Open in app

Sign In

Write

Sign In

Jo Kristian Bergum
Jo Kristian Bergum

185 Followers

Home

About

Published in vespa

·Oct 27, 2022

Building Billion-Scale Vector Search — part two

This blog is the second post in a series on building a billion-scale vector search using Vespa. The series covers the cost and serving performance tradeoffs related to approximate nearest neighbor search at a large scale. In the first post, we introduced some challenges related to building large-scale vector search…

Vector Search

14 min read

Building Billion-Scale Vector Search — part two
Building Billion-Scale Vector Search — part two
Vector Search

14 min read


Published in vespa

·Oct 27, 2022

Building Billion-Scale Vector Search — part one

How 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 manage, your blink-of-an-eye latency is around 100ms. …

Vector Search

6 min read

Building Billion-Scale Vector Search — part one
Building Billion-Scale Vector Search — part one
Vector Search

6 min read


Sep 15, 2022

Will new vector databases dislodge traditional search engines?

Doug Turnbull asks an interesting question on Linkedin; Will new vector databases dislodge traditional search engines? The short answer is no, but it depends on what you classify as a traditional search engine. Features like phrase search, exact search, BM25 ranking, dynamic summaries, and result facets are features we take…

Vespa

4 min read

Will new vector databases dislodge traditional search engines?
Will new vector databases dislodge traditional search engines?
Vespa

4 min read


Published in vespa

·Jul 1, 2022

Managed Vector Search using Vespa Cloud

There is a growing interest in AI-powered vector representations of unstructured multimodal data and searching efficiently over these representations. This blog post describes how your organization can unlock the full potential of multimodal AI-powered vector representations using Vespa — the industry-leading open-source big data serving engine. Photo by israel palacio on Unsplash Introduction Deep Learning has revolutionized information extraction from unstructured data like text, audio, image, and videos. Furthermore, self-supervised learning algorithms like data2vec accelerate learning representations of speech, vision, text, and multimodal representations combining these modalities. …

Vespa Cloud

6 min read

Managed Vector Search using Vespa Cloud
Managed Vector Search using Vespa Cloud
Vespa Cloud

6 min read


Published in vespa

·Jun 17, 2022

Vespa at Berlin Buzzwords 2022

Find videos and links from four Vespa-related talks at Berlin Buzzwords 2022, Germany’s most exciting conference on storing, processing, streaming, and searching large amounts of digital data. — Berlin Buzzwords 2022 has just finished, and we thought it would be great to summarize the event. Berlin Buzzwords is Germany’s most exciting conference on storing, processing, streaming, and searching large amounts of digital data, focusing on open-source software projects.

Berlin Buzzwords

5 min read

Vespa at Berlin Buzzwords 2022
Vespa at Berlin Buzzwords 2022
Berlin Buzzwords

5 min read


Published in vespa

·Jun 8, 2022

Billion-scale vector search using hybrid HNSW-IF

This blog post describes HNSW-IF, a cost-efficient solution for high-accuracy vector search over billion scale vector datasets. — The first blog post on billion-scale vector search covered methods for compressing real-valued vectors to binary representations and using hamming distance for efficient coarse level search. …

Vespa

15 min read

Billion-scale vector search using hybrid HNSW-IF
Billion-scale vector search using hybrid HNSW-IF
Vespa

15 min read


Published in vespa

·May 20, 2022

Query Time Constrained Approximate Nearest Neighbor Search

This blog post describes Vespa’s industry-leading support for combining approximate nearest neighbor search, or vector search, with query constraints to solve real-world search and recommendation problems at scale. Photo by Christopher Burns on Unsplash This blog post describes Vespa’s support for combining approximate nearest neighbor search, or vector search, with query-time filters or constraints to tackle real-world search and recommendation use cases at scale. The first section covers the data structures Vespa builds to support fast search in…

Vector Search Engine

13 min read

Query Time Constrained Approximate Nearest Neighbor Search
Query Time Constrained Approximate Nearest Neighbor Search
Vector Search Engine

13 min read


Published in vespa

·Jan 27, 2022

Billion-scale vector search with Vespa — part two

In the first post in this series, we introduced compact binary-coded vector representations that can reduce the storage and computational complexity of both exact and approximate nearest neighbor search. This second post covers an experiment using a 1-billion binary-coded representation derived from a vector dataset used in the big-ann-benchmark challenge. …

Vespa

12 min read

Billion-scale vector search with Vespa — part two
Billion-scale vector search with Vespa — part two
Vespa

12 min read


Jan 2, 2022

Moving ML Inference from the Cloud to the Edge

In this blog post, I investigate running Machine Learned (ML) inference computation as close as possible to where the model input data is generated on a user's device at the edge. There are several definitions of "Edge," but for me, Edge computations cover inference computations on the user device, in…

Edge Ai

9 min read

Moving ML Inference from the Cloud to the Edge
Moving ML Inference from the Cloud to the Edge
Edge Ai

9 min read


Published in vespa

·Dec 3, 2021

Billion-scale vector search with Vespa — part one

Part one in a blog post series on a billion-scale vector search. This post covers using nearest neighbor search with compact binary representations and bitwise hamming distance. — NASA estimates that the Milky Way galaxy contains between 100 to 400 billion stars. A mind-blowing large number of stars and solar systems, and also a stunning sight from planet earth on a clear night. Many organizations face challenges involving star-sized datasets, even orders of magnitude larger. AI-powered representations of…

Vector Search

9 min read

Billion-scale vector search with Vespa — part one
Billion-scale vector search with Vespa — part one
Vector Search

9 min read

Jo Kristian Bergum

Jo Kristian Bergum

185 Followers

Working on Vespa.ai

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech