Case studies:
Discover how leading tech companies use Vespa
Explore real-world applications and success stories showcasing the power and versatility of Vespa.
-
Spotify relies on Vespa for a variety of use cases
“As a reliable and scalable solution, Vespa has been instrumental in enabling Search at Spotify. We look forward to continuing our work with the Vespa team, and enabling innovation that will enhance the experience for Spotify listeners.“
Daniel Doro, Director of Engineering, Search
One of the use cases for Vespa at Spotify is to provide semantic search in Podcasts:
“We are using a machine learning technique called Dense Retrieval, which consists of training a model that produces query and episode vectors in a shared embedding space. […] The objective is that the vectors of a search query and a relevant episode would be close together in the embedding space. For queries, we use the query text as input to the model, and for episodes, we use a concatenation of textual metadata fields of the episode such as its title, description, its parent podcast show’s title and description, and so on.
During live Search traffic, we can then employ sophisticated vector search techniques to efficiently retrieve the episodes whose vectors are the closest to the query vector.“
-
Elicit has chosen to build their innovative solution for working with the scientific body of knowledge on Vespa
“Vespa is a battle-tested platform that allows us to integrate keyword and vector search seamlessly. It forms a key part of our AI research solution, guaranteeing both precision and rapidity in streamlining research processes. We highly recommend Vespa for its reliability and efficiency.“
Jungwon Byun, COO & Cofounder
Elicit emphasises how RAG solutions are mostly about getting search right:
“Ultimately, recent advancements in AI make it much easier to build cutting-edge search, using orders of magnitude less effort than once required. Because of that, the return on sitting down and seriously building good search is extremely high.
If you want to build a RAG-based tool, first build search.“
-
Yahoo has leveraged Vespa Cloud to build most of their highly scaled personalized interactive experiences
“Vespa has been a critical component to Yahoo’s AI and machine learning capabilities across all of our properties for many years”
Jim Lanzone, Yahoo CEO
Yahoo has leveraged Vespa Cloud to build most of their highly scaled personalized interactive experiences, powering teams across the company:
“Yahoo claims that it’s using around 150 apps created with Vespa and that these apps collectively serve a user base of a billion people — processing 800,000 queries per second.”
-
“Our team successfully implemented the entire recommendation process of one algorithm with Vespa, matching the latency requirements (provide recommendations under 100ms) and scalability needs.”
Ricardo Rossi Tegão, Machine Learning Engineer
Farfetch use Vespa to scale online recommendations in theire-commerce platform:
One of our major challenges is to do it without increasing our infrastructure indefinitely. To tackle this scalability challenge, we choose to use a vector database and Vespa matches our necessity because of all the available features:
- Tensor Operations: Dense and sparse vector operations (e.g. map, reduce, slice, etc.).
Complex Ranking: Compute different signals (e.g. bm25, dot-product, cosine, etc.) and use them freely to rank document matches. - Keyword Search: You can use Vespa like Elasticsearch.
- LTR: Native model service that can be used for ranking (e.g. LTR).
- Filtering: Pre and post-filtering that you can tune to fit your use cases.
- Performance: C++ code optimised to use SIMD operations when possible.
With this, we intend to serve all recommendations for all platforms using Vespa and have no scalability issues when a new online retailer joins our services.
- Tensor Operations: Dense and sparse vector operations (e.g. map, reduce, slice, etc.).
-
Qwant, the privacy-friendly search engine developed in France and leader in Europe, is accelerating its collaboration with Vespa.ai, the open big data serving engine, to index and serve web queries on a large scale.
By storing its own web index in this new infrastructure deployed in its data center in France, the Qwant search engine responds even more relevantly and quickly to its users queries.
Qwant is thus improving the performance and experience of its search engine, while respecting its users personal data and offering unbiased search results.
-
Vinted uses Vespa to power their e-commerce personalized recommendations
“We are excited to share our story as we have found Vespa to be a great solution combining the now trendy vector search with more traditional sparse search techniques, as well as offering a great engineering experience.”