--- title: Just brute force your embeddings | daily.dev description: For many teams with around 1 million documents, a full vector database is overkill. A simple NumPy dot product brute-force search on float32 embeddings can... canonical: https://daily.dev/posts/just-brute-force-your-embeddings-2putsthhk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Just brute force your embeddings | daily.dev og:description: For many teams with around 1 million documents, a full vector database is overkill. A simple NumPy dot product brute-force search on float32 embeddings can... og:url: https://daily.dev/posts/just-brute-force-your-embeddings-2putsthhk og:image: https://api.daily.dev/og/posts/2PuTStHHk.png og:image:alt: Just brute force your embeddings og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Just brute force your embeddings **[Hacker News](https://daily.dev/sources/hn)** · 2 min read · 0 upvotes · 0 comments ## Summary For many teams with around 1 million documents, a full vector database is overkill. A simple NumPy dot product brute-force search on float32 embeddings can achieve ~80 QPS at 12ms latency on a modern laptop. Benchmarks show this approach scales reasonably up to ~9 million documents before latency becomes a concern. The recommendation is to start with brute-force search and only graduate to a vector database or in-memory FAISS index when the simpler approach genuinely can't keep up. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [You Probably Don’t Need a Vector Database for Your RAG — Yet](https://daily.dev/posts/you-probably-don-t-need-a-vector-database-for-your-rag-yet-ldtdyx6gt) · Towards Data Science · 0 upvotes · 0 comments - [RW \#9 - How Vector DBs Store 100M Embeddings on One Machine \(and Still Search Fast\)](https://daily.dev/posts/rw-9---how-vector-dbs-store-100m-embeddings-on-one-machine-and-still-search-fast--xf5prc5bc) · Machine Learning Pills · 0 upvotes · 0 comments - [Build And Understand a Vector Database From Scratch in 10 Easy Steps](https://daily.dev/posts/build-and-understand-a-vector-database-from-scratch-in-10-easy-steps-lxnnko47t) · Machine Learning Mastery · 1 upvotes · 0 comments - [Benchmarking vector indexes](https://daily.dev/posts/benchmarking-vector-indexes-hch39inje) · Percona Blog · 1 upvotes · 1 comments --- Tags: [#python](https://daily.dev/tags/python), [#vector-search](https://daily.dev/tags/vector-search), [#embeddings](https://daily.dev/tags/embeddings), [#numpy](https://daily.dev/tags/numpy) [View this post on daily.dev](https://daily.dev/posts/just-brute-force-your-embeddings-2putsthhk) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Just brute force your embeddings","url":"https://daily.dev/posts/just-brute-force-your-embeddings-2putsthhk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/just-brute-force-your-embeddings-2putsthhk"},"datePublished":"2026-07-31T22:30:46.478Z","dateModified":"2026-08-01T02:49:36.628Z","description":"For many teams with around 1 million documents, a full vector database is overkill. A simple NumPy dot product brute-force search on float32 embeddings can...","image":"https://media.daily.dev/image/upload/s--2-1xRawN--/f_auto/v1722860399/public/Placeholder%2011","thumbnailUrl":"https://media.daily.dev/image/upload/s--2-1xRawN--/f_auto/v1722860399/public/Placeholder%2011","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/just-brute-force-your-embeddings-2putsthhk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,vector-search,embeddings,numpy","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Just brute force your embeddings"}]} ```