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...

Almost all my clients face this issue. They want to build a RAG system. They have: Millions of PDFs That turn into Billions of chunks + embeddings Turns into become petabytes of floats That's the recipe of nearly every speculative RAG project I've worked on. A mature search team stands up a vector database and can't tame the sheer scale of data they're facing. That drags project timelines out months while costs skyrocket. It's important to have tools to manage the scale. One often overlooked...