Jon BratsethinvespaWhen you’re using vectors you’re doing searchThe legends tell us that in the ancient times you could only put numbers in your databases. Then somebody invented the string, and the…Feb 21Feb 21
Jon BratsethinvespaVector streaming search: AI assistants at scale without breaking the bankIf you are using a large language model to build a personal assistant you often need to give it access to personal data such as email…Oct 10, 2023Oct 10, 2023
Jon BratsethinvespaThe hardest problem in computingWhat is the hardest problem in applied computing? My bet is on big data serving — computing over large data sets online. It requires…Jun 26, 2020Jun 26, 2020
Jon BratsethinvespaWhy most computation will become onlineAdvanced companies are busy moving their machine learning application online, making decisions right at the moment they are needed. But…Mar 2, 2020Mar 2, 2020
Jon BratsethinvespaThe big data maturity levelsBy now it’s well known that making effective use of data is a competitive advantage. But how advanced is your organization at making use…Jan 21, 20201Jan 21, 20201
Jon BratsethinvespaServing article comments using reinforcement learning of a neural netDon’t look at the comments. When you allow users to make comments on your content pages you face the problem that not all of them are…Feb 12, 2019Feb 12, 2019
Jon BratsethinvespaEfficient personal search at large scaleVespa includes a relatively unknown mode which provides personal search at massive scale for a fraction of the cost of alternatives…Jan 21, 2019Jan 21, 2019
Jon BratsethinvespaScaling serving time TensorFlow model evaluation with VespaEvaluating machine-learned models over a single item per user request is quite simple, but this isn’t sufficient for for advanced use…Jan 17, 2019Jan 17, 2019
Jon BratsethinvespaBlog recommendation with neural network modelsIntroductionJan 15, 2019Jan 15, 2019