Vectors help you retrieve. Tensors help you reason.
One embedding flattens a document into a single point, and the structure relevance needs is lost.
Vespa.ai is tensor-native: hybrid, multi-vector, multimodal, real-time and ML-ranked signals in one pipeline.
Introducing agent-ready schemas.
By enabling agents to search like experts, we can increase success rates while reducing cost.
blog.vespa.ai/introducing-ag…
On the BrowseComp Plus benchmark, GPT 4.1 answered 93% of questions correctly when handed the right documents. When it had to find them with standard keyword search? Just 15%. Jenny Morris of @vespaengine joins our upcoming live webinar to explain why.
Save your spot: bit.ly/4yNVUOM
As AI gets more capable, its answers still depend on what it can find.
Vespa Voice is back for Season 2 🎙️ Our CEO and cofounder @jonbratseth opens with why relevance is the real moat, and why agents need more than vector search.
Twenty minutes with the person who has spent decades building search at scale.
Watch or listen here:👇
vespa.ai/vespa-voice/?utm_so…#VespaVoice#AISearch#AIAgents#RAG#InformationRetrieval
𝗪𝗵𝗮𝘁 𝗶𝘀 𝗮𝗻 𝗔𝗜 𝗦𝗲𝗮𝗿𝗰𝗵 𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺? 𝗚𝗲𝘁 𝘁𝗵𝗲 𝗼𝘃𝗲𝗿𝘃𝗶𝗲𝘄 𝗶𝗻 𝗷𝘂𝘀𝘁 𝗼𝘃𝗲𝗿 𝗮 𝗺𝗶𝗻𝘂𝘁𝗲. 🧐
AI applications need to find relevant information, rank it, and keep up as data changes. Spreading those capabilities across separate systems adds latency, cost, and complexity.
This short video explains how Vespa brings retrieval, ranking, and model inference together in one platform and why that matters for the applications you build.
The first in our short video series explaining AI search, one concept at a time.
Explore the Vespa AI Search Platform, including the architecture, the GigaOm brief, and the Perplexity case study: vespa.ai/ai-search-platform/#AISearch#RetrievalEngineering#AIAgents
𝗘𝘅𝘁𝗲𝗻𝗱𝗶𝗻𝗴 𝗩𝗲𝘀𝗽𝗮’𝘀 𝗛𝘆𝗯𝗿𝗶𝗱 𝗦𝗲𝗮𝗿𝗰𝗵 𝘄𝗶𝘁𝗵 𝗪𝗼𝗿𝗺𝗵𝗼𝗹𝗲 𝗩𝗲𝗰𝘁𝗼𝗿𝘀 🌀
Most hybrid search runs lexical and semantic search separately, then merges the results with RRF.
Wormhole Vectors take a different path: they let you travel between similar regions of lexical, semantic and behavioral vector spaces, and use them all in one search.
At Vespa.ai Live, Trey Grainger (Founder, Searchkernel) showed how to build them, using an e-commerce dataset.
Watch the recap 👇
youtu.be/hESWtiE3av8
How do you modernize recommendations when your data is anything but perfect?
At Vespa.ai Live London, Dr Christiane Lemke and André Charton of @kleinanzeigen_o , Germany's largest classifieds marketplace, shared how they moved homepage recommendations from a search-first setup to Vespa. Not a big-bang rewrite, but step by step.
What they covered:
◽ Starting with Motors, where data is most structured, then expanding
◽ Running old and new systems side by side, with quality guardrails
◽ Better signals from text embeddings, extracted attributes and images
◽ What didn't work, and which assumptions broke under real traffic
Watch the full talk👇
youtu.be/lh9wF1ugRyg
How Etsy replaced Solr and several other retrieval engines with one Vespa.ai-based system
Gregg Donovan shared the lessons at Vespa.ai Live London:
🔹 One platform, so teams focus on better search
🔹 Partial updates keep product data fresh, no full reindex
🔹 Lightweight models + deeper reranking on content nodes
🔹 Reproducible evaluation as the base for automated research
Watch the full talk 👇
youtu.be/INbNwOqoZFk
Building the foundations for AI search
At Vespa.ai Live London, Cem Ünsal of Walmart drew on roles at Yahoo, Optum, and Walmart to discuss the data, relevance, and organizational challenges behind effective enterprise search.
His lessons go well beyond choosing technology:
▪️ Build trust with rapid prototypes and blind, side-by-side relevance evaluations.
▪️ Bring engineers, data scientists, and product teams together.
▪️ Measure relevance, latency, and cost.
▪️ Invest in the skills and support needed for adoption.
These lessons matter more as companies work to become AI-native. As Walmart's CEO John Furner stated on the company's 21 May earnings call:
"We're also becoming AI native. Using AI, we can now serve customer needs that previous technologies could not meet, from making shopping easier and more personalized to expanding the range of shopping occasions and interactions we have with our customers and members."
Watch the talk 👇
youtu.be/ic4tOydC8y0
Quepid now works with Vespa!
Eric Pugh from OpenSource Connections recorded a short demo of Vespa integrated into Quepid, the open-source tool for measuring and tuning search relevance.
Thank you for putting this together, Eric! 👏
Watch the 4-min demo:👇
youtube.com/watch?v=-Sy5MG8R…
No reranker can recover a relevant passage that retrieval failed to surface. Bonnie Chase and Jenny Morris of @vespaengine join TNS Host Dr. Kim Fessel to examine the retrieval challenges behind scalable AI search.
Don't miss it: bit.ly/3UMqBG4
What happens when the right answer never makes it into the candidate set? Join Bonnie Chase and Jenny Morris of @vespaengine with TNS Host Dr. Kim Fessel to explore why retrieval quality is fundamental to effective AI search.
Register here: bit.ly/3UMqBG4
Human-scale retrieval and agent-scale retrieval are two very different infrastructure problems. Whit Walters from @GigaOm, Bonnie Chase from @vespaengine, and Alex Wilhelm from The New Stack will explore where conventional retrieval architectures start to break and what teams should rethink.
Join us live: bit.ly/45Ihf03
Your agent wants to search like a 2010 quant.
Retrieval for AI has passed through several stages of enlightenment. After the vector database craze, and the absorption of learnings from human information retrieval over the last half century, we might be officially entering the third stage with Perplexity's announcement of Search as Code.
Search for humans has over the years been dumbed down to accommodate the average user's capacity for formulating advanced queries, to the point where the words typed into query boxes are merely treated as vague indicators of what the user might want.
I see many replicating this way of thinking with AI agents, which leaves a lot of quality improvement on the table, as can be seen in Perplexity's benchmarks (ignore the "code" aspect as code execution is generally useful and where it runs doesn't matter for quality).
Models are quite capable and there's no reason to limit their options to those of a casual human user! They should be able to search for the names of those involved near each other in text when researching a legal case, choose a pure semantic search prioritizing high-quality sources when seeking a broad overview of a topic, or select a year range and group by month when constructing a timeline of some events, and so on.
An agent will typically string together many of these queries to reach its goal. First gaining an overview, then researching more specific topics, forming hypotheses, verifying important details in them. In short, search like an expert who knows what they are doing and really cares about the results— like a quant doing financial analysis.
Doing this in practice, with your own data, is actually quite easy. The models already know how to write complex queries in the languages of well-known AI search engines; they just need to be told that they can, what fields are available, and what they mean, and what choices they have in ranking the results.
How you tell them doesn’t actually matter that much; any simple textual description of what fields and ranking options are available will do. Models today are smart enough to use this effectively to connect their intents to specific YQL queries.
When creating search for humans, developers need to implement solutions that work well across a broad set of use cases, which involves making trade-offs where some types of queries cannot be improved because doing so would impact other types. When implementing for agents, the focus shifts to providing a wide toolbox for the agent to use to address their varied informational needs: broad and highly specific lexical recall, metadata attributes for filtering, grouping, and aggregation, as well as different ranking methods suited to different needs.
Developers working on agentic search should shift their focus from replicating search for average humans the much richer capabilities traditionally provided by solutions for competent professionals.
It’s time to let your agents search like a 2010 quant.