Jo Kristian BergumThree mistakes when introducing embeddings and vector searchRepresenting unstructured data as embedding vectors and embedding-based retrieval (EBR) using vector search is more popular than ever. What…8 min read·Apr 14, 2023--9--9
Jo Kristian BerguminvespaBuilding Billion-Scale Vector Search — part twoThis blog is the second post in a series on building a billion-scale vector search using Vespa. The series covers the cost and serving…14 min read·Oct 27, 2022----
Jo Kristian BerguminvespaBuilding Billion-Scale Vector Search — part oneHow fast is fast? Many consider the blink of an eye, around 100–250ms, to be plenty fast. Try blinking 10 times in a second? If you can…6 min read·Oct 27, 2022----
Jo Kristian BergumWill new vector databases dislodge traditional search engines?Doug Turnbull asks an interesting question on Linkedin; Will new vector databases dislodge traditional search engines?4 min read·Sep 15, 2022----
Jo Kristian BerguminvespaManaged Vector Search using Vespa CloudThere is a growing interest in AI-powered vector representations of unstructured multimodal data and searching efficiently over these…6 min read·Jul 1, 2022----
Jo Kristian BerguminvespaVespa at Berlin Buzzwords 2022Find videos and links from four Vespa-related talks at Berlin Buzzwords 2022, Germany’s most exciting conference on storing, processing…5 min read·Jun 17, 2022----
Jo Kristian BerguminvespaBillion-scale vector search using hybrid HNSW-IFThis blog post describes HNSW-IF, a cost-efficient solution for high-accuracy vector search over billion scale vector datasets.15 min read·Jun 8, 2022----
Jo Kristian BerguminvespaQuery Time Constrained Approximate Nearest Neighbor SearchThis blog post describes Vespa’s industry-leading support for combining approximate nearest neighbor search, or vector search, with query…13 min read·May 20, 2022----
Jo Kristian BerguminvespaBillion-scale vector search with Vespa — part twoPhoto by Vincentiu Solomon on Unsplash12 min read·Jan 27, 2022----
Jo Kristian BergumMoving ML Inference from the Cloud to the EdgeIn this blog post, I investigate running Machine Learned (ML) inference computation as close as possible to where the model input data is…9 min read·Jan 2, 2022--3--3