{"slug": "vectors-week-become-a-savier-vector-db-customer", "title": "Vectors Week: become a savier vector db customer", "summary": "A series of vector database courses, led by Doug Turnbull and Adam Hevenor, will run the week of August 10, covering how to choose a vector database, improve hybrid search, and build a vector database from scratch. The courses aim to help users become informed buyers and practitioners of vector retrieval technology.", "body_md": "Become a savvy vector database user and buyer. Come hang with me and [Adam Hevenor](http://hevmind.com) as we learn about vector retrieval from first principles the week of August 10th.\n\n## How to choose a vector database (Aug 10)\n\nSign up: [https://maven.com/p/59a7d9/how-to-choose-a-vector-database](https://maven.com/p/59a7d9/how-to-choose-a-vector-database)\n\nI am asked constantly which vector database to choose. It’s not a simple question to answer. And I don’t just want to rattle off what I’m personally comfortable with.\n\nAdam’s going to give us a more systematic approach to vector database selection. What should you measure? What features matter? What doesn’t get attention in vector benchmarks and comparisons?\n\n## Why your hybrid search sucks (Aug 12)\n\nSign up: [https://maven.com/p/ec3299/why-your-hybrid-search-sucks](https://maven.com/p/ec3299/why-your-hybrid-search-sucks)\n\nA classic search team mistake: naively merging lexical and dense vector search and saying “done”. User intent and query understanding must come first. Then you can consider how to select candidates for later ranking. In this talk, we’ll go beyond naive [RRF](https://softwaredoug.com/blog/2024/11/03/rrf-is-not-enough), and build hybrid search that ranks and filters with the user first, not the technology.\n\n## Build your own vector database (Aug 14)\n\nSign up: [https://maven.com/softwaredoug/vectordb](https://maven.com/softwaredoug/vectordb)\n\nI don’t recommend you work in search without becoming intimately acquainted with vector search primitives.\n\n- Quantization and dimensionality reduction - how to shrink the footprint of embeddings so that vector storage doesn’t cost a fortune\n- Graph and clustering algorithms - how do production vector databases find nearest neighbors? How, exactly, do the core family of algorithms work?\n- Filtering by metadata - Almost every production vector search will have filters. Filtering zeros in on the best candidates worth ranking. But it’s also a blind spot for production teams.\n\nSo join me in a short, paid course Friday afternoon where we’ll [build a vector database together](https://maven.com/softwaredoug/vectordb), making you an informed buyer and user.\n\n### Upcoming course: Build your own vector database\n\nWant to understand what makes embedding retrieval fast, relevant, and useful in real AI systems? Join [Build your own vector database](https://maven.com/softwaredoug/vectordb) and build the core pieces yourself, from embeddings and indexing to search and retrieval.", "url": "https://wpnews.pro/news/vectors-week-become-a-savier-vector-db-customer", "canonical_source": "http://softwaredoug.com/blog/2026/07/29/vectors-week.html", "published_at": "2026-07-29 00:00:00+00:00", "updated_at": "2026-07-29 13:54:50.892436+00:00", "lang": "en", "topics": ["ai-infrastructure", "ai-tools", "machine-learning", "developer-tools"], "entities": ["Doug Turnbull", "Adam Hevenor", "Maven"], "alternates": {"html": "https://wpnews.pro/news/vectors-week-become-a-savier-vector-db-customer", "markdown": "https://wpnews.pro/news/vectors-week-become-a-savier-vector-db-customer.md", "text": "https://wpnews.pro/news/vectors-week-become-a-savier-vector-db-customer.txt", "jsonld": "https://wpnews.pro/news/vectors-week-become-a-savier-vector-db-customer.jsonld"}}