✳flâneur — a map of the web's best reading
How We Store and Search 30 Billion Faces
clearview.ai · 2,224 words · saved by 2 readers
Our team of dedicated engineers has been working around the clock to enhance our product’s capabilities, and we have learned a lot along the
By Terence Liu BLOG Overview of a vector database: search and add flows. Our team of dedicated engineers has been working around the clock to enhance our product’s capabilities, and we have learned a lot along the way. We are looking forward to sharing some of the challenges and insights to a wider audience. This article is just the start of an exciting series of Engineering write-ups. We hope you find it interesting! The Clearview AI platform has evolved significantly over the past few years, with our database growing from a few million face images to an astounding 30 billion today. As the da
Explore this link on the map →saved by
related reading
- Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Vector embeddings | OpenAI APIplatform.openai.com
- Build Your Own Databasenan.fyi
- Announcing ScaNN: Efficient Vector Similarity Searchai.googleblog.com
- Not All Vector Databases Are Made Equal | Towards Data Sciencetowardsdatascience.com
- Indexing 1T vectors · facebookresearch/faiss Wiki · GitHubgithub.com
- What Is a Vector Database? | IBMibm.com
- Hierarchical Navigable Small Worlds (HNSW) | Pineconepinecone.io
- Welcome to Faiss Documentation - Faiss documentationfaiss.ai
- From 3 TB RAM to 96 GB: superseding billion vector HNSW with 40x cheaper DiskANNblog.wilsonl.in
- Vector databases explained | Lantern Bloglantern.dev