{ }
Blog
Vespa.ai
Docs
Subscribe
Vespa Blog
We Make AI Work
Posts by Jon Bratseth
Architecture Inversion: Scale By Moving Computation Not Data
Have you ever wondered how the world’s largest internet and social media companies can deliver algorithmic content to so many users so fast?
Vector search beyond the database
The purpose of using vectors is to improve quality, but that takes much more than a similarity lookup. Search engines are built for that, databases...
Vinted moves from Elasticsearch to Vespa
With Vespa, Vinted managed to halve the number of servers, slash query latency by 2.5x, indexing latency by 3x, and increase ranking depth by more...
Farfetch: Scaling recommendations with Vespa
E-commerce platform Farfetch explains how they use Vespa to scale their online recommendation system
Marqo chooses Vespa
Vector search experts Marqo choose Vespa as their vector database after benchmarking against Milvus, OpenSearch, Weaviate, Redis, and Qdrant.
The Singaporean government deploys state of the art semantic search
The Singaporean government leverages Vespa to do semantic search in every word ever said in Parliament
Embedding flexibility in Vespa
Why did Vespa score "Exceptional" on Embedding Flexibility in GigaOm's report on Vector Databases?
When you're using vectors you're doing search
Combining scale and quality takes more than vector similarity search
GigaOm Sonar for Vector Databases Positions Vespa as a Leader
Although we're more than a vector database, we're happy to be recognized as a leader in this category
Yahoo Mail turns to Vespa to do RAG at scale
Vector search in trillions of personal documents can be done cost-effectively with vector streaming search.
Announcing our series A funding
Announcing a $31 million investment from Blossom Capital
Vespa is becoming a company
Vespa is becoming its own company!
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...
Vespa support in langchain
Langchain now comes with a Vespa retriever.
Pre-trained models on Vespa Cloud
Vespa Cloud now provides pre-trained ML models for your applications
Text embedding made simple
Vespa now lets you create a production quality semantic search application from scratch in minutes
Vespa 8 is here
Announcing the release of Vespa 8 - the next major version of vespa.ai
The hardest problem in computing
What is the hardest problem in applied computing? My bet is on big data serving — computing over large data sets online.
Why most computation will become online
The most advanced companies of the world are busy moving their computation over data online. But why?
The big data maturity levels
By now it’s well known that making effective use of data is a competitive advantage. But how advanced is your organization at making use of...
Never miss a
story
from us, subscribe to our newsletter
Subscribe