All Stories

Internship at Vespa

After the summer internship of 2021 the interns have summarised what they have done and their experience at Vespa

Vespa Product Updates, July 2021

Photo by Scott Graham on Unsplash

Vespa Product Updates, July 2021

Advances in Vespa features and performance include HTTP/2 feed and query endpoints, ONNX Runtime integration for stateless model inference, and the new open Vespa Factory build and test system.

Accelerating stateless model evaluation on Vespa

It has become increasingly important to efficiently evaluate machine-learned models in the stateless container cluster. We have recently added accelerated model evaluation here, which opens up new usage areas.

Improve throughput and concurrency with HTTP/2

The Vespa HTTP container now accepts HTTP/2 with TLS enabled. Learn how this improves HTTP throughput and efficiency, and how to get started using HTTP/2.

Pretrained Transformer Language Models for Search - part 4

This is the fourth blog post in a series of posts where we introduce using pretrained Transformer models for search and document ranking with Vespa.ai.

Build a basic text search application from python with Vespa: Part 2

Evaluate search engine experiments from python.

Pretrained Transformer Language Models for Search - part 3

Photo by Frank Busch on Unsplash

Pretrained Transformer Language Models for Search - part 3

This is the third blog post in a series of posts where we introduce using pretrained Transformer models for search and document ranking with Vespa.ai.

Pretrained Transformer Language Models for Search - part 2

Photo by Rob Fuller on Unsplash

Pretrained Transformer Language Models for Search - part 2

This is the second blog post in a series of posts where we introduce using pretrained Transformer models for search and document ranking with Vespa.ai.

Vespa Product Updates, May 2021

Photo by Ilya Pavlov on Unsplash

Vespa Product Updates, May 2021

Advances in features and performance include new int8 and bfloat16 tensor cell types, compact tensor feed format, Approximate Nearest Neighbor using Hamming distance, hash-based attribute dictionaries and case-sensitive attribute search...

Build a News recommendation app from python with Vespa: Part 3

Part 3 - Efficient use of click-through rate via parent-child relationship.

Pretrained Transformer Language Models for Search - part 1

Photo by Jamie Street on Unsplash

Pretrained Transformer Language Models for Search - part 1

This is the first blog post in a series of posts where we introduce using pretrained Transformer models for search and document ranking with Vespa.ai.

Build sentence/paragraph level QA application from python with Vespa

Photo by Brett Jordan on Unsplash

Build sentence/paragraph level QA application from python with Vespa

Retrieve paragraph and sentence level information with sparse and dense ranking features.