder...