All Stories

Announcing vector streaming search: AI assistants at scale without breaking the bank
Photo by Marc Sendra Martorell on Unsplash

Announcing vector streaming search: AI assistants at scale without breaking the bank

With personal data, you need complete results at low cost, something vector databases cannot provide. Vespa's new vector streaming search delivers complete results at a fraction of the cost.

Geir Storli Jon Bratseth Tor Egge
Geir Storli Jon Bratseth Tor Egge
28 Jun 2023
Vespa at Berlin Buzzwords 2023

Vespa at Berlin Buzzwords 2023

Summarizing Berlin Buzzwords 2023, Germany’s most exciting conference on storing, processing, streaming and searching large amounts of digital data.

Kristian Aune
Kristian Aune
23 Jun 2023
Enhancing Vespa’s Embedding Management Capabilities
Photo by vnwayne fan on Unsplash

Enhancing Vespa’s Embedding Management Capabilities

We are thrilled to announce significant updates to Vespa’s support for inference with text embedding models that maps texts into vector representations.

Jo Kristian Bergum Bjørn C Seime
Jo Kristian Bergum Bjørn C Seime
14 Jun 2023
Vespa Newsletter, May 2023
Photo by Scott Graham on Unsplash

Vespa Newsletter, May 2023

Advances in Vespa features and performance include multi-vector HNSW Indexing, global-phase re-ranking, LangChain support, improved bfloat16 throughput, and new document feed/export features in the Vespa CLI.

Kristian Aune
Kristian Aune
31 May 2023
High performance feeding with Vespa CLI
Photo by Shiro hatori on Unsplash

High performance feeding with Vespa CLI

Vespa CLI can now feed large sets of documents to Vespa efficiently.
Martin Polden
Martin Polden
22 May 2023
Vespa support in langchain

Vespa support in langchain

Langchain now comes with a Vespa retriever.
Jon Bratseth
Jon Bratseth
08 May 2023
Minimizing LLM Distraction with Cross-Encoder Re-Ranking
Photo by Will van Wingerden on Unsplash

Minimizing LLM Distraction with Cross-Encoder Re-Ranking

Announcing global-phase re-ranking support in Vespa, unlocking efficient re-ranking with precise cross-encoder models. Cross-encoder models minimize distraction in retrieval-augmented completions generated by Large Language Models.
Bjørn C Seime Arne H Juul Jo Kristian Bergum
Bjørn C Seime Arne H Juul Jo Kristian Bergum
08 May 2023
Customizing Reusable Frozen ML-Embeddings with Vespa
Photo by fabio on Unsplash

Customizing Reusable Frozen ML-Embeddings with Vespa

Deep-learned embeddings are popular for search and recommendation use cases. This post introduces the concept of using reusable frozen embeddings and tailoring them with Vespa.
Jo Kristian Bergum
Jo Kristian Bergum
31 Mar 2023
Revolutionizing Semantic Search with Multi-Vector HNSW Indexing in Vespa
Photo by Peter Herrmann on Unsplash

Revolutionizing Semantic Search with Multi-Vector HNSW Indexing in Vespa

Announcing multi-vector indexing support in Vespa, which allows you to index multiple vectors per document and retrieve documents by the closest vector in each document.
Geir Storli Tor Egge Jo Kristian Bergum
Geir Storli Tor Egge Jo Kristian Bergum
29 Mar 2023
Private regional endpoints in Vespa Cloud
Photo by Taylor Vick on Unsplash

Private regional endpoints in Vespa Cloud

Set up private endpoint services on your Vespa Cloud application, and access them from your own VPC, in the same region, through the cloud provider's private network.
Jon M Venstad
Jon M Venstad
24 Mar 2023
Vespa Newsletter, March 2023
Photo by Ilya Pavlov on Unsplash

Vespa Newsletter, March 2023

Advances in Vespa features and performance include GPU support, advanced BCP autoscaling, GCP Private Service Connect, and a great update to the e-commerce sample app.

Kristian Aune
Kristian Aune
21 Mar 2023
GPU-accelerated ML inference in Vespa Cloud
Photo by Sandro Katalina on Unsplash

GPU-accelerated ML inference in Vespa Cloud

Today we're introducing support for GPU-accelerated ONNX model inference in Vespa, together with support for GPU instances in Vespa Cloud!
Martin Polden
Martin Polden
08 Mar 2023